diff --git a/bgpranking/bgpranking.py b/bgpranking/bgpranking.py index 9c53cbd..1b5eb6b 100644 --- a/bgpranking/bgpranking.py +++ b/bgpranking/bgpranking.py @@ -256,7 +256,6 @@ class BGPRanking(): if (not response.get('data') or not response['data'].get('countries') or not response['data']['countries'][0].get('routed')): logging.warning(f'Invalid response: {response}') - # FIXME: return something return 0, [(0, 0)] routed_asns = re.findall(r"AsnSingle\(([\d]*)\)", response['data']['countries'][0]['routed']) ranks = [self.asn_rank(asn, d, source, ipversion)['response'] for asn in routed_asns] diff --git a/ranking/kvrocks.conf b/ranking/kvrocks.conf index 6de8c63..e3be5bc 100644 --- a/ranking/kvrocks.conf +++ b/ranking/kvrocks.conf @@ -1,52 +1,79 @@ ################################ GENERAL ##################################### -# By default kvrocks listens for connections from all the network interfaces -# available on the server. It is possible to listen to just one or multiple -# interfaces using the "bind" configuration directive, followed by one or -# more IP addresses. +# By default kvrocks listens for connections from localhost interface. +# It is possible to listen to just one or multiple interfaces using +# the "bind" configuration directive, followed by one or more IP addresses. # # Examples: # # bind 192.168.1.100 10.0.0.1 +# bind 127.0.0.1 ::1 +# bind 0.0.0.0 # bind 127.0.0.1 bind 0.0.0.0 +# Unix socket. +# +# Specify the path for the unix socket that will be used to listen for +# incoming connections. There is no default, so kvrocks will not listen +# on a unix socket when not specified. +# +unixsocket ranking.sock +unixsocketperm 777 + # Accept connections on the specified port, default is 6666. +# port 6666 port 5189 # Close the connection after a client is idle for N seconds (0 to disable) timeout 0 -# The number of worker's threads, increase or decrease it would effect the performance. +# The number of worker's threads, increase or decrease would affect the performance. workers 8 -# The number of replication worker's threads, increase or decrease it would effect the replication performance. -# Default: 1 -repl-workers 1 +# By default, kvrocks does not run as a daemon. Use 'yes' if you need it. +# Note that kvrocks will write a PID file in /var/run/kvrocks.pid when daemonized +daemonize yes -# By default kvrocks does not run as a daemon. Use 'yes' if you need it. -# Note that kvrocks will write a pid file in /var/run/kvrocks.pid when daemonized. -daemonize no - -# Kvrocks implements cluster solution that is similar with redis cluster sulution. +# Kvrocks implements the cluster solution that is similar to the Redis cluster solution. # You can get cluster information by CLUSTER NODES|SLOTS|INFO command, it also is -# adapted to redis-cli, redis-benchmark, redis cluster SDK and redis cluster proxy. -# But kvrocks doesn't support to communicate with each others, so you must set +# adapted to redis-cli, redis-benchmark, Redis cluster SDK, and Redis cluster proxy. +# But kvrocks doesn't support communicating with each other, so you must set # cluster topology by CLUSTER SETNODES|SETNODEID commands, more details: #219. # # PLEASE NOTE: # If you enable cluster, kvrocks will encode key with its slot id calculated by -# CRC16 and modulo 16384, endoding key with its slot id makes it efficient to -# migrate keys based on slot. So if you enabled at first time, cluster mode must +# CRC16 and modulo 16384, encoding key with its slot id makes it efficient to +# migrate keys based on the slot. So if you enabled at first time, cluster mode must # not be disabled after restarting, and vice versa. That is to say, data is not # compatible between standalone mode with cluster mode, you must migrate data # if you want to change mode, otherwise, kvrocks will make data corrupt. # # Default: no + cluster-enabled no +# By default, namespaces are stored in the configuration file and won't be replicated +# to replicas. This option allows to change this behavior, so that namespaces are also +# propagated to slaves. Note that: +# 1) it won't replicate the 'masterauth' to prevent breaking master/replica replication +# 2) it will overwrite replica's namespace with master's namespace, so be careful of in-using namespaces +# 3) cannot switch off the namespace replication once it's enabled +# +# Default: no +repl-namespace-enabled no + +# Persist the cluster nodes topology in local file($dir/nodes.conf). This configuration +# takes effect only if the cluster mode was enabled. +# +# If yes, it will try to load the cluster topology from the local file when starting, +# and dump the cluster nodes into the file if it was changed. +# +# Default: yes +persist-cluster-nodes-enabled yes + # Set the max number of connected clients at the same time. By default -# this limit is set to 10000 clients, however if the server is not +# this limit is set to 10000 clients. However, if the server is not # able to configure the process file limit to allow for the specified limit # the max number of allowed clients is set to the current file limit # @@ -70,15 +97,15 @@ maxclients 10000 # If the master is password protected (using the "masterauth" configuration # directive below) it is possible to tell the slave to authenticate before -# starting the replication synchronization process, otherwise the master will +# starting the replication synchronization process. Otherwise, the master will # refuse the slave request. # # masterauth foobared # Master-Salve replication would check db name is matched. if not, the slave should -# refuse to sync the db from master. Don't use default value, set the db-name to identify +# refuse to sync the db from master. Don't use the default value, set the db-name to identify # the cluster. -db-name storage.db +db-name ranking.db # The working directory # @@ -86,12 +113,28 @@ db-name storage.db # Note that you must specify a directory here, not a file name. dir ./ -# The logs of server will be stored in this directory. If you don't specify -# one directory, by default, we store logs in the working directory that set -# by 'dir' above. -# log-dir /tmp/kvrocks +# You can configure where to store your server logs by the log-dir. +# If you don't specify one, we will use the above `dir` as our default log directory. +# We also can send logs to stdout/stderr is as simple as: +# +log-dir stdout -# When running daemonized, kvrocks writes a pid file in ${CONFIG_DIR}/kvrocks.pid by +# Log level +# Possible values: info, warning, error, fatal +# Default: info +log-level info + +# You can configure log-retention-days to control whether to enable the log cleaner +# and the maximum retention days that the INFO level logs will be kept. +# +# if set to -1, that means to disable the log cleaner. +# if set to 0, all previous INFO level logs will be immediately removed. +# if set to between 0 to INT_MAX, that means it will retent latest N(log-retention-days) day logs. + +# By default the log-retention-days is -1. +log-retention-days -1 + +# When running in daemonize mode, kvrocks writes a PID file in ${CONFIG_DIR}/kvrocks.pid by # default. You can specify a custom pid file location here. # pidfile /var/run/kvrocks.pid pidfile storage.pid @@ -138,6 +181,20 @@ tcp-backlog 511 # connect 'master's listening port' when synchronization. master-use-repl-port no +# Currently, master only checks sequence number when replica asks for PSYNC, +# that is not enough since they may have different replication histories even +# the replica asking sequence is in the range of the master current WAL. +# +# We design 'Replication Sequence ID' PSYNC, we add unique replication id for +# every write batch (the operation of each command on the storage engine), so +# the combination of replication id and sequence is unique for write batch. +# The master can identify whether the replica has the same replication history +# by checking replication id and sequence. +# +# By default, it is not enabled since this stricter check may easily lead to +# full synchronization. +use-rsid-psync no + # Master-Slave replication. Use slaveof to make a kvrocks instance a copy of # another kvrocks server. A few things to understand ASAP about kvrocks replication. # @@ -159,11 +216,11 @@ master-use-repl-port no # is still in progress, the slave can act in two different ways: # # 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will -# still reply to client requests, possibly with out of date data, or the +# still reply to client requests, possibly with out-of-date data, or the # data set may just be empty if this is the first synchronization. # # 2) if slave-serve-stale-data is set to 'no' the slave will reply with -# an error "SYNC with master in progress" to all the kind of commands +# an error "SYNC with master in progress" to all kinds of commands # but to INFO and SLAVEOF. # slave-serve-stale-data yes @@ -182,6 +239,35 @@ slave-serve-stale-data yes # Default: no slave-empty-db-before-fullsync no +# A Kvrocks master is able to list the address and port of the attached +# replicas in different ways. For example the "INFO replication" section +# offers this information, which is used, among other tools, by +# Redis Sentinel in order to discover replica instances. +# Another place where this info is available is in the output of the +# "ROLE" command of a master. +# +# The listed IP address and port normally reported by a replica is +# obtained in the following way: +# +# IP: The address is auto detected by checking the peer address +# of the socket used by the replica to connect with the master. +# +# Port: The port is communicated by the replica during the replication +# handshake, and is normally the port that the replica is using to +# listen for connections. +# +# However when port forwarding or Network Address Translation (NAT) is +# used, the replica may actually be reachable via different IP and port +# pairs. The following two options can be used by a replica in order to +# report to its master a specific set of IP and port, so that both INFO +# and ROLE will report those values. +# +# There is no need to use both the options if you need to override just +# the port or the IP address. +# +# replica-announce-ip 5.5.5.5 +# replica-announce-port 1234 + # If replicas need full synchronization with master, master need to create # checkpoint for feeding replicas, and replicas also stage a checkpoint of # the master. If we also keep the backup, it maybe occupy extra disk space. @@ -191,7 +277,7 @@ slave-empty-db-before-fullsync no # Default: no purge-backup-on-fullsync no -# The maximum allowed rate (in MB/s) that should be used by Replication. +# The maximum allowed rate (in MB/s) that should be used by replication. # If the rate exceeds max-replication-mb, replication will slow down. # Default: 0 (i.e. no limit) max-replication-mb 0 @@ -199,8 +285,8 @@ max-replication-mb 0 # The maximum allowed aggregated write rate of flush and compaction (in MB/s). # If the rate exceeds max-io-mb, io will slow down. # 0 is no limit -# Default: 500 -max-io-mb 500 +# Default: 0 +max-io-mb 0 # The maximum allowed space (in GB) that should be used by RocksDB. # If the total size of the SST files exceeds max_allowed_space, writes to RocksDB will fail. @@ -210,33 +296,130 @@ max-db-size 0 # The maximum backup to keep, server cron would run every minutes to check the num of current # backup, and purge the old backup if exceed the max backup num to keep. If max-backup-to-keep -# is 0, no backup would be keep. But now, we only support 0 or 1. +# is 0, no backup would be kept. But now, we only support 0 or 1. max-backup-to-keep 1 # The maximum hours to keep the backup. If max-backup-keep-hours is 0, wouldn't purge any backup. # default: 1 day max-backup-keep-hours 24 -# Ratio of the samples would be recorded when the profiling was enabled. -# we simply use the rand to determine whether to record the sample or not. +# max-bitmap-to-string-mb use to limit the max size of bitmap to string transformation(MB). # -# Default: 0 -profiling-sample-ratio 0 +# Default: 16 +max-bitmap-to-string-mb 16 -# There is no limit to this length. Just be aware that it will consume memory. -# You can reclaim memory used by the perf log with PERFLOG RESET. -# -# Default: 256 -profiling-sample-record-max-len 256 +# Whether to enable SCAN-like cursor compatible with Redis. +# If enabled, the cursor will be unsigned 64-bit integers. +# If disabled, the cursor will be a string. +# Default: no +redis-cursor-compatible yes -# profiling-sample-record-threshold-ms use to tell the kvrocks when to record. +# Whether to enable the RESP3 protocol. +# NOTICE: RESP3 is still under development, don't enable it in production environment. # -# Default: 100 millisecond -profiling-sample-record-threshold-ms 100 +# Default: no +# resp3-enabled no + +# Maximum nesting depth allowed when parsing and serializing +# JSON documents while using JSON commands like JSON.SET. +# Default: 1024 +json-max-nesting-depth 1024 + +# The underlying storage format of JSON data type +# NOTE: This option only affects newly written/updated key-values +# The CBOR format may reduce the storage size and speed up JSON commands +# Available values: json, cbor +# Default: json +json-storage-format json + +################################## TLS ################################### + +# By default, TLS/SSL is disabled, i.e. `tls-port` is set to 0. +# To enable it, `tls-port` can be used to define TLS-listening ports. +# tls-port 0 + +# Configure a X.509 certificate and private key to use for authenticating the +# server to connected clients, masters or cluster peers. +# These files should be PEM formatted. +# +# tls-cert-file kvrocks.crt +# tls-key-file kvrocks.key + +# If the key file is encrypted using a passphrase, it can be included here +# as well. +# +# tls-key-file-pass secret + +# Configure a CA certificate(s) bundle or directory to authenticate TLS/SSL +# clients and peers. Kvrocks requires an explicit configuration of at least one +# of these, and will not implicitly use the system wide configuration. +# +# tls-ca-cert-file ca.crt +# tls-ca-cert-dir /etc/ssl/certs + +# By default, clients on a TLS port are required +# to authenticate using valid client side certificates. +# +# If "no" is specified, client certificates are not required and not accepted. +# If "optional" is specified, client certificates are accepted and must be +# valid if provided, but are not required. +# +# tls-auth-clients no +# tls-auth-clients optional + +# By default, only TLSv1.2 and TLSv1.3 are enabled and it is highly recommended +# that older formally deprecated versions are kept disabled to reduce the attack surface. +# You can explicitly specify TLS versions to support. +# Allowed values are case insensitive and include "TLSv1", "TLSv1.1", "TLSv1.2", +# "TLSv1.3" (OpenSSL >= 1.1.1) or any combination. +# To enable only TLSv1.2 and TLSv1.3, use: +# +# tls-protocols "TLSv1.2 TLSv1.3" + +# Configure allowed ciphers. See the ciphers(1ssl) manpage for more information +# about the syntax of this string. +# +# Note: this configuration applies only to <= TLSv1.2. +# +# tls-ciphers DEFAULT:!MEDIUM + +# Configure allowed TLSv1.3 ciphersuites. See the ciphers(1ssl) manpage for more +# information about the syntax of this string, and specifically for TLSv1.3 +# ciphersuites. +# +# tls-ciphersuites TLS_CHACHA20_POLY1305_SHA256 + +# When choosing a cipher, use the server's preference instead of the client +# preference. By default, the server follows the client's preference. +# +# tls-prefer-server-ciphers yes + +# By default, TLS session caching is enabled to allow faster and less expensive +# reconnections by clients that support it. Use the following directive to disable +# caching. +# +# tls-session-caching no + +# Change the default number of TLS sessions cached. A zero value sets the cache +# to unlimited size. The default size is 20480. +# +# tls-session-cache-size 5000 + +# Change the default timeout of cached TLS sessions. The default timeout is 300 +# seconds. +# +# tls-session-cache-timeout 60 + +# By default, a replica does not attempt to establish a TLS connection +# with its master. +# +# Use the following directive to enable TLS on replication links. +# +# tls-replication yes ################################## SLOW LOG ################################### -# The Kvrocks Slow Log is a system to log queries that exceeded a specified +# The Kvrocks Slow Log is a mechanism to log queries that exceeded a specified # execution time. The execution time does not include the I/O operations # like talking with the client, sending the reply and so forth, # but just the time needed to actually execute the command (this is the only @@ -269,6 +452,46 @@ slowlog-max-len 128 # They do not enable continuous liveness pings back to your supervisor. supervised no +################################## PERF LOG ################################### + +# The Kvrocks Perf Log is a mechanism to log queries' performance context that +# exceeded a specified execution time. This mechanism uses rocksdb's +# Perf Context and IO Stats Context, Please see: +# https://github.com/facebook/rocksdb/wiki/Perf-Context-and-IO-Stats-Context +# +# This mechanism is enabled when profiling-sample-commands is not empty and +# profiling-sample-ratio greater than 0. +# It is important to note that this mechanism affects performance, but it is +# useful for troubleshooting performance bottlenecks, so it should only be +# enabled when performance problems occur. + +# The name of the commands you want to record. Must be original name of +# commands supported by Kvrocks. Use ',' to separate multiple commands and +# use '*' to record all commands supported by Kvrocks. +# Example: +# - Single command: profiling-sample-commands get +# - Multiple commands: profiling-sample-commands get,mget,hget +# +# Default: empty +# profiling-sample-commands "" + +# Ratio of the samples would be recorded. It is a number between 0 and 100. +# We simply use the rand to determine whether to record the sample or not. +# +# Default: 0 +profiling-sample-ratio 0 + +# There is no limit to this length. Just be aware that it will consume memory. +# You can reclaim memory used by the perf log with PERFLOG RESET. +# +# Default: 256 +profiling-sample-record-max-len 256 + +# profiling-sample-record-threshold-ms use to tell the kvrocks when to record. +# +# Default: 100 millisecond +profiling-sample-record-threshold-ms 100 + ################################## CRON ################################### # Compact Scheduler, auto compact at schedule time @@ -282,15 +505,27 @@ supervised no # 0-7am every day. compaction-checker-range 0-7 -# Bgsave scheduler, auto bgsave at schedule time +# When the compaction checker is triggered, the db will periodically pick the SST file +# with the highest "deleted percentage" (i.e. the percentage of deleted keys in the SST +# file) to compact, in order to free disk space. +# However, if a specific SST file was created more than "force-compact-file-age" seconds +# ago, and its percentage of deleted keys is higher than +# "force-compact-file-min-deleted-percentage", it will be forcely compacted as well. + +# Default: 172800 seconds; Range: [60, INT64_MAX]; +# force-compact-file-age 172800 +# Default: 10 %; Range: [1, 100]; +# force-compact-file-min-deleted-percentage 10 + +# Bgsave scheduler, auto bgsave at scheduled time # time expression format is the same as crontab(currently only support * and int) # e.g. bgsave-cron 0 3 * * * 0 4 * * * -# would bgsave the db at 3am and 4am everyday +# would bgsave the db at 3am and 4am every day # Command renaming. # # It is possible to change the name of dangerous commands in a shared -# environment. For instance the KEYS command may be renamed into something +# environment. For instance, the KEYS command may be renamed into something # hard to guess so that it will still be available for internal-use tools # but not available for general clients. # @@ -303,44 +538,86 @@ compaction-checker-range 0-7 # # rename-command KEYS "" -# The key-value size may so be quite different in many scenes, and use 256MiB as SST file size -# may cause data loading(large index/filter block) ineffective when the key-value was too small. -# kvrocks supports user-defined SST file in config(rocksdb.target_file_size_base), -# but it still too trivial and inconvenient to adjust the different sizes for different instances. -# so we want to periodic auto-adjust the SST size in-flight with user avg key-value size. +################################ MIGRATE ##################################### +# Slot migration supports two ways: +# - redis-command: Migrate data by redis serialization protocol(RESP). +# - raw-key-value: Migrate the raw key value data of the storage engine directly. +# This way eliminates the overhead of converting to the redis +# command, reduces resource consumption, improves migration +# efficiency, and can implement a finer rate limit. # -# If enabled, kvrocks will auto resize rocksdb.target_file_size_base -# and rocksdb.write_buffer_size in-flight with user avg key-value size. -# Please see #118. +# Default: redis-command +migrate-type redis-command + +# If the network bandwidth is completely consumed by the migration task, +# it will affect the availability of kvrocks. To avoid this situation, +# migrate-speed is adopted to limit the migrating speed. +# Migrating speed is limited by controlling the duration between sending data, +# the duration is calculated by: 1000000 * migrate-pipeline-size / migrate-speed (us). +# Value: [0,INT_MAX], 0 means no limit # -# Default: yes -auto-resize-block-and-sst yes +# Default: 4096 +migrate-speed 4096 + +# In order to reduce data transmission times and improve the efficiency of data migration, +# pipeline is adopted to send multiple data at once. Pipeline size can be set by this option. +# Value: [1, INT_MAX], it can't be 0 +# +# Default: 16 +migrate-pipeline-size 16 + +# In order to reduce the write forbidden time during migrating slot, we will migrate the incremental +# data several times to reduce the amount of incremental data. Until the quantity of incremental +# data is reduced to a certain threshold, slot will be forbidden write. The threshold is set by +# this option. +# Value: [1, INT_MAX], it can't be 0 +# +# Default: 10000 +migrate-sequence-gap 10000 + +# The raw-key-value migration way uses batch for migration. This option sets the batch size +# for each migration. +# +# Default: 16kb +migrate-batch-size-kb 16 + +# Rate limit for migration based on raw-key-value, representing the maximum number of data +# that can be migrated per second. 0 means no limit. +# +# Default: 16M +migrate-batch-rate-limit-mb 16 ################################ ROCKSDB ##################################### -# Specify the capacity of metadata column family block cache. Larger block cache -# may make request faster while more keys would be cached. Max Size is 200*1024. -# Default: 2048MB -rocksdb.metadata_block_cache_size 2048 +# Specify the capacity of column family block cache. A larger block cache +# may make requests faster while more keys would be cached. Max Size is 400*1024. +# Default: 4096MB +rocksdb.block_cache_size 4096 -# Specify the capacity of subkey column family block cache. Larger block cache -# may make request faster while more keys would be cached. Max Size is 200*1024. -# Default: 2048MB -rocksdb.subkey_block_cache_size 2048 - -# Metadata column family and subkey column family will share a single block cache -# if set 'yes'. The capacity of shared block cache is -# metadata_block_cache_size + subkey_block_cache_size +# Specify the type of cache used in the block cache. +# Accept value: "lru", "hcc" +# "lru" stands for the cache with the LRU(Least Recently Used) replacement policy. # -# Default: yes -rocksdb.share_metadata_and_subkey_block_cache yes +# "hcc" stands for the Hyper Clock Cache, a lock-free cache alternative +# that offers much improved CPU efficiency vs. LRU cache under high parallel +# load or high contention. +# +# default lru +rocksdb.block_cache_type lru + +# A global cache for table-level rows in RocksDB. If almost always point +# lookups, enlarging row cache may improve read performance. Otherwise, +# if we enlarge this value, we can lessen metadata/subkey block cache size. +# +# Default: 0 (disabled) +rocksdb.row_cache_size 0 # Number of open files that can be used by the DB. You may need to # increase this if your database has a large working set. Value -1 means # files opened are always kept open. You can estimate number of files based # on target_file_size_base and target_file_size_multiplier for level-based # compaction. For universal-style compaction, you can usually set it to -1. -# Default: 4096 +# Default: 8096 rocksdb.max_open_files 8096 # Amount of data to build up in memory (backed by an unsorted log @@ -357,13 +634,13 @@ rocksdb.max_open_files 8096 # See db_write_buffer_size for sharing memory across column families. # default is 64MB -rocksdb.write_buffer_size 16 +rocksdb.write_buffer_size 64 -# Target file size for compaction, target file size for Leve N can be caculated +# Target file size for compaction, target file size for Level N can be calculated # by target_file_size_base * (target_file_size_multiplier ^ (L-1)) # # Default: 128MB -rocksdb.target_file_size_base 16 +rocksdb.target_file_size_base 128 # The maximum number of write buffers that are built up in memory. # The default and the minimum number is 2, so that when 1 write buffer @@ -374,20 +651,29 @@ rocksdb.target_file_size_base 16 # allowed. rocksdb.max_write_buffer_number 4 +# Maximum number of concurrent background jobs (compactions and flushes). +# For backwards compatibility we will set `max_background_jobs = +# max_background_compactions + max_background_flushes` in the case where user +# sets at least one of `max_background_compactions` or `max_background_flushes` +# (we replace -1 by 1 in case one option is unset). +rocksdb.max_background_jobs 4 + +# DEPRECATED: it is automatically decided based on the value of rocksdb.max_background_jobs # Maximum number of concurrent background compaction jobs, submitted to # the default LOW priority thread pool. -rocksdb.max_background_compactions 4 +rocksdb.max_background_compactions -1 +# DEPRECATED: it is automatically decided based on the value of rocksdb.max_background_jobs # Maximum number of concurrent background memtable flush jobs, submitted by # default to the HIGH priority thread pool. If the HIGH priority thread pool # is configured to have zero threads, flush jobs will share the LOW priority # thread pool with compaction jobs. -rocksdb.max_background_flushes 4 +rocksdb.max_background_flushes -1 # This value represents the maximum number of threads that will # concurrently perform a compaction job by breaking it into multiple, # smaller ones that are run simultaneously. -# Default: 2 (i.e. no subcompactions) +# Default: 2 rocksdb.max_sub_compactions 2 # In order to limit the size of WALs, RocksDB uses DBOptions::max_total_wal_size @@ -411,8 +697,8 @@ rocksdb.max_sub_compactions 2 # default is 512MB rocksdb.max_total_wal_size 512 -# We impl the repliction with rocksdb WAL, it would trigger full sync when the seq was out of range. -# wal_ttl_seconds and wal_size_limit_mb would affect how archived logswill be deleted. +# We implement the replication with rocksdb WAL, it would trigger full sync when the seq was out of range. +# wal_ttl_seconds and wal_size_limit_mb would affect how archived logs will be deleted. # If WAL_ttl_seconds is not 0, then WAL files will be checked every WAL_ttl_seconds / 2 and those that # are older than WAL_ttl_seconds will be deleted# # @@ -422,25 +708,25 @@ rocksdb.wal_ttl_seconds 10800 # If WAL_ttl_seconds is 0 and WAL_size_limit_MB is not 0, # WAL files will be checked every 10 min and if total size is greater # then WAL_size_limit_MB, they will be deleted starting with the -# earliest until size_limit is met. All empty files will be deleted +# earliest until size_limit is met. All empty files will be deleted # Default: 16GB rocksdb.wal_size_limit_mb 16384 # Approximate size of user data packed per block. Note that the -# block size specified here corresponds to uncompressed data. The +# block size specified here corresponds to uncompressed data. The # actual size of the unit read from disk may be smaller if # compression is enabled. # -# Default: 4KB -rocksdb.block_size 2048 +# Default: 16KB +rocksdb.block_size 16384 # Indicating if we'd put index/filter blocks to the block cache # -# Default: no +# Default: yes rocksdb.cache_index_and_filter_blocks yes # Specify the compression to use. -# Accept value: "no", "snappy" +# Accept value: "no", "snappy", "lz4", "zstd", "zlib" # default snappy rocksdb.compression snappy @@ -480,6 +766,11 @@ rocksdb.level0_slowdown_writes_trigger 20 # Default: 40 rocksdb.level0_stop_writes_trigger 40 +# Number of files to trigger level-0 compaction. +# +# Default: 4 +rocksdb.level0_file_num_compaction_trigger 4 + # if not zero, dump rocksdb.stats to LOG every stats_dump_period_sec # # Default: 0 @@ -489,9 +780,138 @@ rocksdb.stats_dump_period_sec 0 # # Default: no rocksdb.disable_auto_compactions no + +# BlobDB(key-value separation) is essentially RocksDB for large-value use cases. +# Since 6.18.0, The new implementation is integrated into the RocksDB core. +# When set, large values (blobs) are written to separate blob files, and only +# pointers to them are stored in SST files. This can reduce write amplification +# for large-value use cases at the cost of introducing a level of indirection +# for reads. Please see: https://github.com/facebook/rocksdb/wiki/BlobDB. +# +# Note that when enable_blob_files is set to yes, BlobDB-related configuration +# items will take effect. +# +# Default: no +rocksdb.enable_blob_files no + +# The size of the smallest value to be stored separately in a blob file. Values +# which have an uncompressed size smaller than this threshold are stored alongside +# the keys in SST files in the usual fashion. +# +# Default: 4096 byte, 0 means that all values are stored in blob files +rocksdb.min_blob_size 4096 + +# The size limit for blob files. When writing blob files, a new file is +# opened once this limit is reached. +# +# Default: 268435456 bytes +rocksdb.blob_file_size 268435456 + +# Enables garbage collection of blobs. Valid blobs residing in blob files +# older than a cutoff get relocated to new files as they are encountered +# during compaction, which makes it possible to clean up blob files once +# they contain nothing but obsolete/garbage blobs. +# See also rocksdb.blob_garbage_collection_age_cutoff below. +# +# Default: yes +rocksdb.enable_blob_garbage_collection yes + +# The percentage cutoff in terms of blob file age for garbage collection. +# Blobs in the oldest N blob files will be relocated when encountered during +# compaction, where N = (garbage_collection_cutoff/100) * number_of_blob_files. +# Note that this value must belong to [0, 100]. +# +# Default: 25 +rocksdb.blob_garbage_collection_age_cutoff 25 + + +# The purpose of the following three options are to dynamically adjust the upper limit of +# the data that each layer can store according to the size of the different +# layers of the LSM. Enabling this option will bring some improvements in +# deletion efficiency and space amplification, but it will lose a certain +# amount of read performance. +# If you want to know more details about Levels' Target Size, you can read RocksDB wiki: +# https://github.com/facebook/rocksdb/wiki/Leveled-Compaction#levels-target-size +# +# Default: yes +rocksdb.level_compaction_dynamic_level_bytes yes + +# The total file size of level-1 sst. +# +# Default: 268435456 bytes +rocksdb.max_bytes_for_level_base 268435456 + +# Multiplication factor for the total file size of L(n+1) layers. +# This option is a double type number in RocksDB, but kvrocks is +# not support the double data type number yet, so we use integer +# number instead of double currently. +# +# Default: 10 +rocksdb.max_bytes_for_level_multiplier 10 + +# This feature only takes effect in Iterators and MultiGet. +# If yes, RocksDB will try to read asynchronously and in parallel as much as possible to hide IO latency. +# In iterators, it will prefetch data asynchronously in the background for each file being iterated on. +# In MultiGet, it will read the necessary data blocks from those files in parallel as much as possible. + +# Default no +rocksdb.read_options.async_io no + +# If yes, the write will be flushed from the operating system +# buffer cache before the write is considered complete. +# If this flag is enabled, writes will be slower. +# If this flag is disabled, and the machine crashes, some recent +# writes may be lost. Note that if it is just the process that +# crashes (i.e., the machine does not reboot), no writes will be +# lost even if sync==false. +# +# Default: no +rocksdb.write_options.sync no + +# If yes, writes will not first go to the write ahead log, +# and the write may get lost after a crash. +# You must keep wal enabled if you use replication. +# +# Default: no +rocksdb.write_options.disable_wal no + +# If enabled and we need to wait or sleep for the write request, fails +# immediately. +# +# Default: no +rocksdb.write_options.no_slowdown no + +# If enabled, write requests are of lower priority if compaction is +# behind. In this case, no_slowdown = true, the request will be canceled +# immediately. Otherwise, it will be slowed down. +# The slowdown value is determined by RocksDB to guarantee +# it introduces minimum impacts to high priority writes. +# +# Default: no +rocksdb.write_options.low_pri no + +# If enabled, this writebatch will maintain the last insert positions of each +# memtable as hints in concurrent write. It can improve write performance +# in concurrent writes if keys in one writebatch are sequential. +# +# Default: no +rocksdb.write_options.memtable_insert_hint_per_batch no + + +# Support RocksDB auto-tune rate limiter for the background IO +# if enabled, Rate limiter will limit the compaction write if flush write is high +# Please see https://rocksdb.org/blog/2017/12/18/17-auto-tuned-rate-limiter.html +# +# Default: yes +rocksdb.rate_limiter_auto_tuned yes + +# Enable this option will schedule the deletion of obsolete files in a background thread +# on iterator destruction. It can reduce the latency if there are many files to be removed. +# see https://github.com/facebook/rocksdb/wiki/IO#avoid-blocking-io +# +# Default: yes +# rocksdb.avoid_unnecessary_blocking_io yes + ################################ NAMESPACE ##################################### # namespace.test change.me - - backup-dir .//backup -log-dir ./ diff --git a/storage/kvrocks.conf b/storage/kvrocks.conf index 91c3957..3f34cc5 100644 --- a/storage/kvrocks.conf +++ b/storage/kvrocks.conf @@ -1,52 +1,79 @@ ################################ GENERAL ##################################### -# By default kvrocks listens for connections from all the network interfaces -# available on the server. It is possible to listen to just one or multiple -# interfaces using the "bind" configuration directive, followed by one or -# more IP addresses. +# By default kvrocks listens for connections from localhost interface. +# It is possible to listen to just one or multiple interfaces using +# the "bind" configuration directive, followed by one or more IP addresses. # # Examples: # # bind 192.168.1.100 10.0.0.1 +# bind 127.0.0.1 ::1 +# bind 0.0.0.0 # bind 127.0.0.1 bind 0.0.0.0 +# Unix socket. +# +# Specify the path for the unix socket that will be used to listen for +# incoming connections. There is no default, so kvrocks will not listen +# on a unix socket when not specified. +# +unixsocket storage.sock +unixsocketperm 777 + # Accept connections on the specified port, default is 6666. +# port 6666 port 5188 # Close the connection after a client is idle for N seconds (0 to disable) timeout 0 -# The number of worker's threads, increase or decrease it would effect the performance. +# The number of worker's threads, increase or decrease would affect the performance. workers 8 -# The number of replication worker's threads, increase or decrease it would effect the replication performance. -# Default: 1 -repl-workers 1 +# By default, kvrocks does not run as a daemon. Use 'yes' if you need it. +# Note that kvrocks will write a PID file in /var/run/kvrocks.pid when daemonized +daemonize yes -# By default kvrocks does not run as a daemon. Use 'yes' if you need it. -# Note that kvrocks will write a pid file in /var/run/kvrocks.pid when daemonized. -daemonize no - -# Kvrocks implements cluster solution that is similar with redis cluster sulution. +# Kvrocks implements the cluster solution that is similar to the Redis cluster solution. # You can get cluster information by CLUSTER NODES|SLOTS|INFO command, it also is -# adapted to redis-cli, redis-benchmark, redis cluster SDK and redis cluster proxy. -# But kvrocks doesn't support to communicate with each others, so you must set +# adapted to redis-cli, redis-benchmark, Redis cluster SDK, and Redis cluster proxy. +# But kvrocks doesn't support communicating with each other, so you must set # cluster topology by CLUSTER SETNODES|SETNODEID commands, more details: #219. # # PLEASE NOTE: # If you enable cluster, kvrocks will encode key with its slot id calculated by -# CRC16 and modulo 16384, endoding key with its slot id makes it efficient to -# migrate keys based on slot. So if you enabled at first time, cluster mode must +# CRC16 and modulo 16384, encoding key with its slot id makes it efficient to +# migrate keys based on the slot. So if you enabled at first time, cluster mode must # not be disabled after restarting, and vice versa. That is to say, data is not # compatible between standalone mode with cluster mode, you must migrate data # if you want to change mode, otherwise, kvrocks will make data corrupt. # # Default: no + cluster-enabled no +# By default, namespaces are stored in the configuration file and won't be replicated +# to replicas. This option allows to change this behavior, so that namespaces are also +# propagated to slaves. Note that: +# 1) it won't replicate the 'masterauth' to prevent breaking master/replica replication +# 2) it will overwrite replica's namespace with master's namespace, so be careful of in-using namespaces +# 3) cannot switch off the namespace replication once it's enabled +# +# Default: no +repl-namespace-enabled no + +# Persist the cluster nodes topology in local file($dir/nodes.conf). This configuration +# takes effect only if the cluster mode was enabled. +# +# If yes, it will try to load the cluster topology from the local file when starting, +# and dump the cluster nodes into the file if it was changed. +# +# Default: yes +persist-cluster-nodes-enabled yes + # Set the max number of connected clients at the same time. By default -# this limit is set to 10000 clients, however if the server is not +# this limit is set to 10000 clients. However, if the server is not # able to configure the process file limit to allow for the specified limit # the max number of allowed clients is set to the current file limit # @@ -70,13 +97,13 @@ maxclients 10000 # If the master is password protected (using the "masterauth" configuration # directive below) it is possible to tell the slave to authenticate before -# starting the replication synchronization process, otherwise the master will +# starting the replication synchronization process. Otherwise, the master will # refuse the slave request. # # masterauth foobared # Master-Salve replication would check db name is matched. if not, the slave should -# refuse to sync the db from master. Don't use default value, set the db-name to identify +# refuse to sync the db from master. Don't use the default value, set the db-name to identify # the cluster. db-name storage.db @@ -86,12 +113,28 @@ db-name storage.db # Note that you must specify a directory here, not a file name. dir ./ -# The logs of server will be stored in this directory. If you don't specify -# one directory, by default, we store logs in the working directory that set -# by 'dir' above. -# log-dir /tmp/kvrocks +# You can configure where to store your server logs by the log-dir. +# If you don't specify one, we will use the above `dir` as our default log directory. +# We also can send logs to stdout/stderr is as simple as: +# +log-dir stdout -# When running daemonized, kvrocks writes a pid file in ${CONFIG_DIR}/kvrocks.pid by +# Log level +# Possible values: info, warning, error, fatal +# Default: info +log-level info + +# You can configure log-retention-days to control whether to enable the log cleaner +# and the maximum retention days that the INFO level logs will be kept. +# +# if set to -1, that means to disable the log cleaner. +# if set to 0, all previous INFO level logs will be immediately removed. +# if set to between 0 to INT_MAX, that means it will retent latest N(log-retention-days) day logs. + +# By default the log-retention-days is -1. +log-retention-days -1 + +# When running in daemonize mode, kvrocks writes a PID file in ${CONFIG_DIR}/kvrocks.pid by # default. You can specify a custom pid file location here. # pidfile /var/run/kvrocks.pid pidfile storage.pid @@ -138,6 +181,20 @@ tcp-backlog 511 # connect 'master's listening port' when synchronization. master-use-repl-port no +# Currently, master only checks sequence number when replica asks for PSYNC, +# that is not enough since they may have different replication histories even +# the replica asking sequence is in the range of the master current WAL. +# +# We design 'Replication Sequence ID' PSYNC, we add unique replication id for +# every write batch (the operation of each command on the storage engine), so +# the combination of replication id and sequence is unique for write batch. +# The master can identify whether the replica has the same replication history +# by checking replication id and sequence. +# +# By default, it is not enabled since this stricter check may easily lead to +# full synchronization. +use-rsid-psync no + # Master-Slave replication. Use slaveof to make a kvrocks instance a copy of # another kvrocks server. A few things to understand ASAP about kvrocks replication. # @@ -159,11 +216,11 @@ master-use-repl-port no # is still in progress, the slave can act in two different ways: # # 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will -# still reply to client requests, possibly with out of date data, or the +# still reply to client requests, possibly with out-of-date data, or the # data set may just be empty if this is the first synchronization. # # 2) if slave-serve-stale-data is set to 'no' the slave will reply with -# an error "SYNC with master in progress" to all the kind of commands +# an error "SYNC with master in progress" to all kinds of commands # but to INFO and SLAVEOF. # slave-serve-stale-data yes @@ -182,6 +239,35 @@ slave-serve-stale-data yes # Default: no slave-empty-db-before-fullsync no +# A Kvrocks master is able to list the address and port of the attached +# replicas in different ways. For example the "INFO replication" section +# offers this information, which is used, among other tools, by +# Redis Sentinel in order to discover replica instances. +# Another place where this info is available is in the output of the +# "ROLE" command of a master. +# +# The listed IP address and port normally reported by a replica is +# obtained in the following way: +# +# IP: The address is auto detected by checking the peer address +# of the socket used by the replica to connect with the master. +# +# Port: The port is communicated by the replica during the replication +# handshake, and is normally the port that the replica is using to +# listen for connections. +# +# However when port forwarding or Network Address Translation (NAT) is +# used, the replica may actually be reachable via different IP and port +# pairs. The following two options can be used by a replica in order to +# report to its master a specific set of IP and port, so that both INFO +# and ROLE will report those values. +# +# There is no need to use both the options if you need to override just +# the port or the IP address. +# +# replica-announce-ip 5.5.5.5 +# replica-announce-port 1234 + # If replicas need full synchronization with master, master need to create # checkpoint for feeding replicas, and replicas also stage a checkpoint of # the master. If we also keep the backup, it maybe occupy extra disk space. @@ -191,7 +277,7 @@ slave-empty-db-before-fullsync no # Default: no purge-backup-on-fullsync no -# The maximum allowed rate (in MB/s) that should be used by Replication. +# The maximum allowed rate (in MB/s) that should be used by replication. # If the rate exceeds max-replication-mb, replication will slow down. # Default: 0 (i.e. no limit) max-replication-mb 0 @@ -199,8 +285,8 @@ max-replication-mb 0 # The maximum allowed aggregated write rate of flush and compaction (in MB/s). # If the rate exceeds max-io-mb, io will slow down. # 0 is no limit -# Default: 500 -max-io-mb 500 +# Default: 0 +max-io-mb 0 # The maximum allowed space (in GB) that should be used by RocksDB. # If the total size of the SST files exceeds max_allowed_space, writes to RocksDB will fail. @@ -210,33 +296,130 @@ max-db-size 0 # The maximum backup to keep, server cron would run every minutes to check the num of current # backup, and purge the old backup if exceed the max backup num to keep. If max-backup-to-keep -# is 0, no backup would be keep. But now, we only support 0 or 1. +# is 0, no backup would be kept. But now, we only support 0 or 1. max-backup-to-keep 1 # The maximum hours to keep the backup. If max-backup-keep-hours is 0, wouldn't purge any backup. # default: 1 day max-backup-keep-hours 24 -# Ratio of the samples would be recorded when the profiling was enabled. -# we simply use the rand to determine whether to record the sample or not. +# max-bitmap-to-string-mb use to limit the max size of bitmap to string transformation(MB). # -# Default: 0 -profiling-sample-ratio 0 +# Default: 16 +max-bitmap-to-string-mb 16 -# There is no limit to this length. Just be aware that it will consume memory. -# You can reclaim memory used by the perf log with PERFLOG RESET. -# -# Default: 256 -profiling-sample-record-max-len 256 +# Whether to enable SCAN-like cursor compatible with Redis. +# If enabled, the cursor will be unsigned 64-bit integers. +# If disabled, the cursor will be a string. +# Default: no +redis-cursor-compatible yes -# profiling-sample-record-threshold-ms use to tell the kvrocks when to record. +# Whether to enable the RESP3 protocol. +# NOTICE: RESP3 is still under development, don't enable it in production environment. # -# Default: 100 millisecond -profiling-sample-record-threshold-ms 100 +# Default: no +# resp3-enabled no + +# Maximum nesting depth allowed when parsing and serializing +# JSON documents while using JSON commands like JSON.SET. +# Default: 1024 +json-max-nesting-depth 1024 + +# The underlying storage format of JSON data type +# NOTE: This option only affects newly written/updated key-values +# The CBOR format may reduce the storage size and speed up JSON commands +# Available values: json, cbor +# Default: json +json-storage-format json + +################################## TLS ################################### + +# By default, TLS/SSL is disabled, i.e. `tls-port` is set to 0. +# To enable it, `tls-port` can be used to define TLS-listening ports. +# tls-port 0 + +# Configure a X.509 certificate and private key to use for authenticating the +# server to connected clients, masters or cluster peers. +# These files should be PEM formatted. +# +# tls-cert-file kvrocks.crt +# tls-key-file kvrocks.key + +# If the key file is encrypted using a passphrase, it can be included here +# as well. +# +# tls-key-file-pass secret + +# Configure a CA certificate(s) bundle or directory to authenticate TLS/SSL +# clients and peers. Kvrocks requires an explicit configuration of at least one +# of these, and will not implicitly use the system wide configuration. +# +# tls-ca-cert-file ca.crt +# tls-ca-cert-dir /etc/ssl/certs + +# By default, clients on a TLS port are required +# to authenticate using valid client side certificates. +# +# If "no" is specified, client certificates are not required and not accepted. +# If "optional" is specified, client certificates are accepted and must be +# valid if provided, but are not required. +# +# tls-auth-clients no +# tls-auth-clients optional + +# By default, only TLSv1.2 and TLSv1.3 are enabled and it is highly recommended +# that older formally deprecated versions are kept disabled to reduce the attack surface. +# You can explicitly specify TLS versions to support. +# Allowed values are case insensitive and include "TLSv1", "TLSv1.1", "TLSv1.2", +# "TLSv1.3" (OpenSSL >= 1.1.1) or any combination. +# To enable only TLSv1.2 and TLSv1.3, use: +# +# tls-protocols "TLSv1.2 TLSv1.3" + +# Configure allowed ciphers. See the ciphers(1ssl) manpage for more information +# about the syntax of this string. +# +# Note: this configuration applies only to <= TLSv1.2. +# +# tls-ciphers DEFAULT:!MEDIUM + +# Configure allowed TLSv1.3 ciphersuites. See the ciphers(1ssl) manpage for more +# information about the syntax of this string, and specifically for TLSv1.3 +# ciphersuites. +# +# tls-ciphersuites TLS_CHACHA20_POLY1305_SHA256 + +# When choosing a cipher, use the server's preference instead of the client +# preference. By default, the server follows the client's preference. +# +# tls-prefer-server-ciphers yes + +# By default, TLS session caching is enabled to allow faster and less expensive +# reconnections by clients that support it. Use the following directive to disable +# caching. +# +# tls-session-caching no + +# Change the default number of TLS sessions cached. A zero value sets the cache +# to unlimited size. The default size is 20480. +# +# tls-session-cache-size 5000 + +# Change the default timeout of cached TLS sessions. The default timeout is 300 +# seconds. +# +# tls-session-cache-timeout 60 + +# By default, a replica does not attempt to establish a TLS connection +# with its master. +# +# Use the following directive to enable TLS on replication links. +# +# tls-replication yes ################################## SLOW LOG ################################### -# The Kvrocks Slow Log is a system to log queries that exceeded a specified +# The Kvrocks Slow Log is a mechanism to log queries that exceeded a specified # execution time. The execution time does not include the I/O operations # like talking with the client, sending the reply and so forth, # but just the time needed to actually execute the command (this is the only @@ -269,6 +452,46 @@ slowlog-max-len 128 # They do not enable continuous liveness pings back to your supervisor. supervised no +################################## PERF LOG ################################### + +# The Kvrocks Perf Log is a mechanism to log queries' performance context that +# exceeded a specified execution time. This mechanism uses rocksdb's +# Perf Context and IO Stats Context, Please see: +# https://github.com/facebook/rocksdb/wiki/Perf-Context-and-IO-Stats-Context +# +# This mechanism is enabled when profiling-sample-commands is not empty and +# profiling-sample-ratio greater than 0. +# It is important to note that this mechanism affects performance, but it is +# useful for troubleshooting performance bottlenecks, so it should only be +# enabled when performance problems occur. + +# The name of the commands you want to record. Must be original name of +# commands supported by Kvrocks. Use ',' to separate multiple commands and +# use '*' to record all commands supported by Kvrocks. +# Example: +# - Single command: profiling-sample-commands get +# - Multiple commands: profiling-sample-commands get,mget,hget +# +# Default: empty +# profiling-sample-commands "" + +# Ratio of the samples would be recorded. It is a number between 0 and 100. +# We simply use the rand to determine whether to record the sample or not. +# +# Default: 0 +profiling-sample-ratio 0 + +# There is no limit to this length. Just be aware that it will consume memory. +# You can reclaim memory used by the perf log with PERFLOG RESET. +# +# Default: 256 +profiling-sample-record-max-len 256 + +# profiling-sample-record-threshold-ms use to tell the kvrocks when to record. +# +# Default: 100 millisecond +profiling-sample-record-threshold-ms 100 + ################################## CRON ################################### # Compact Scheduler, auto compact at schedule time @@ -282,15 +505,27 @@ supervised no # 0-7am every day. compaction-checker-range 0-7 -# Bgsave scheduler, auto bgsave at schedule time +# When the compaction checker is triggered, the db will periodically pick the SST file +# with the highest "deleted percentage" (i.e. the percentage of deleted keys in the SST +# file) to compact, in order to free disk space. +# However, if a specific SST file was created more than "force-compact-file-age" seconds +# ago, and its percentage of deleted keys is higher than +# "force-compact-file-min-deleted-percentage", it will be forcely compacted as well. + +# Default: 172800 seconds; Range: [60, INT64_MAX]; +# force-compact-file-age 172800 +# Default: 10 %; Range: [1, 100]; +# force-compact-file-min-deleted-percentage 10 + +# Bgsave scheduler, auto bgsave at scheduled time # time expression format is the same as crontab(currently only support * and int) # e.g. bgsave-cron 0 3 * * * 0 4 * * * -# would bgsave the db at 3am and 4am everyday +# would bgsave the db at 3am and 4am every day # Command renaming. # # It is possible to change the name of dangerous commands in a shared -# environment. For instance the KEYS command may be renamed into something +# environment. For instance, the KEYS command may be renamed into something # hard to guess so that it will still be available for internal-use tools # but not available for general clients. # @@ -303,44 +538,86 @@ compaction-checker-range 0-7 # # rename-command KEYS "" -# The key-value size may so be quite different in many scenes, and use 256MiB as SST file size -# may cause data loading(large index/filter block) ineffective when the key-value was too small. -# kvrocks supports user-defined SST file in config(rocksdb.target_file_size_base), -# but it still too trivial and inconvenient to adjust the different sizes for different instances. -# so we want to periodic auto-adjust the SST size in-flight with user avg key-value size. +################################ MIGRATE ##################################### +# Slot migration supports two ways: +# - redis-command: Migrate data by redis serialization protocol(RESP). +# - raw-key-value: Migrate the raw key value data of the storage engine directly. +# This way eliminates the overhead of converting to the redis +# command, reduces resource consumption, improves migration +# efficiency, and can implement a finer rate limit. # -# If enabled, kvrocks will auto resize rocksdb.target_file_size_base -# and rocksdb.write_buffer_size in-flight with user avg key-value size. -# Please see #118. +# Default: redis-command +migrate-type redis-command + +# If the network bandwidth is completely consumed by the migration task, +# it will affect the availability of kvrocks. To avoid this situation, +# migrate-speed is adopted to limit the migrating speed. +# Migrating speed is limited by controlling the duration between sending data, +# the duration is calculated by: 1000000 * migrate-pipeline-size / migrate-speed (us). +# Value: [0,INT_MAX], 0 means no limit # -# Default: yes -auto-resize-block-and-sst yes +# Default: 4096 +migrate-speed 4096 + +# In order to reduce data transmission times and improve the efficiency of data migration, +# pipeline is adopted to send multiple data at once. Pipeline size can be set by this option. +# Value: [1, INT_MAX], it can't be 0 +# +# Default: 16 +migrate-pipeline-size 16 + +# In order to reduce the write forbidden time during migrating slot, we will migrate the incremental +# data several times to reduce the amount of incremental data. Until the quantity of incremental +# data is reduced to a certain threshold, slot will be forbidden write. The threshold is set by +# this option. +# Value: [1, INT_MAX], it can't be 0 +# +# Default: 10000 +migrate-sequence-gap 10000 + +# The raw-key-value migration way uses batch for migration. This option sets the batch size +# for each migration. +# +# Default: 16kb +migrate-batch-size-kb 16 + +# Rate limit for migration based on raw-key-value, representing the maximum number of data +# that can be migrated per second. 0 means no limit. +# +# Default: 16M +migrate-batch-rate-limit-mb 16 ################################ ROCKSDB ##################################### -# Specify the capacity of metadata column family block cache. Larger block cache -# may make request faster while more keys would be cached. Max Size is 200*1024. -# Default: 2048MB -rocksdb.metadata_block_cache_size 2048 +# Specify the capacity of column family block cache. A larger block cache +# may make requests faster while more keys would be cached. Max Size is 400*1024. +# Default: 4096MB +rocksdb.block_cache_size 4096 -# Specify the capacity of subkey column family block cache. Larger block cache -# may make request faster while more keys would be cached. Max Size is 200*1024. -# Default: 2048MB -rocksdb.subkey_block_cache_size 2048 - -# Metadata column family and subkey column family will share a single block cache -# if set 'yes'. The capacity of shared block cache is -# metadata_block_cache_size + subkey_block_cache_size +# Specify the type of cache used in the block cache. +# Accept value: "lru", "hcc" +# "lru" stands for the cache with the LRU(Least Recently Used) replacement policy. # -# Default: yes -rocksdb.share_metadata_and_subkey_block_cache yes +# "hcc" stands for the Hyper Clock Cache, a lock-free cache alternative +# that offers much improved CPU efficiency vs. LRU cache under high parallel +# load or high contention. +# +# default lru +rocksdb.block_cache_type lru + +# A global cache for table-level rows in RocksDB. If almost always point +# lookups, enlarging row cache may improve read performance. Otherwise, +# if we enlarge this value, we can lessen metadata/subkey block cache size. +# +# Default: 0 (disabled) +rocksdb.row_cache_size 0 # Number of open files that can be used by the DB. You may need to # increase this if your database has a large working set. Value -1 means # files opened are always kept open. You can estimate number of files based # on target_file_size_base and target_file_size_multiplier for level-based # compaction. For universal-style compaction, you can usually set it to -1. -# Default: 4096 +# Default: 8096 rocksdb.max_open_files 8096 # Amount of data to build up in memory (backed by an unsorted log @@ -357,13 +634,13 @@ rocksdb.max_open_files 8096 # See db_write_buffer_size for sharing memory across column families. # default is 64MB -rocksdb.write_buffer_size 16 +rocksdb.write_buffer_size 64 -# Target file size for compaction, target file size for Leve N can be caculated +# Target file size for compaction, target file size for Level N can be calculated # by target_file_size_base * (target_file_size_multiplier ^ (L-1)) # # Default: 128MB -rocksdb.target_file_size_base 16 +rocksdb.target_file_size_base 128 # The maximum number of write buffers that are built up in memory. # The default and the minimum number is 2, so that when 1 write buffer @@ -374,20 +651,29 @@ rocksdb.target_file_size_base 16 # allowed. rocksdb.max_write_buffer_number 4 +# Maximum number of concurrent background jobs (compactions and flushes). +# For backwards compatibility we will set `max_background_jobs = +# max_background_compactions + max_background_flushes` in the case where user +# sets at least one of `max_background_compactions` or `max_background_flushes` +# (we replace -1 by 1 in case one option is unset). +rocksdb.max_background_jobs 4 + +# DEPRECATED: it is automatically decided based on the value of rocksdb.max_background_jobs # Maximum number of concurrent background compaction jobs, submitted to # the default LOW priority thread pool. -rocksdb.max_background_compactions 4 +rocksdb.max_background_compactions -1 +# DEPRECATED: it is automatically decided based on the value of rocksdb.max_background_jobs # Maximum number of concurrent background memtable flush jobs, submitted by # default to the HIGH priority thread pool. If the HIGH priority thread pool # is configured to have zero threads, flush jobs will share the LOW priority # thread pool with compaction jobs. -rocksdb.max_background_flushes 4 +rocksdb.max_background_flushes -1 # This value represents the maximum number of threads that will # concurrently perform a compaction job by breaking it into multiple, # smaller ones that are run simultaneously. -# Default: 2 (i.e. no subcompactions) +# Default: 2 rocksdb.max_sub_compactions 2 # In order to limit the size of WALs, RocksDB uses DBOptions::max_total_wal_size @@ -411,8 +697,8 @@ rocksdb.max_sub_compactions 2 # default is 512MB rocksdb.max_total_wal_size 512 -# We impl the repliction with rocksdb WAL, it would trigger full sync when the seq was out of range. -# wal_ttl_seconds and wal_size_limit_mb would affect how archived logswill be deleted. +# We implement the replication with rocksdb WAL, it would trigger full sync when the seq was out of range. +# wal_ttl_seconds and wal_size_limit_mb would affect how archived logs will be deleted. # If WAL_ttl_seconds is not 0, then WAL files will be checked every WAL_ttl_seconds / 2 and those that # are older than WAL_ttl_seconds will be deleted# # @@ -422,25 +708,25 @@ rocksdb.wal_ttl_seconds 10800 # If WAL_ttl_seconds is 0 and WAL_size_limit_MB is not 0, # WAL files will be checked every 10 min and if total size is greater # then WAL_size_limit_MB, they will be deleted starting with the -# earliest until size_limit is met. All empty files will be deleted +# earliest until size_limit is met. All empty files will be deleted # Default: 16GB rocksdb.wal_size_limit_mb 16384 # Approximate size of user data packed per block. Note that the -# block size specified here corresponds to uncompressed data. The +# block size specified here corresponds to uncompressed data. The # actual size of the unit read from disk may be smaller if # compression is enabled. # -# Default: 4KB -rocksdb.block_size 2048 +# Default: 16KB +rocksdb.block_size 16384 # Indicating if we'd put index/filter blocks to the block cache # -# Default: no +# Default: yes rocksdb.cache_index_and_filter_blocks yes # Specify the compression to use. -# Accept value: "no", "snappy" +# Accept value: "no", "snappy", "lz4", "zstd", "zlib" # default snappy rocksdb.compression snappy @@ -480,6 +766,11 @@ rocksdb.level0_slowdown_writes_trigger 20 # Default: 40 rocksdb.level0_stop_writes_trigger 40 +# Number of files to trigger level-0 compaction. +# +# Default: 4 +rocksdb.level0_file_num_compaction_trigger 4 + # if not zero, dump rocksdb.stats to LOG every stats_dump_period_sec # # Default: 0 @@ -489,9 +780,138 @@ rocksdb.stats_dump_period_sec 0 # # Default: no rocksdb.disable_auto_compactions no + +# BlobDB(key-value separation) is essentially RocksDB for large-value use cases. +# Since 6.18.0, The new implementation is integrated into the RocksDB core. +# When set, large values (blobs) are written to separate blob files, and only +# pointers to them are stored in SST files. This can reduce write amplification +# for large-value use cases at the cost of introducing a level of indirection +# for reads. Please see: https://github.com/facebook/rocksdb/wiki/BlobDB. +# +# Note that when enable_blob_files is set to yes, BlobDB-related configuration +# items will take effect. +# +# Default: no +rocksdb.enable_blob_files no + +# The size of the smallest value to be stored separately in a blob file. Values +# which have an uncompressed size smaller than this threshold are stored alongside +# the keys in SST files in the usual fashion. +# +# Default: 4096 byte, 0 means that all values are stored in blob files +rocksdb.min_blob_size 4096 + +# The size limit for blob files. When writing blob files, a new file is +# opened once this limit is reached. +# +# Default: 268435456 bytes +rocksdb.blob_file_size 268435456 + +# Enables garbage collection of blobs. Valid blobs residing in blob files +# older than a cutoff get relocated to new files as they are encountered +# during compaction, which makes it possible to clean up blob files once +# they contain nothing but obsolete/garbage blobs. +# See also rocksdb.blob_garbage_collection_age_cutoff below. +# +# Default: yes +rocksdb.enable_blob_garbage_collection yes + +# The percentage cutoff in terms of blob file age for garbage collection. +# Blobs in the oldest N blob files will be relocated when encountered during +# compaction, where N = (garbage_collection_cutoff/100) * number_of_blob_files. +# Note that this value must belong to [0, 100]. +# +# Default: 25 +rocksdb.blob_garbage_collection_age_cutoff 25 + + +# The purpose of the following three options are to dynamically adjust the upper limit of +# the data that each layer can store according to the size of the different +# layers of the LSM. Enabling this option will bring some improvements in +# deletion efficiency and space amplification, but it will lose a certain +# amount of read performance. +# If you want to know more details about Levels' Target Size, you can read RocksDB wiki: +# https://github.com/facebook/rocksdb/wiki/Leveled-Compaction#levels-target-size +# +# Default: yes +rocksdb.level_compaction_dynamic_level_bytes yes + +# The total file size of level-1 sst. +# +# Default: 268435456 bytes +rocksdb.max_bytes_for_level_base 268435456 + +# Multiplication factor for the total file size of L(n+1) layers. +# This option is a double type number in RocksDB, but kvrocks is +# not support the double data type number yet, so we use integer +# number instead of double currently. +# +# Default: 10 +rocksdb.max_bytes_for_level_multiplier 10 + +# This feature only takes effect in Iterators and MultiGet. +# If yes, RocksDB will try to read asynchronously and in parallel as much as possible to hide IO latency. +# In iterators, it will prefetch data asynchronously in the background for each file being iterated on. +# In MultiGet, it will read the necessary data blocks from those files in parallel as much as possible. + +# Default no +rocksdb.read_options.async_io no + +# If yes, the write will be flushed from the operating system +# buffer cache before the write is considered complete. +# If this flag is enabled, writes will be slower. +# If this flag is disabled, and the machine crashes, some recent +# writes may be lost. Note that if it is just the process that +# crashes (i.e., the machine does not reboot), no writes will be +# lost even if sync==false. +# +# Default: no +rocksdb.write_options.sync no + +# If yes, writes will not first go to the write ahead log, +# and the write may get lost after a crash. +# You must keep wal enabled if you use replication. +# +# Default: no +rocksdb.write_options.disable_wal no + +# If enabled and we need to wait or sleep for the write request, fails +# immediately. +# +# Default: no +rocksdb.write_options.no_slowdown no + +# If enabled, write requests are of lower priority if compaction is +# behind. In this case, no_slowdown = true, the request will be canceled +# immediately. Otherwise, it will be slowed down. +# The slowdown value is determined by RocksDB to guarantee +# it introduces minimum impacts to high priority writes. +# +# Default: no +rocksdb.write_options.low_pri no + +# If enabled, this writebatch will maintain the last insert positions of each +# memtable as hints in concurrent write. It can improve write performance +# in concurrent writes if keys in one writebatch are sequential. +# +# Default: no +rocksdb.write_options.memtable_insert_hint_per_batch no + + +# Support RocksDB auto-tune rate limiter for the background IO +# if enabled, Rate limiter will limit the compaction write if flush write is high +# Please see https://rocksdb.org/blog/2017/12/18/17-auto-tuned-rate-limiter.html +# +# Default: yes +rocksdb.rate_limiter_auto_tuned yes + +# Enable this option will schedule the deletion of obsolete files in a background thread +# on iterator destruction. It can reduce the latency if there are many files to be removed. +# see https://github.com/facebook/rocksdb/wiki/IO#avoid-blocking-io +# +# Default: yes +# rocksdb.avoid_unnecessary_blocking_io yes + ################################ NAMESPACE ##################################### # namespace.test change.me - - backup-dir .//backup -log-dir ./ diff --git a/temp/intake.conf b/temp/intake.conf index a678f2f..2bb765b 100644 --- a/temp/intake.conf +++ b/temp/intake.conf @@ -1,9 +1,9 @@ -# Redis configuration file example. +# Valkey configuration file example. # -# Note that in order to read the configuration file, Redis must be +# Note that in order to read the configuration file, the server must be # started with the file path as first argument: # -# ./redis-server /path/to/redis.conf +# ./valkey-server /path/to/valkey.conf # Note on units: when memory size is needed, it is possible to specify # it in the usual form of 1k 5GB 4M and so forth: @@ -20,20 +20,29 @@ ################################## INCLUDES ################################### # Include one or more other config files here. This is useful if you -# have a standard template that goes to all Redis servers but also need +# have a standard template that goes to all servers but also need # to customize a few per-server settings. Include files can include # other files, so use this wisely. # -# Notice option "include" won't be rewritten by command "CONFIG REWRITE" -# from admin or Redis Sentinel. Since Redis always uses the last processed +# Note that option "include" won't be rewritten by command "CONFIG REWRITE" +# from admin or Sentinel. Since the server always uses the last processed # line as value of a configuration directive, you'd better put includes # at the beginning of this file to avoid overwriting config change at runtime. # # If instead you are interested in using includes to override configuration # options, it is better to use include as the last line. # +# Included paths may contain wildcards. All files matching the wildcards will +# be included in alphabetical order. +# Note that if an include path contains a wildcards but no files match it when +# the server is started, the include statement will be ignored and no error will +# be emitted. It is safe, therefore, to include wildcard files from empty +# directories. +# # include /path/to/local.conf # include /path/to/other.conf +# include /path/to/fragments/*.conf +# ################################## MODULES ##################################### @@ -45,56 +54,93 @@ ################################## NETWORK ##################################### -# By default, if no "bind" configuration directive is specified, Redis listens -# for connections from all the network interfaces available on the server. +# By default, if no "bind" configuration directive is specified, the server listens +# for connections from all available network interfaces on the host machine. # It is possible to listen to just one or multiple selected interfaces using # the "bind" configuration directive, followed by one or more IP addresses. +# Each address can be prefixed by "-", which means that the server will not fail to +# start if the address is not available. Being not available only refers to +# addresses that does not correspond to any network interface. Addresses that +# are already in use will always fail, and unsupported protocols will always BE +# silently skipped. # # Examples: # -# bind 192.168.1.100 10.0.0.1 -# bind 127.0.0.1 ::1 +# bind 192.168.1.100 10.0.0.1 # listens on two specific IPv4 addresses +# bind 127.0.0.1 ::1 # listens on loopback IPv4 and IPv6 +# bind * -::* # like the default, all available interfaces # -# ~~~ WARNING ~~~ If the computer running Redis is directly exposed to the +# ~~~ WARNING ~~~ If the computer running the server is directly exposed to the # internet, binding to all the interfaces is dangerous and will expose the # instance to everybody on the internet. So by default we uncomment the -# following bind directive, that will force Redis to listen only into -# the IPv4 lookback interface address (this means Redis will be able to -# accept connections only from clients running into the same computer it -# is running). +# following bind directive, that will force the server to listen only on the +# IPv4 and IPv6 (if available) loopback interface addresses (this means the server +# will only be able to accept client connections from the same host that it is +# running on). # # IF YOU ARE SURE YOU WANT YOUR INSTANCE TO LISTEN TO ALL THE INTERFACES -# JUST COMMENT THE FOLLOWING LINE. +# COMMENT OUT THE FOLLOWING LINE. +# +# You will also need to set a password unless you explicitly disable protected +# mode. # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -bind 127.0.0.1 +bind 127.0.0.1 -::1 + +# By default, outgoing connections (from replica to master, from Sentinel to +# instances, cluster bus, etc.) are not bound to a specific local address. In +# most cases, this means the operating system will handle that based on routing +# and the interface through which the connection goes out. +# +# Using bind-source-addr it is possible to configure a specific address to bind +# to, which may also affect how the connection gets routed. +# +# Example: +# +# bind-source-addr 10.0.0.1 # Protected mode is a layer of security protection, in order to avoid that -# Redis instances left open on the internet are accessed and exploited. +# the server instances left open on the internet are accessed and exploited. # -# When protected mode is on and if: -# -# 1) The server is not binding explicitly to a set of addresses using the -# "bind" directive. -# 2) No password is configured. -# -# The server only accepts connections from clients connecting from the -# IPv4 and IPv6 loopback addresses 127.0.0.1 and ::1, and from Unix domain -# sockets. +# When protected mode is on and the default user has no password, the server +# only accepts local connections from the IPv4 address (127.0.0.1), IPv6 address +# (::1) or Unix domain sockets. # # By default protected mode is enabled. You should disable it only if -# you are sure you want clients from other hosts to connect to Redis -# even if no authentication is configured, nor a specific set of interfaces -# are explicitly listed using the "bind" directive. +# you are sure you want clients from other hosts to connect to the server +# even if no authentication is configured. protected-mode yes +# The server uses default hardened security configuration directives to reduce the +# attack surface on innocent users. Therefore, several sensitive configuration +# directives are immutable, and some potentially-dangerous commands are blocked. +# +# Configuration directives that control files that the server writes to (e.g., 'dir' +# and 'dbfilename') and that aren't usually modified during runtime +# are protected by making them immutable. +# +# Commands that can increase the attack surface of the server and that aren't usually +# called by users are blocked by default. +# +# These can be exposed to either all connections or just local ones by setting +# each of the configs listed below to either of these values: +# +# no - Block for any connection (remain immutable) +# yes - Allow for any connection (no protection) +# local - Allow only for local connections. Ones originating from the +# IPv4 address (127.0.0.1), IPv6 address (::1) or Unix domain sockets. +# +# enable-protected-configs no +# enable-debug-command no +# enable-module-command no + # Accept connections on the specified port, default is 6379 (IANA #815344). -# If port 0 is specified Redis will not listen on a TCP socket. +# If port 0 is specified the server will not listen on a TCP socket. port 0 # TCP listen() backlog. # -# In high requests-per-second environments you need an high backlog in order -# to avoid slow clients connections issues. Note that the Linux kernel +# In high requests-per-second environments you need a high backlog in order +# to avoid slow clients connection issues. Note that the Linux kernel # will silently truncate it to the value of /proc/sys/net/core/somaxconn so # make sure to raise both the value of somaxconn and tcp_max_syn_backlog # in order to get the desired effect. @@ -103,7 +149,7 @@ tcp-backlog 511 # Unix socket. # # Specify the path for the Unix socket that will be used to listen for -# incoming connections. There is no default, so Redis will not listen +# incoming connections. There is no default, so the server will not listen # on a unix socket when not specified. # unixsocket intake.sock @@ -118,44 +164,178 @@ timeout 0 # of communication. This is useful for two reasons: # # 1) Detect dead peers. -# 2) Take the connection alive from the point of view of network -# equipment in the middle. +# 2) Force network equipment in the middle to consider the connection to be +# alive. # # On Linux, the specified value (in seconds) is the period used to send ACKs. # Note that to close the connection the double of the time is needed. # On other kernels the period depends on the kernel configuration. -# -# A reasonable value for this option is 300 seconds, which is the new -# Redis default starting with Redis 3.2.1. tcp-keepalive 300 +# Apply OS-specific mechanism to mark the listening socket with the specified +# ID, to support advanced routing and filtering capabilities. +# +# On Linux, the ID represents a connection mark. +# On FreeBSD, the ID represents a socket cookie ID. +# On OpenBSD, the ID represents a route table ID. +# +# The default value is 0, which implies no marking is required. +# socket-mark-id 0 + +################################# TLS/SSL ##################################### + +# By default, TLS/SSL is disabled. To enable it, the "tls-port" configuration +# directive can be used to define TLS-listening ports. To enable TLS on the +# default port, use: +# +# port 0 +# tls-port 6379 + +# Configure a X.509 certificate and private key to use for authenticating the +# server to connected clients, masters or cluster peers. These files should be +# PEM formatted. +# +# tls-cert-file valkey.crt +# tls-key-file valkey.key +# +# If the key file is encrypted using a passphrase, it can be included here +# as well. +# +# tls-key-file-pass secret + +# Normally the server uses the same certificate for both server functions (accepting +# connections) and client functions (replicating from a master, establishing +# cluster bus connections, etc.). +# +# Sometimes certificates are issued with attributes that designate them as +# client-only or server-only certificates. In that case it may be desired to use +# different certificates for incoming (server) and outgoing (client) +# connections. To do that, use the following directives: +# +# tls-client-cert-file client.crt +# tls-client-key-file client.key +# +# If the key file is encrypted using a passphrase, it can be included here +# as well. +# +# tls-client-key-file-pass secret + +# Configure a DH parameters file to enable Diffie-Hellman (DH) key exchange, +# required by older versions of OpenSSL (<3.0). Newer versions do not require +# this configuration and recommend against it. +# +# tls-dh-params-file valkey.dh + +# Configure a CA certificate(s) bundle or directory to authenticate TLS/SSL +# clients and peers. The server requires an explicit configuration of at least one +# of these, and will not implicitly use the system wide configuration. +# +# tls-ca-cert-file ca.crt +# tls-ca-cert-dir /etc/ssl/certs + +# By default, clients (including replica servers) on a TLS port are required +# to authenticate using valid client side certificates. +# +# If "no" is specified, client certificates are not required and not accepted. +# If "optional" is specified, client certificates are accepted and must be +# valid if provided, but are not required. +# +# tls-auth-clients no +# tls-auth-clients optional + +# By default, a replica does not attempt to establish a TLS connection +# with its master. +# +# Use the following directive to enable TLS on replication links. +# +# tls-replication yes + +# By default, the cluster bus uses a plain TCP connection. To enable +# TLS for the bus protocol, use the following directive: +# +# tls-cluster yes + +# By default, only TLSv1.2 and TLSv1.3 are enabled and it is highly recommended +# that older formally deprecated versions are kept disabled to reduce the attack surface. +# You can explicitly specify TLS versions to support. +# Allowed values are case insensitive and include "TLSv1", "TLSv1.1", "TLSv1.2", +# "TLSv1.3" (OpenSSL >= 1.1.1) or any combination. +# To enable only TLSv1.2 and TLSv1.3, use: +# +# tls-protocols "TLSv1.2 TLSv1.3" + +# Configure allowed ciphers. See the ciphers(1ssl) manpage for more information +# about the syntax of this string. +# +# Note: this configuration applies only to <= TLSv1.2. +# +# tls-ciphers DEFAULT:!MEDIUM + +# Configure allowed TLSv1.3 ciphersuites. See the ciphers(1ssl) manpage for more +# information about the syntax of this string, and specifically for TLSv1.3 +# ciphersuites. +# +# tls-ciphersuites TLS_CHACHA20_POLY1305_SHA256 + +# When choosing a cipher, use the server's preference instead of the client +# preference. By default, the server follows the client's preference. +# +# tls-prefer-server-ciphers yes + +# By default, TLS session caching is enabled to allow faster and less expensive +# reconnections by clients that support it. Use the following directive to disable +# caching. +# +# tls-session-caching no + +# Change the default number of TLS sessions cached. A zero value sets the cache +# to unlimited size. The default size is 20480. +# +# tls-session-cache-size 5000 + +# Change the default timeout of cached TLS sessions. The default timeout is 300 +# seconds. +# +# tls-session-cache-timeout 60 + ################################# GENERAL ##################################### -# By default Redis does not run as a daemon. Use 'yes' if you need it. -# Note that Redis will write a pid file in /var/run/redis.pid when daemonized. +# By default the server does not run as a daemon. Use 'yes' if you need it. +# Note that the server will write a pid file in /var/run/valkey.pid when daemonized. +# When the server is supervised by upstart or systemd, this parameter has no impact. daemonize yes -# If you run Redis from upstart or systemd, Redis can interact with your +# If you run the server from upstart or systemd, the server can interact with your # supervision tree. Options: # supervised no - no supervision interaction -# supervised upstart - signal upstart by putting Redis into SIGSTOP mode +# supervised upstart - signal upstart by putting the server into SIGSTOP mode +# requires "expect stop" in your upstart job config # supervised systemd - signal systemd by writing READY=1 to $NOTIFY_SOCKET +# on startup, and updating the server status on a regular +# basis. # supervised auto - detect upstart or systemd method based on # UPSTART_JOB or NOTIFY_SOCKET environment variables # Note: these supervision methods only signal "process is ready." -# They do not enable continuous liveness pings back to your supervisor. -supervised no +# They do not enable continuous pings back to your supervisor. +# +# The default is "no". To run under upstart/systemd, you can simply uncomment +# the line below: +# +# supervised auto -# If a pid file is specified, Redis writes it where specified at startup +# If a pid file is specified, the server writes it where specified at startup # and removes it at exit. # # When the server runs non daemonized, no pid file is created if none is # specified in the configuration. When the server is daemonized, the pid file # is used even if not specified, defaulting to "/var/run/redis.pid". # -# Creating a pid file is best effort: if Redis is not able to create it +# Creating a pid file is best effort: if the server is not able to create it # nothing bad happens, the server will start and run normally. -# pidfile /var/run/redis_6379.pid +# +# Note that on modern Linux systems "/run/valkey.pid" is more conforming +# and should be used instead. +pidfile intake.pid # Specify the server verbosity level. # This can be one of: @@ -163,12 +343,13 @@ supervised no # verbose (many rarely useful info, but not a mess like the debug level) # notice (moderately verbose, what you want in production probably) # warning (only very important / critical messages are logged) +# nothing (nothing is logged) loglevel notice # Specify the log file name. Also the empty string can be used to force -# Redis to log on the standard output. Note that if you use standard +# the server to log on the standard output. Note that if you use standard # output for logging but daemonize, logs will be sent to /dev/null -logfile "intake.log" +logfile "" # To enable logging to the system logger, just set 'syslog-enabled' to yes, # and optionally update the other syslog parameters to suit your needs. @@ -180,62 +361,97 @@ logfile "intake.log" # Specify the syslog facility. Must be USER or between LOCAL0-LOCAL7. # syslog-facility local0 +# To disable the built in crash log, which will possibly produce cleaner core +# dumps when they are needed, uncomment the following: +# +# crash-log-enabled no + +# To disable the fast memory check that's run as part of the crash log, which +# will possibly let the server terminate sooner, uncomment the following: +# +# crash-memcheck-enabled no + # Set the number of databases. The default database is DB 0, you can select # a different one on a per-connection basis using SELECT where # dbid is a number between 0 and 'databases'-1 databases 16 -# By default Redis shows an ASCII art logo only when started to log to the -# standard output and if the standard output is a TTY. Basically this means -# that normally a logo is displayed only in interactive sessions. +# By default the server shows an ASCII art logo only when started to log to the +# standard output and if the standard output is a TTY and syslog logging is +# disabled. Basically this means that normally a logo is displayed only in +# interactive sessions. # # However it is possible to force the pre-4.0 behavior and always show a # ASCII art logo in startup logs by setting the following option to yes. -always-show-logo yes +always-show-logo no + +# By default, the server modifies the process title (as seen in 'top' and 'ps') to +# provide some runtime information. It is possible to disable this and leave +# the process name as executed by setting the following to no. +set-proc-title yes + +# When changing the process title, the server uses the following template to construct +# the modified title. +# +# Template variables are specified in curly brackets. The following variables are +# supported: +# +# {title} Name of process as executed if parent, or type of child process. +# {listen-addr} Bind address or '*' followed by TCP or TLS port listening on, or +# Unix socket if only that's available. +# {server-mode} Special mode, i.e. "[sentinel]" or "[cluster]". +# {port} TCP port listening on, or 0. +# {tls-port} TLS port listening on, or 0. +# {unixsocket} Unix domain socket listening on, or "". +# {config-file} Name of configuration file used. +# +proc-title-template "{title} {listen-addr} {server-mode}" + +# Set the local environment which is used for string comparison operations, and +# also affect the performance of Lua scripts. Empty String indicates the locale +# is derived from the environment variables. +locale-collate "" ################################ SNAPSHOTTING ################################ -# -# Save the DB on disk: -# -# save -# -# Will save the DB if both the given number of seconds and the given -# number of write operations against the DB occurred. -# -# In the example below the behaviour will be to save: -# after 900 sec (15 min) if at least 1 key changed -# after 300 sec (5 min) if at least 10 keys changed -# after 60 sec if at least 10000 keys changed -# -# Note: you can disable saving completely by commenting out all "save" lines. -# -# It is also possible to remove all the previously configured save -# points by adding a save directive with a single empty string argument -# like in the following example: -# -# save "" -#save 900 1 -#save 300 10 -save 600 10000 +# Save the DB to disk. +# +# save [ ...] +# +# The server will save the DB if the given number of seconds elapsed and it +# surpassed the given number of write operations against the DB. +# +# Snapshotting can be completely disabled with a single empty string argument +# as in following example: +# +# save "" +# +# Unless specified otherwise, by default the server will save the DB: +# * After 3600 seconds (an hour) if at least 1 change was performed +# * After 300 seconds (5 minutes) if at least 100 changes were performed +# * After 60 seconds if at least 10000 changes were performed +# +# You can set these explicitly by uncommenting the following line. +# +save 3600 1 -# By default Redis will stop accepting writes if RDB snapshots are enabled +# By default the server will stop accepting writes if RDB snapshots are enabled # (at least one save point) and the latest background save failed. # This will make the user aware (in a hard way) that data is not persisting # on disk properly, otherwise chances are that no one will notice and some # disaster will happen. # -# If the background saving process will start working again Redis will +# If the background saving process will start working again, the server will # automatically allow writes again. # -# However if you have setup your proper monitoring of the Redis server -# and persistence, you may want to disable this feature so that Redis will +# However if you have setup your proper monitoring of the server +# and persistence, you may want to disable this feature so that the server will # continue to work as usual even if there are problems with disk, # permissions, and so forth. stop-writes-on-bgsave-error yes # Compress string objects using LZF when dump .rdb databases? -# For default that's set to 'yes' as it's almost always a win. +# By default compression is enabled as it's almost always a win. # If you want to save some CPU in the saving child set it to 'no' but # the dataset will likely be bigger if you have compressible values or keys. rdbcompression yes @@ -249,8 +465,36 @@ rdbcompression yes # tell the loading code to skip the check. rdbchecksum yes +# Enables or disables full sanitization checks for ziplist and listpack etc when +# loading an RDB or RESTORE payload. This reduces the chances of a assertion or +# crash later on while processing commands. +# Options: +# no - Never perform full sanitization +# yes - Always perform full sanitization +# clients - Perform full sanitization only for user connections. +# Excludes: RDB files, RESTORE commands received from the master +# connection, and client connections which have the +# skip-sanitize-payload ACL flag. +# The default should be 'clients' but since it currently affects cluster +# resharding via MIGRATE, it is temporarily set to 'no' by default. +# +# sanitize-dump-payload no + # The filename where to dump the DB -dbfilename intake.rdb +dbfilename dump.rdb + +# Remove RDB files used by replication in instances without persistence +# enabled. By default this option is disabled, however there are environments +# where for regulations or other security concerns, RDB files persisted on +# disk by masters in order to feed replicas, or stored on disk by replicas +# in order to load them for the initial synchronization, should be deleted +# ASAP. Note that this option ONLY WORKS in instances that have both AOF +# and RDB persistence disabled, otherwise is completely ignored. +# +# An alternative (and sometimes better) way to obtain the same effect is +# to use diskless replication on both master and replicas instances. However +# in the case of replicas, diskless is not always an option. +rdb-del-sync-files no # The working directory. # @@ -264,242 +508,550 @@ dir ./ ################################# REPLICATION ################################# -# Master-Slave replication. Use slaveof to make a Redis instance a copy of -# another Redis server. A few things to understand ASAP about Redis replication. +# Master-Replica replication. Use replicaof to make a server a copy of +# another server. A few things to understand ASAP about replication. # -# 1) Redis replication is asynchronous, but you can configure a master to +# +------------------+ +---------------+ +# | Master | ---> | Replica | +# | (receive writes) | | (exact copy) | +# +------------------+ +---------------+ +# +# 1) Replication is asynchronous, but you can configure a master to # stop accepting writes if it appears to be not connected with at least -# a given number of slaves. -# 2) Redis slaves are able to perform a partial resynchronization with the +# a given number of replicas. +# 2) Replicas are able to perform a partial resynchronization with the # master if the replication link is lost for a relatively small amount of # time. You may want to configure the replication backlog size (see the next # sections of this file) with a sensible value depending on your needs. # 3) Replication is automatic and does not need user intervention. After a -# network partition slaves automatically try to reconnect to masters +# network partition replicas automatically try to reconnect to masters # and resynchronize with them. # -# slaveof +# replicaof # If the master is password protected (using the "requirepass" configuration -# directive below) it is possible to tell the slave to authenticate before +# directive below) it is possible to tell the replica to authenticate before # starting the replication synchronization process, otherwise the master will -# refuse the slave request. +# refuse the replica request. # # masterauth - -# When a slave loses its connection with the master, or when the replication -# is still in progress, the slave can act in two different ways: # -# 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will +# However this is not enough if you are using ACLs +# and the default user is not capable of running the PSYNC +# command and/or other commands needed for replication. In this case it's +# better to configure a special user to use with replication, and specify the +# masteruser configuration as such: +# +# masteruser +# +# When masteruser is specified, the replica will authenticate against its +# master using the new AUTH form: AUTH . + +# When a replica loses its connection with the master, or when the replication +# is still in progress, the replica can act in two different ways: +# +# 1) if replica-serve-stale-data is set to 'yes' (the default) the replica will # still reply to client requests, possibly with out of date data, or the # data set may just be empty if this is the first synchronization. # -# 2) if slave-serve-stale-data is set to 'no' the slave will reply with -# an error "SYNC with master in progress" to all the kind of commands -# but to INFO and SLAVEOF. +# 2) If replica-serve-stale-data is set to 'no' the replica will reply with error +# "MASTERDOWN Link with MASTER is down and replica-serve-stale-data is set to 'no'" +# to all data access commands, excluding commands such as: +# INFO, REPLICAOF, AUTH, SHUTDOWN, REPLCONF, ROLE, CONFIG, SUBSCRIBE, +# UNSUBSCRIBE, PSUBSCRIBE, PUNSUBSCRIBE, PUBLISH, PUBSUB, COMMAND, POST, +# HOST and LATENCY. # -slave-serve-stale-data yes +replica-serve-stale-data yes -# You can configure a slave instance to accept writes or not. Writing against -# a slave instance may be useful to store some ephemeral data (because data -# written on a slave will be easily deleted after resync with the master) but +# You can configure a replica instance to accept writes or not. Writing against +# a replica instance may be useful to store some ephemeral data (because data +# written on a replica will be easily deleted after resync with the master) but # may also cause problems if clients are writing to it because of a # misconfiguration. # -# Since Redis 2.6 by default slaves are read-only. +# By default, replicas are read-only. # -# Note: read only slaves are not designed to be exposed to untrusted clients +# Note: read only replicas are not designed to be exposed to untrusted clients # on the internet. It's just a protection layer against misuse of the instance. -# Still a read only slave exports by default all the administrative commands +# Still a read only replica exports by default all the administrative commands # such as CONFIG, DEBUG, and so forth. To a limited extent you can improve -# security of read only slaves using 'rename-command' to shadow all the +# security of read only replicas using 'rename-command' to shadow all the # administrative / dangerous commands. -slave-read-only yes +replica-read-only yes # Replication SYNC strategy: disk or socket. # -# ------------------------------------------------------- -# WARNING: DISKLESS REPLICATION IS EXPERIMENTAL CURRENTLY -# ------------------------------------------------------- +# New replicas and reconnecting replicas that are not able to continue the +# replication process just receiving differences, need to do what is called a +# "full synchronization". An RDB file is transmitted from the master to the +# replicas. # -# New slaves and reconnecting slaves that are not able to continue the replication -# process just receiving differences, need to do what is called a "full -# synchronization". An RDB file is transmitted from the master to the slaves. # The transmission can happen in two different ways: # -# 1) Disk-backed: The Redis master creates a new process that writes the RDB +# 1) Disk-backed: The master creates a new process that writes the RDB # file on disk. Later the file is transferred by the parent -# process to the slaves incrementally. -# 2) Diskless: The Redis master creates a new process that directly writes the -# RDB file to slave sockets, without touching the disk at all. +# process to the replicas incrementally. +# 2) Diskless: The master creates a new process that directly writes the +# RDB file to replica sockets, without touching the disk at all. # -# With disk-backed replication, while the RDB file is generated, more slaves -# can be queued and served with the RDB file as soon as the current child producing -# the RDB file finishes its work. With diskless replication instead once -# the transfer starts, new slaves arriving will be queued and a new transfer -# will start when the current one terminates. +# With disk-backed replication, while the RDB file is generated, more replicas +# can be queued and served with the RDB file as soon as the current child +# producing the RDB file finishes its work. With diskless replication instead +# once the transfer starts, new replicas arriving will be queued and a new +# transfer will start when the current one terminates. # # When diskless replication is used, the master waits a configurable amount of -# time (in seconds) before starting the transfer in the hope that multiple slaves -# will arrive and the transfer can be parallelized. +# time (in seconds) before starting the transfer in the hope that multiple +# replicas will arrive and the transfer can be parallelized. # # With slow disks and fast (large bandwidth) networks, diskless replication # works better. -repl-diskless-sync no +repl-diskless-sync yes # When diskless replication is enabled, it is possible to configure the delay # the server waits in order to spawn the child that transfers the RDB via socket -# to the slaves. +# to the replicas. # # This is important since once the transfer starts, it is not possible to serve -# new slaves arriving, that will be queued for the next RDB transfer, so the server -# waits a delay in order to let more slaves arrive. +# new replicas arriving, that will be queued for the next RDB transfer, so the +# server waits a delay in order to let more replicas arrive. # # The delay is specified in seconds, and by default is 5 seconds. To disable # it entirely just set it to 0 seconds and the transfer will start ASAP. repl-diskless-sync-delay 5 -# Slaves send PINGs to server in a predefined interval. It's possible to change -# this interval with the repl_ping_slave_period option. The default value is 10 -# seconds. +# When diskless replication is enabled with a delay, it is possible to let +# the replication start before the maximum delay is reached if the maximum +# number of replicas expected have connected. Default of 0 means that the +# maximum is not defined and the server will wait the full delay. +repl-diskless-sync-max-replicas 0 + +# ----------------------------------------------------------------------------- +# WARNING: Since in this setup the replica does not immediately store an RDB on +# disk, it may cause data loss during failovers. RDB diskless load + server +# modules not handling I/O reads may cause the server to abort in case of I/O errors +# during the initial synchronization stage with the master. +# ----------------------------------------------------------------------------- # -# repl-ping-slave-period 10 +# Replica can load the RDB it reads from the replication link directly from the +# socket, or store the RDB to a file and read that file after it was completely +# received from the master. +# +# In many cases the disk is slower than the network, and storing and loading +# the RDB file may increase replication time (and even increase the master's +# Copy on Write memory and replica buffers). +# However, when parsing the RDB file directly from the socket, in order to avoid +# data loss it's only safe to flush the current dataset when the new dataset is +# fully loaded in memory, resulting in higher memory usage. +# For this reason we have the following options: +# +# "disabled" - Don't use diskless load (store the rdb file to the disk first) +# "swapdb" - Keep current db contents in RAM while parsing the data directly +# from the socket. Replicas in this mode can keep serving current +# dataset while replication is in progress, except for cases where +# they can't recognize master as having a data set from same +# replication history. +# Note that this requires sufficient memory, if you don't have it, +# you risk an OOM kill. +# "on-empty-db" - Use diskless load only when current dataset is empty. This is +# safer and avoid having old and new dataset loaded side by side +# during replication. +repl-diskless-load disabled + +# Master send PINGs to its replicas in a predefined interval. It's possible to +# change this interval with the repl_ping_replica_period option. The default +# value is 10 seconds. +# +# repl-ping-replica-period 10 # The following option sets the replication timeout for: # -# 1) Bulk transfer I/O during SYNC, from the point of view of slave. -# 2) Master timeout from the point of view of slaves (data, pings). -# 3) Slave timeout from the point of view of masters (REPLCONF ACK pings). +# 1) Bulk transfer I/O during SYNC, from the point of view of replica. +# 2) Master timeout from the point of view of replicas (data, pings). +# 3) Replica timeout from the point of view of masters (REPLCONF ACK pings). # # It is important to make sure that this value is greater than the value -# specified for repl-ping-slave-period otherwise a timeout will be detected -# every time there is low traffic between the master and the slave. +# specified for repl-ping-replica-period otherwise a timeout will be detected +# every time there is low traffic between the master and the replica. The default +# value is 60 seconds. # # repl-timeout 60 -# Disable TCP_NODELAY on the slave socket after SYNC? +# Disable TCP_NODELAY on the replica socket after SYNC? # -# If you select "yes" Redis will use a smaller number of TCP packets and -# less bandwidth to send data to slaves. But this can add a delay for -# the data to appear on the slave side, up to 40 milliseconds with +# If you select "yes", the server will use a smaller number of TCP packets and +# less bandwidth to send data to replicas. But this can add a delay for +# the data to appear on the replica side, up to 40 milliseconds with # Linux kernels using a default configuration. # -# If you select "no" the delay for data to appear on the slave side will +# If you select "no" the delay for data to appear on the replica side will # be reduced but more bandwidth will be used for replication. # # By default we optimize for low latency, but in very high traffic conditions -# or when the master and slaves are many hops away, turning this to "yes" may +# or when the master and replicas are many hops away, turning this to "yes" may # be a good idea. repl-disable-tcp-nodelay no # Set the replication backlog size. The backlog is a buffer that accumulates -# slave data when slaves are disconnected for some time, so that when a slave -# wants to reconnect again, often a full resync is not needed, but a partial -# resync is enough, just passing the portion of data the slave missed while -# disconnected. +# replica data when replicas are disconnected for some time, so that when a +# replica wants to reconnect again, often a full resync is not needed, but a +# partial resync is enough, just passing the portion of data the replica +# missed while disconnected. # -# The bigger the replication backlog, the longer the time the slave can be -# disconnected and later be able to perform a partial resynchronization. +# The bigger the replication backlog, the longer the replica can endure the +# disconnect and later be able to perform a partial resynchronization. # -# The backlog is only allocated once there is at least a slave connected. +# The backlog is only allocated if there is at least one replica connected. # # repl-backlog-size 1mb -# After a master has no longer connected slaves for some time, the backlog -# will be freed. The following option configures the amount of seconds that -# need to elapse, starting from the time the last slave disconnected, for -# the backlog buffer to be freed. +# After a master has no connected replicas for some time, the backlog will be +# freed. The following option configures the amount of seconds that need to +# elapse, starting from the time the last replica disconnected, for the backlog +# buffer to be freed. # -# Note that slaves never free the backlog for timeout, since they may be +# Note that replicas never free the backlog for timeout, since they may be # promoted to masters later, and should be able to correctly "partially -# resynchronize" with the slaves: hence they should always accumulate backlog. +# resynchronize" with other replicas: hence they should always accumulate backlog. # # A value of 0 means to never release the backlog. # # repl-backlog-ttl 3600 -# The slave priority is an integer number published by Redis in the INFO output. -# It is used by Redis Sentinel in order to select a slave to promote into a -# master if the master is no longer working correctly. +# The replica priority is an integer number published by the server in the INFO +# output. It is used by Sentinel in order to select a replica to promote +# into a master if the master is no longer working correctly. # -# A slave with a low priority number is considered better for promotion, so -# for instance if there are three slaves with priority 10, 100, 25 Sentinel will -# pick the one with priority 10, that is the lowest. +# A replica with a low priority number is considered better for promotion, so +# for instance if there are three replicas with priority 10, 100, 25 Sentinel +# will pick the one with priority 10, that is the lowest. # -# However a special priority of 0 marks the slave as not able to perform the -# role of master, so a slave with priority of 0 will never be selected by -# Redis Sentinel for promotion. +# However a special priority of 0 marks the replica as not able to perform the +# role of master, so a replica with priority of 0 will never be selected by +# Sentinel for promotion. # # By default the priority is 100. -slave-priority 100 +replica-priority 100 + +# The propagation error behavior controls how the server will behave when it is +# unable to handle a command being processed in the replication stream from a master +# or processed while reading from an AOF file. Errors that occur during propagation +# are unexpected, and can cause data inconsistency. +# +# If an application wants to ensure there is no data divergence, this configuration +# should be set to 'panic' instead. The value can also be set to 'panic-on-replicas' +# to only panic when a replica encounters an error on the replication stream. One of +# these two panic values will become the default value in the future once there are +# sufficient safety mechanisms in place to prevent false positive crashes. +# +# propagation-error-behavior ignore + +# Replica ignore disk write errors controls the behavior of a replica when it is +# unable to persist a write command received from its master to disk. By default, +# this configuration is set to 'no' and will crash the replica in this condition. +# It is not recommended to change this default. +# +# replica-ignore-disk-write-errors no + +# ----------------------------------------------------------------------------- +# By default, Sentinel includes all replicas in its reports. A replica +# can be excluded from Sentinel's announcements. An unannounced replica +# will be ignored by the 'sentinel replicas ' command and won't be +# exposed to Sentinel's clients. +# +# This option does not change the behavior of replica-priority. Even with +# replica-announced set to 'no', the replica can be promoted to master. To +# prevent this behavior, set replica-priority to 0. +# +# replica-announced yes # It is possible for a master to stop accepting writes if there are less than -# N slaves connected, having a lag less or equal than M seconds. +# N replicas connected, having a lag less or equal than M seconds. # -# The N slaves need to be in "online" state. +# The N replicas need to be in "online" state. # # The lag in seconds, that must be <= the specified value, is calculated from -# the last ping received from the slave, that is usually sent every second. +# the last ping received from the replica, that is usually sent every second. # # This option does not GUARANTEE that N replicas will accept the write, but -# will limit the window of exposure for lost writes in case not enough slaves +# will limit the window of exposure for lost writes in case not enough replicas # are available, to the specified number of seconds. # -# For example to require at least 3 slaves with a lag <= 10 seconds use: +# For example to require at least 3 replicas with a lag <= 10 seconds use: # -# min-slaves-to-write 3 -# min-slaves-max-lag 10 +# min-replicas-to-write 3 +# min-replicas-max-lag 10 # # Setting one or the other to 0 disables the feature. # -# By default min-slaves-to-write is set to 0 (feature disabled) and -# min-slaves-max-lag is set to 10. +# By default min-replicas-to-write is set to 0 (feature disabled) and +# min-replicas-max-lag is set to 10. -# A Redis master is able to list the address and port of the attached -# slaves in different ways. For example the "INFO replication" section +# A master is able to list the address and port of the attached +# replicas in different ways. For example the "INFO replication" section # offers this information, which is used, among other tools, by -# Redis Sentinel in order to discover slave instances. +# Sentinel in order to discover replica instances. # Another place where this info is available is in the output of the # "ROLE" command of a master. # -# The listed IP and address normally reported by a slave is obtained -# in the following way: +# The listed IP address and port normally reported by a replica is +# obtained in the following way: # # IP: The address is auto detected by checking the peer address -# of the socket used by the slave to connect with the master. +# of the socket used by the replica to connect with the master. # -# Port: The port is communicated by the slave during the replication -# handshake, and is normally the port that the slave is using to -# list for connections. +# Port: The port is communicated by the replica during the replication +# handshake, and is normally the port that the replica is using to +# listen for connections. # # However when port forwarding or Network Address Translation (NAT) is -# used, the slave may be actually reachable via different IP and port -# pairs. The following two options can be used by a slave in order to +# used, the replica may actually be reachable via different IP and port +# pairs. The following two options can be used by a replica in order to # report to its master a specific set of IP and port, so that both INFO # and ROLE will report those values. # # There is no need to use both the options if you need to override just # the port or the IP address. # -# slave-announce-ip 5.5.5.5 -# slave-announce-port 1234 +# replica-announce-ip 5.5.5.5 +# replica-announce-port 1234 + +############################### KEYS TRACKING ################################# + +# The client side caching of values is assisted via server-side support. +# This is implemented using an invalidation table that remembers, using +# a radix key indexed by key name, what clients have which keys. In turn +# this is used in order to send invalidation messages to clients. Please +# check this page to understand more about the feature: +# +# https://valkey.io/topics/client-side-caching +# +# When tracking is enabled for a client, all the read only queries are assumed +# to be cached: this will force the server to store information in the invalidation +# table. When keys are modified, such information is flushed away, and +# invalidation messages are sent to the clients. However if the workload is +# heavily dominated by reads, the server could use more and more memory in order +# to track the keys fetched by many clients. +# +# For this reason it is possible to configure a maximum fill value for the +# invalidation table. By default it is set to 1M of keys, and once this limit +# is reached, the server will start to evict keys in the invalidation table +# even if they were not modified, just to reclaim memory: this will in turn +# force the clients to invalidate the cached values. Basically the table +# maximum size is a trade off between the memory you want to spend server +# side to track information about who cached what, and the ability of clients +# to retain cached objects in memory. +# +# If you set the value to 0, it means there are no limits, and the server will +# retain as many keys as needed in the invalidation table. +# In the "stats" INFO section, you can find information about the number of +# keys in the invalidation table at every given moment. +# +# Note: when key tracking is used in broadcasting mode, no memory is used +# in the server side so this setting is useless. +# +# tracking-table-max-keys 1000000 ################################## SECURITY ################################### -# Require clients to issue AUTH before processing any other -# commands. This might be useful in environments in which you do not trust -# others with access to the host running redis-server. +# Warning: since the server is pretty fast, an outside user can try up to +# 1 million passwords per second against a modern box. This means that you +# should use very strong passwords, otherwise they will be very easy to break. +# Note that because the password is really a shared secret between the client +# and the server, and should not be memorized by any human, the password +# can be easily a long string from /dev/urandom or whatever, so by using a +# long and unguessable password no brute force attack will be possible. + +# ACL users are defined in the following format: # -# This should stay commented out for backward compatibility and because most -# people do not need auth (e.g. they run their own servers). +# user ... acl rules ... # -# Warning: since Redis is pretty fast an outside user can try up to -# 150k passwords per second against a good box. This means that you should -# use a very strong password otherwise it will be very easy to break. +# For example: +# +# user worker +@list +@connection ~jobs:* on >ffa9203c493aa99 +# +# The special username "default" is used for new connections. If this user +# has the "nopass" rule, then new connections will be immediately authenticated +# as the "default" user without the need of any password provided via the +# AUTH command. Otherwise if the "default" user is not flagged with "nopass" +# the connections will start in not authenticated state, and will require +# AUTH (or the HELLO command AUTH option) in order to be authenticated and +# start to work. +# +# The ACL rules that describe what a user can do are the following: +# +# on Enable the user: it is possible to authenticate as this user. +# off Disable the user: it's no longer possible to authenticate +# with this user, however the already authenticated connections +# will still work. +# skip-sanitize-payload RESTORE dump-payload sanitization is skipped. +# sanitize-payload RESTORE dump-payload is sanitized (default). +# + Allow the execution of that command. +# May be used with `|` for allowing subcommands (e.g "+config|get") +# - Disallow the execution of that command. +# May be used with `|` for blocking subcommands (e.g "-config|set") +# +@ Allow the execution of all the commands in such category +# with valid categories are like @admin, @set, @sortedset, ... +# and so forth, see the full list in the server.c file where +# the server command table is described and defined. +# The special category @all means all the commands, but currently +# present in the server, and that will be loaded in the future +# via modules. +# +|first-arg Allow a specific first argument of an otherwise +# disabled command. It is only supported on commands with +# no sub-commands, and is not allowed as negative form +# like -SELECT|1, only additive starting with "+". This +# feature is deprecated and may be removed in the future. +# allcommands Alias for +@all. Note that it implies the ability to execute +# all the future commands loaded via the modules system. +# nocommands Alias for -@all. +# ~ Add a pattern of keys that can be mentioned as part of +# commands. For instance ~* allows all the keys. The pattern +# is a glob-style pattern like the one of KEYS. +# It is possible to specify multiple patterns. +# %R~ Add key read pattern that specifies which keys can be read +# from. +# %W~ Add key write pattern that specifies which keys can be +# written to. +# allkeys Alias for ~* +# resetkeys Flush the list of allowed keys patterns. +# & Add a glob-style pattern of Pub/Sub channels that can be +# accessed by the user. It is possible to specify multiple channel +# patterns. +# allchannels Alias for &* +# resetchannels Flush the list of allowed channel patterns. +# > Add this password to the list of valid password for the user. +# For example >mypass will add "mypass" to the list. +# This directive clears the "nopass" flag (see later). +# < Remove this password from the list of valid passwords. +# nopass All the set passwords of the user are removed, and the user +# is flagged as requiring no password: it means that every +# password will work against this user. If this directive is +# used for the default user, every new connection will be +# immediately authenticated with the default user without +# any explicit AUTH command required. Note that the "resetpass" +# directive will clear this condition. +# resetpass Flush the list of allowed passwords. Moreover removes the +# "nopass" status. After "resetpass" the user has no associated +# passwords and there is no way to authenticate without adding +# some password (or setting it as "nopass" later). +# reset Performs the following actions: resetpass, resetkeys, resetchannels, +# allchannels (if acl-pubsub-default is set), off, clearselectors, -@all. +# The user returns to the same state it has immediately after its creation. +# () Create a new selector with the options specified within the +# parentheses and attach it to the user. Each option should be +# space separated. The first character must be ( and the last +# character must be ). +# clearselectors Remove all of the currently attached selectors. +# Note this does not change the "root" user permissions, +# which are the permissions directly applied onto the +# user (outside the parentheses). +# +# ACL rules can be specified in any order: for instance you can start with +# passwords, then flags, or key patterns. However note that the additive +# and subtractive rules will CHANGE MEANING depending on the ordering. +# For instance see the following example: +# +# user alice on +@all -DEBUG ~* >somepassword +# +# This will allow "alice" to use all the commands with the exception of the +# DEBUG command, since +@all added all the commands to the set of the commands +# alice can use, and later DEBUG was removed. However if we invert the order +# of two ACL rules the result will be different: +# +# user alice on -DEBUG +@all ~* >somepassword +# +# Now DEBUG was removed when alice had yet no commands in the set of allowed +# commands, later all the commands are added, so the user will be able to +# execute everything. +# +# Basically ACL rules are processed left-to-right. +# +# The following is a list of command categories and their meanings: +# * keyspace - Writing or reading from keys, databases, or their metadata +# in a type agnostic way. Includes DEL, RESTORE, DUMP, RENAME, EXISTS, DBSIZE, +# KEYS, EXPIRE, TTL, FLUSHALL, etc. Commands that may modify the keyspace, +# key or metadata will also have `write` category. Commands that only read +# the keyspace, key or metadata will have the `read` category. +# * read - Reading from keys (values or metadata). Note that commands that don't +# interact with keys, will not have either `read` or `write`. +# * write - Writing to keys (values or metadata) +# * admin - Administrative commands. Normal applications will never need to use +# these. Includes REPLICAOF, CONFIG, DEBUG, SAVE, MONITOR, ACL, SHUTDOWN, etc. +# * dangerous - Potentially dangerous (each should be considered with care for +# various reasons). This includes FLUSHALL, MIGRATE, RESTORE, SORT, KEYS, +# CLIENT, DEBUG, INFO, CONFIG, SAVE, REPLICAOF, etc. +# * connection - Commands affecting the connection or other connections. +# This includes AUTH, SELECT, COMMAND, CLIENT, ECHO, PING, etc. +# * blocking - Potentially blocking the connection until released by another +# command. +# * fast - Fast O(1) commands. May loop on the number of arguments, but not the +# number of elements in the key. +# * slow - All commands that are not Fast. +# * pubsub - PUBLISH / SUBSCRIBE related +# * transaction - WATCH / MULTI / EXEC related commands. +# * scripting - Scripting related. +# * set - Data type: sets related. +# * sortedset - Data type: zsets related. +# * list - Data type: lists related. +# * hash - Data type: hashes related. +# * string - Data type: strings related. +# * bitmap - Data type: bitmaps related. +# * hyperloglog - Data type: hyperloglog related. +# * geo - Data type: geo related. +# * stream - Data type: streams related. +# +# For more information about ACL configuration please refer to +# the Valkey web site at https://valkey.io/topics/acl + +# ACL LOG +# +# The ACL Log tracks failed commands and authentication events associated +# with ACLs. The ACL Log is useful to troubleshoot failed commands blocked +# by ACLs. The ACL Log is stored in memory. You can reclaim memory with +# ACL LOG RESET. Define the maximum entry length of the ACL Log below. +acllog-max-len 128 + +# Using an external ACL file +# +# Instead of configuring users here in this file, it is possible to use +# a stand-alone file just listing users. The two methods cannot be mixed: +# if you configure users here and at the same time you activate the external +# ACL file, the server will refuse to start. +# +# The format of the external ACL user file is exactly the same as the +# format that is used inside valkey.conf to describe users. +# +# aclfile /etc/valkey/users.acl + +# IMPORTANT NOTE: "requirepass" is just a compatibility +# layer on top of the new ACL system. The option effect will be just setting +# the password for the default user. Clients will still authenticate using +# AUTH as usually, or more explicitly with AUTH default +# if they follow the new protocol: both will work. +# +# The requirepass is not compatible with aclfile option and the ACL LOAD +# command, these will cause requirepass to be ignored. # # requirepass foobared -# Command renaming. +# The default Pub/Sub channels permission for new users is controlled by the +# acl-pubsub-default configuration directive, which accepts one of these values: +# +# allchannels: grants access to all Pub/Sub channels +# resetchannels: revokes access to all Pub/Sub channels +# +# acl-pubsub-default defaults to 'resetchannels' permission. +# +# acl-pubsub-default resetchannels + +# Command renaming (DEPRECATED). +# +# ------------------------------------------------------------------------ +# WARNING: avoid using this option if possible. Instead use ACLs to remove +# commands from the default user, and put them only in some admin user you +# create for administrative purposes. +# ------------------------------------------------------------------------ # # It is possible to change the name of dangerous commands in a shared # environment. For instance the CONFIG command may be renamed into something @@ -516,56 +1068,61 @@ slave-priority 100 # rename-command CONFIG "" # # Please note that changing the name of commands that are logged into the -# AOF file or transmitted to slaves may cause problems. +# AOF file or transmitted to replicas may cause problems. ################################### CLIENTS #################################### # Set the max number of connected clients at the same time. By default -# this limit is set to 10000 clients, however if the Redis server is not +# this limit is set to 10000 clients, however if the server is not # able to configure the process file limit to allow for the specified limit # the max number of allowed clients is set to the current file limit -# minus 32 (as Redis reserves a few file descriptors for internal uses). +# minus 32 (as the server reserves a few file descriptors for internal uses). # -# Once the limit is reached Redis will close all the new connections sending +# Once the limit is reached the server will close all the new connections sending # an error 'max number of clients reached'. # +# IMPORTANT: With a cluster-enabled setup, the max number of connections is also +# shared with the cluster bus: every node in the cluster will use two +# connections, one incoming and another outgoing. It is important to size the +# limit accordingly in case of very large clusters. +# # maxclients 10000 ############################## MEMORY MANAGEMENT ################################ # Set a memory usage limit to the specified amount of bytes. -# When the memory limit is reached Redis will try to remove keys +# When the memory limit is reached the server will try to remove keys # according to the eviction policy selected (see maxmemory-policy). # -# If Redis can't remove keys according to the policy, or if the policy is -# set to 'noeviction', Redis will start to reply with errors to commands +# If the server can't remove keys according to the policy, or if the policy is +# set to 'noeviction', the server will start to reply with errors to commands # that would use more memory, like SET, LPUSH, and so on, and will continue # to reply to read-only commands like GET. # -# This option is usually useful when using Redis as an LRU or LFU cache, or to +# This option is usually useful when using the server as an LRU or LFU cache, or to # set a hard memory limit for an instance (using the 'noeviction' policy). # -# WARNING: If you have slaves attached to an instance with maxmemory on, -# the size of the output buffers needed to feed the slaves are subtracted +# WARNING: If you have replicas attached to an instance with maxmemory on, +# the size of the output buffers needed to feed the replicas are subtracted # from the used memory count, so that network problems / resyncs will # not trigger a loop where keys are evicted, and in turn the output -# buffer of slaves is full with DELs of keys evicted triggering the deletion +# buffer of replicas is full with DELs of keys evicted triggering the deletion # of more keys, and so forth until the database is completely emptied. # -# In short... if you have slaves attached it is suggested that you set a lower -# limit for maxmemory so that there is some free RAM on the system for slave +# In short... if you have replicas attached it is suggested that you set a lower +# limit for maxmemory so that there is some free RAM on the system for replica # output buffers (but this is not needed if the policy is 'noeviction'). # # maxmemory -# MAXMEMORY POLICY: how Redis will select what to remove when maxmemory -# is reached. You can select among five behaviors: +# MAXMEMORY POLICY: how the server will select what to remove when maxmemory +# is reached. You can select one from the following behaviors: # -# volatile-lru -> Evict using approximated LRU among the keys with an expire set. +# volatile-lru -> Evict using approximated LRU, only keys with an expire set. # allkeys-lru -> Evict any key using approximated LRU. -# volatile-lfu -> Evict using approximated LFU among the keys with an expire set. +# volatile-lfu -> Evict using approximated LFU, only keys with an expire set. # allkeys-lfu -> Evict any key using approximated LFU. -# volatile-random -> Remove a random key among the ones with an expire set. +# volatile-random -> Remove a random key having an expire set. # allkeys-random -> Remove a random key, any key. # volatile-ttl -> Remove the key with the nearest expire time (minor TTL) # noeviction -> Don't evict anything, just return an error on write operations. @@ -576,14 +1133,12 @@ slave-priority 100 # Both LRU, LFU and volatile-ttl are implemented using approximated # randomized algorithms. # -# Note: with any of the above policies, Redis will return an error on write -# operations, when there are no suitable keys for eviction. -# -# At the date of writing these commands are: set setnx setex append -# incr decr rpush lpush rpushx lpushx linsert lset rpoplpush sadd -# sinter sinterstore sunion sunionstore sdiff sdiffstore zadd zincrby -# zunionstore zinterstore hset hsetnx hmset hincrby incrby decrby -# getset mset msetnx exec sort +# Note: with any of the above policies, when there are no suitable keys for +# eviction, the server will return an error on write operations that require +# more memory. These are usually commands that create new keys, add data or +# modify existing keys. A few examples are: SET, INCR, HSET, LPUSH, SUNIONSTORE, +# SORT (due to the STORE argument), and EXEC (if the transaction includes any +# command that requires memory). # # The default is: # @@ -591,8 +1146,8 @@ slave-priority 100 # LRU, LFU and minimal TTL algorithms are not precise algorithms but approximated # algorithms (in order to save memory), so you can tune it for speed or -# accuracy. For default Redis will check five keys and pick the one that was -# used less recently, you can change the sample size using the following +# accuracy. By default the server will check five keys and pick the one that was +# used least recently, you can change the sample size using the following # configuration directive. # # The default of 5 produces good enough results. 10 Approximates very closely @@ -600,18 +1155,63 @@ slave-priority 100 # # maxmemory-samples 5 +# Eviction processing is designed to function well with the default setting. +# If there is an unusually large amount of write traffic, this value may need to +# be increased. Decreasing this value may reduce latency at the risk of +# eviction processing effectiveness +# 0 = minimum latency, 10 = default, 100 = process without regard to latency +# +# maxmemory-eviction-tenacity 10 + +# By default a replica will ignore its maxmemory setting +# (unless it is promoted to master after a failover or manually). It means +# that the eviction of keys will be just handled by the master, sending the +# DEL commands to the replica as keys evict in the master side. +# +# This behavior ensures that masters and replicas stay consistent, and is usually +# what you want, however if your replica is writable, or you want the replica +# to have a different memory setting, and you are sure all the writes performed +# to the replica are idempotent, then you may change this default (but be sure +# to understand what you are doing). +# +# Note that since the replica by default does not evict, it may end using more +# memory than the one set via maxmemory (there are certain buffers that may +# be larger on the replica, or data structures may sometimes take more memory +# and so forth). So make sure you monitor your replicas and make sure they +# have enough memory to never hit a real out-of-memory condition before the +# master hits the configured maxmemory setting. +# +# replica-ignore-maxmemory yes + +# The server reclaims expired keys in two ways: upon access when those keys are +# found to be expired, and also in background, in what is called the +# "active expire key". The key space is slowly and interactively scanned +# looking for expired keys to reclaim, so that it is possible to free memory +# of keys that are expired and will never be accessed again in a short time. +# +# The default effort of the expire cycle will try to avoid having more than +# ten percent of expired keys still in memory, and will try to avoid consuming +# more than 25% of total memory and to add latency to the system. However +# it is possible to increase the expire "effort" that is normally set to +# "1", to a greater value, up to the value "10". At its maximum value the +# system will use more CPU, longer cycles (and technically may introduce +# more latency), and will tolerate less already expired keys still present +# in the system. It's a tradeoff between memory, CPU and latency. +# +# active-expire-effort 1 + ############################# LAZY FREEING #################################### -# Redis has two primitives to delete keys. One is called DEL and is a blocking +# The server has two primitives to delete keys. One is called DEL and is a blocking # deletion of the object. It means that the server stops processing new commands # in order to reclaim all the memory associated with an object in a synchronous # way. If the key deleted is associated with a small object, the time needed # in order to execute the DEL command is very small and comparable to most other -# O(1) or O(log_N) commands in Redis. However if the key is associated with an +# O(1) or O(log_N) commands in the server. However if the key is associated with an # aggregated value containing millions of elements, the server can block for # a long time (even seconds) in order to complete the operation. # -# For the above reasons Redis also offers non blocking deletion primitives +# For the above reasons the server also offers non blocking deletion primitives # such as UNLINK (non blocking DEL) and the ASYNC option of FLUSHALL and # FLUSHDB commands, in order to reclaim memory in background. Those commands # are executed in constant time. Another thread will incrementally free the @@ -619,9 +1219,9 @@ slave-priority 100 # # DEL, UNLINK and ASYNC option of FLUSHALL and FLUSHDB are user-controlled. # It's up to the design of the application to understand when it is a good -# idea to use one or the other. However the Redis server sometimes has to +# idea to use one or the other. However the server sometimes has to # delete keys or flush the whole database as a side effect of other operations. -# Specifically Redis deletes objects independently of a user call in the +# Specifically the server deletes objects independently of a user call in the # following scenarios: # # 1) On eviction, because of the maxmemory and maxmemory policy configurations, @@ -635,51 +1235,184 @@ slave-priority 100 # or SORT with STORE option may delete existing keys. The SET command # itself removes any old content of the specified key in order to replace # it with the specified string. -# 4) During replication, when a slave performs a full resynchronization with +# 4) During replication, when a replica performs a full resynchronization with # its master, the content of the whole database is removed in order to -# load the RDB file just transfered. +# load the RDB file just transferred. # # In all the above cases the default is to delete objects in a blocking way, # like if DEL was called. However you can configure each case specifically # in order to instead release memory in a non-blocking way like if UNLINK -# was called, using the following configuration directives: +# was called, using the following configuration directives. lazyfree-lazy-eviction no lazyfree-lazy-expire no lazyfree-lazy-server-del no -slave-lazy-flush no +replica-lazy-flush no + +# It is also possible, for the case when to replace the user code DEL calls +# with UNLINK calls is not easy, to modify the default behavior of the DEL +# command to act exactly like UNLINK, using the following configuration +# directive: + +lazyfree-lazy-user-del no + +# FLUSHDB, FLUSHALL, SCRIPT FLUSH and FUNCTION FLUSH support both asynchronous and synchronous +# deletion, which can be controlled by passing the [SYNC|ASYNC] flags into the +# commands. When neither flag is passed, this directive will be used to determine +# if the data should be deleted asynchronously. + +lazyfree-lazy-user-flush no + +################################ THREADED I/O ################################# + +# The server is mostly single threaded, however there are certain threaded +# operations such as UNLINK, slow I/O accesses and other things that are +# performed on side threads. +# +# Now it is also possible to handle the server clients socket reads and writes +# in different I/O threads. Since especially writing is so slow, normally +# users use pipelining in order to speed up the server performances per +# core, and spawn multiple instances in order to scale more. Using I/O +# threads it is possible to easily speedup two times the server without resorting +# to pipelining nor sharding of the instance. +# +# By default threading is disabled, we suggest enabling it only in machines +# that have at least 4 or more cores, leaving at least one spare core. +# Using more than 8 threads is unlikely to help much. We also recommend using +# threaded I/O only if you actually have performance problems, with +# instances being able to use a quite big percentage of CPU time, otherwise +# there is no point in using this feature. +# +# So for instance if you have a four cores boxes, try to use 2 or 3 I/O +# threads, if you have a 8 cores, try to use 6 threads. In order to +# enable I/O threads use the following configuration directive: +# +# io-threads 4 +# +# Setting io-threads to 1 will just use the main thread as usual. +# When I/O threads are enabled, we only use threads for writes, that is +# to thread the write(2) syscall and transfer the client buffers to the +# socket. However it is also possible to enable threading of reads and +# protocol parsing using the following configuration directive, by setting +# it to yes: +# +# io-threads-do-reads no +# +# Usually threading reads doesn't help much. +# +# NOTE 1: This configuration directive cannot be changed at runtime via +# CONFIG SET. Also, this feature currently does not work when SSL is +# enabled. +# +# NOTE 2: If you want to test the server speedup using valkey-benchmark, make +# sure you also run the benchmark itself in threaded mode, using the +# --threads option to match the number of server threads, otherwise you'll not +# be able to notice the improvements. + +############################ KERNEL OOM CONTROL ############################## + +# On Linux, it is possible to hint the kernel OOM killer on what processes +# should be killed first when out of memory. +# +# Enabling this feature makes the server actively control the oom_score_adj value +# for all its processes, depending on their role. The default scores will +# attempt to have background child processes killed before all others, and +# replicas killed before masters. +# +# The server supports these options: +# +# no: Don't make changes to oom-score-adj (default). +# yes: Alias to "relative" see below. +# absolute: Values in oom-score-adj-values are written as is to the kernel. +# relative: Values are used relative to the initial value of oom_score_adj when +# the server starts and are then clamped to a range of -1000 to 1000. +# Because typically the initial value is 0, they will often match the +# absolute values. +oom-score-adj no + +# When oom-score-adj is used, this directive controls the specific values used +# for master, replica and background child processes. Values range -2000 to +# 2000 (higher means more likely to be killed). +# +# Unprivileged processes (not root, and without CAP_SYS_RESOURCE capabilities) +# can freely increase their value, but not decrease it below its initial +# settings. This means that setting oom-score-adj to "relative" and setting the +# oom-score-adj-values to positive values will always succeed. +oom-score-adj-values 0 200 800 + + +#################### KERNEL transparent hugepage CONTROL ###################### + +# Usually the kernel Transparent Huge Pages control is set to "madvise" or +# or "never" by default (/sys/kernel/mm/transparent_hugepage/enabled), in which +# case this config has no effect. On systems in which it is set to "always", +# the server will attempt to disable it specifically for the server process in order +# to avoid latency problems specifically with fork(2) and CoW. +# If for some reason you prefer to keep it enabled, you can set this config to +# "no" and the kernel global to "always". + +disable-thp yes ############################## APPEND ONLY MODE ############################### -# By default Redis asynchronously dumps the dataset on disk. This mode is -# good enough in many applications, but an issue with the Redis process or +# By default the server asynchronously dumps the dataset on disk. This mode is +# good enough in many applications, but an issue with the server process or # a power outage may result into a few minutes of writes lost (depending on # the configured save points). # # The Append Only File is an alternative persistence mode that provides # much better durability. For instance using the default data fsync policy -# (see later in the config file) Redis can lose just one second of writes in a +# (see later in the config file) the server can lose just one second of writes in a # dramatic event like a server power outage, or a single write if something -# wrong with the Redis process itself happens, but the operating system is +# wrong with the process itself happens, but the operating system is # still running correctly. # # AOF and RDB persistence can be enabled at the same time without problems. -# If the AOF is enabled on startup Redis will load the AOF, that is the file +# If the AOF is enabled on startup the server will load the AOF, that is the file # with the better durability guarantees. # -# Please check http://redis.io/topics/persistence for more information. +# Please check https://valkey.io/topics/persistence for more information. appendonly no -# The name of the append only file (default: "appendonly.aof") +# The base name of the append only file. +# +# The server uses a set of append-only files to persist the dataset +# and changes applied to it. There are two basic types of files in use: +# +# - Base files, which are a snapshot representing the complete state of the +# dataset at the time the file was created. Base files can be either in +# the form of RDB (binary serialized) or AOF (textual commands). +# - Incremental files, which contain additional commands that were applied +# to the dataset following the previous file. +# +# In addition, manifest files are used to track the files and the order in +# which they were created and should be applied. +# +# Append-only file names are created by the server following a specific pattern. +# The file name's prefix is based on the 'appendfilename' configuration +# parameter, followed by additional information about the sequence and type. +# +# For example, if appendfilename is set to appendonly.aof, the following file +# names could be derived: +# +# - appendonly.aof.1.base.rdb as a base file. +# - appendonly.aof.1.incr.aof, appendonly.aof.2.incr.aof as incremental files. +# - appendonly.aof.manifest as a manifest file. appendfilename "appendonly.aof" +# For convenience, the server stores all persistent append-only files in a dedicated +# directory. The name of the directory is determined by the appenddirname +# configuration parameter. + +appenddirname "appendonlydir" + # The fsync() call tells the Operating System to actually write data on disk # instead of waiting for more data in the output buffer. Some OS will really flush # data on disk, some other OS will just try to do it ASAP. # -# Redis supports three different modes: +# The server supports three different modes: # # no: don't fsync, just let the OS flush the data when it wants. Faster. # always: fsync after every write to the append only log. Slow, Safest. @@ -705,7 +1438,7 @@ appendfsync everysec # When the AOF fsync policy is set to always or everysec, and a background # saving process (a background save or AOF log background rewriting) is # performing a lot of I/O against the disk, in some Linux configurations -# Redis may block too long on the fsync() call. Note that there is no fix for +# the server may block too long on the fsync() call. Note that there is no fix for # this currently, as even performing fsync in a different thread will block # our synchronous write(2) call. # @@ -713,8 +1446,8 @@ appendfsync everysec # that will prevent fsync() from being called in the main process while a # BGSAVE or BGREWRITEAOF is in progress. # -# This means that while another child is saving, the durability of Redis is -# the same as "appendfsync none". In practical terms, this means that it is +# This means that while another child is saving, the durability of the server is +# the same as "appendfsync no". In practical terms, this means that it is # possible to lose up to 30 seconds of log in the worst scenario (with the # default Linux settings). # @@ -724,10 +1457,10 @@ appendfsync everysec no-appendfsync-on-rewrite no # Automatic rewrite of the append only file. -# Redis is able to automatically rewrite the log file implicitly calling +# The server is able to automatically rewrite the log file implicitly calling # BGREWRITEAOF when the AOF log size grows by the specified percentage. # -# This is how it works: Redis remembers the size of the AOF file after the +# This is how it works: The server remembers the size of the AOF file after the # latest rewrite (if no rewrite has happened since the restart, the size of # the AOF at startup is used). # @@ -743,79 +1476,105 @@ no-appendfsync-on-rewrite no auto-aof-rewrite-percentage 100 auto-aof-rewrite-min-size 64mb -# An AOF file may be found to be truncated at the end during the Redis +# An AOF file may be found to be truncated at the end during the server # startup process, when the AOF data gets loaded back into memory. -# This may happen when the system where Redis is running +# This may happen when the system where the server is running # crashes, especially when an ext4 filesystem is mounted without the -# data=ordered option (however this can't happen when Redis itself +# data=ordered option (however this can't happen when the server itself # crashes or aborts but the operating system still works correctly). # -# Redis can either exit with an error when this happens, or load as much +# The server can either exit with an error when this happens, or load as much # data as possible (the default now) and start if the AOF file is found # to be truncated at the end. The following option controls this behavior. # # If aof-load-truncated is set to yes, a truncated AOF file is loaded and -# the Redis server starts emitting a log to inform the user of the event. +# the server starts emitting a log to inform the user of the event. # Otherwise if the option is set to no, the server aborts with an error # and refuses to start. When the option is set to no, the user requires -# to fix the AOF file using the "redis-check-aof" utility before to restart +# to fix the AOF file using the "valkey-check-aof" utility before to restart # the server. # # Note that if the AOF file will be found to be corrupted in the middle # the server will still exit with an error. This option only applies when -# Redis will try to read more data from the AOF file but not enough bytes +# the server will try to read more data from the AOF file but not enough bytes # will be found. aof-load-truncated yes -# When rewriting the AOF file, Redis is able to use an RDB preamble in the -# AOF file for faster rewrites and recoveries. When this option is turned -# on the rewritten AOF file is composed of two different stanzas: -# -# [RDB file][AOF tail] -# -# When loading Redis recognizes that the AOF file starts with the "REDIS" -# string and loads the prefixed RDB file, and continues loading the AOF -# tail. -# -# This is currently turned off by default in order to avoid the surprise -# of a format change, but will at some point be used as the default. -aof-use-rdb-preamble no +# The server can create append-only base files in either RDB or AOF formats. Using +# the RDB format is always faster and more efficient, and disabling it is only +# supported for backward compatibility purposes. +aof-use-rdb-preamble yes -################################ LUA SCRIPTING ############################### +# The server supports recording timestamp annotations in the AOF to support restoring +# the data from a specific point-in-time. However, using this capability changes +# the AOF format in a way that may not be compatible with existing AOF parsers. +aof-timestamp-enabled no -# Max execution time of a Lua script in milliseconds. -# -# If the maximum execution time is reached Redis will log that a script is -# still in execution after the maximum allowed time and will start to -# reply to queries with an error. -# -# When a long running script exceeds the maximum execution time only the -# SCRIPT KILL and SHUTDOWN NOSAVE commands are available. The first can be -# used to stop a script that did not yet called write commands. The second -# is the only way to shut down the server in the case a write command was -# already issued by the script but the user doesn't want to wait for the natural -# termination of the script. -# -# Set it to 0 or a negative value for unlimited execution without warnings. -lua-time-limit 5000 +################################ SHUTDOWN ##################################### -################################ REDIS CLUSTER ############################### +# Maximum time to wait for replicas when shutting down, in seconds. # -# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ -# WARNING EXPERIMENTAL: Redis Cluster is considered to be stable code, however -# in order to mark it as "mature" we need to wait for a non trivial percentage -# of users to deploy it in production. -# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ +# During shut down, a grace period allows any lagging replicas to catch up with +# the latest replication offset before the master exists. This period can +# prevent data loss, especially for deployments without configured disk backups. # -# Normal Redis instances can't be part of a Redis Cluster; only nodes that are -# started as cluster nodes can. In order to start a Redis instance as a +# The 'shutdown-timeout' value is the grace period's duration in seconds. It is +# only applicable when the instance has replicas. To disable the feature, set +# the value to 0. +# +# shutdown-timeout 10 + +# When the server receives a SIGINT or SIGTERM, shutdown is initiated and by default +# an RDB snapshot is written to disk in a blocking operation if save points are configured. +# The options used on signaled shutdown can include the following values: +# default: Saves RDB snapshot only if save points are configured. +# Waits for lagging replicas to catch up. +# save: Forces a DB saving operation even if no save points are configured. +# nosave: Prevents DB saving operation even if one or more save points are configured. +# now: Skips waiting for lagging replicas. +# force: Ignores any errors that would normally prevent the server from exiting. +# +# Any combination of values is allowed as long as "save" and "nosave" are not set simultaneously. +# Example: "nosave force now" +# +# shutdown-on-sigint default +# shutdown-on-sigterm default + +################ NON-DETERMINISTIC LONG BLOCKING COMMANDS ##################### + +# Maximum time in milliseconds for EVAL scripts, functions and in some cases +# modules' commands before the server can start processing or rejecting other clients. +# +# If the maximum execution time is reached the server will start to reply to most +# commands with a BUSY error. +# +# In this state the server will only allow a handful of commands to be executed. +# For instance, SCRIPT KILL, FUNCTION KILL, SHUTDOWN NOSAVE and possibly some +# module specific 'allow-busy' commands. +# +# SCRIPT KILL and FUNCTION KILL will only be able to stop a script that did not +# yet call any write commands, so SHUTDOWN NOSAVE may be the only way to stop +# the server in the case a write command was already issued by the script when +# the user doesn't want to wait for the natural termination of the script. +# +# The default is 5 seconds. It is possible to set it to 0 or a negative value +# to disable this mechanism (uninterrupted execution). Note that in the past +# this config had a different name, which is now an alias, so both of these do +# the same: +# lua-time-limit 5000 +# busy-reply-threshold 5000 + +################################ VALKEY CLUSTER ############################### + +# Normal server instances can't be part of a cluster; only nodes that are +# started as cluster nodes can. In order to start a server instance as a # cluster node enable the cluster support uncommenting the following: # # cluster-enabled yes # Every cluster node has a cluster configuration file. This file is not -# intended to be edited by hand. It is created and updated by Redis nodes. -# Every Redis Cluster node requires a different cluster configuration file. +# intended to be edited by hand. It is created and updated by each node. +# Every cluster node requires a different cluster configuration file. # Make sure that instances running in the same system do not have # overlapping cluster configuration file names. # @@ -823,46 +1582,51 @@ lua-time-limit 5000 # Cluster node timeout is the amount of milliseconds a node must be unreachable # for it to be considered in failure state. -# Most other internal time limits are multiple of the node timeout. +# Most other internal time limits are a multiple of the node timeout. # # cluster-node-timeout 15000 -# A slave of a failing master will avoid to start a failover if its data +# The cluster port is the port that the cluster bus will listen for inbound connections on. When set +# to the default value, 0, it will be bound to the command port + 10000. Setting this value requires +# you to specify the cluster bus port when executing cluster meet. +# cluster-port 0 + +# A replica of a failing master will avoid to start a failover if its data # looks too old. # -# There is no simple way for a slave to actually have an exact measure of +# There is no simple way for a replica to actually have an exact measure of # its "data age", so the following two checks are performed: # -# 1) If there are multiple slaves able to failover, they exchange messages -# in order to try to give an advantage to the slave with the best +# 1) If there are multiple replicas able to failover, they exchange messages +# in order to try to give an advantage to the replica with the best # replication offset (more data from the master processed). -# Slaves will try to get their rank by offset, and apply to the start +# Replicas will try to get their rank by offset, and apply to the start # of the failover a delay proportional to their rank. # -# 2) Every single slave computes the time of the last interaction with +# 2) Every single replica computes the time of the last interaction with # its master. This can be the last ping or command received (if the master # is still in the "connected" state), or the time that elapsed since the # disconnection with the master (if the replication link is currently down). -# If the last interaction is too old, the slave will not try to failover +# If the last interaction is too old, the replica will not try to failover # at all. # -# The point "2" can be tuned by user. Specifically a slave will not perform +# The point "2" can be tuned by user. Specifically a replica will not perform # the failover if, since the last interaction with the master, the time # elapsed is greater than: # -# (node-timeout * slave-validity-factor) + repl-ping-slave-period +# (node-timeout * cluster-replica-validity-factor) + repl-ping-replica-period # -# So for example if node-timeout is 30 seconds, and the slave-validity-factor -# is 10, and assuming a default repl-ping-slave-period of 10 seconds, the -# slave will not try to failover if it was not able to talk with the master +# So for example if node-timeout is 30 seconds, and the cluster-replica-validity-factor +# is 10, and assuming a default repl-ping-replica-period of 10 seconds, the +# replica will not try to failover if it was not able to talk with the master # for longer than 310 seconds. # -# A large slave-validity-factor may allow slaves with too old data to failover +# A large cluster-replica-validity-factor may allow replicas with too old data to failover # a master, while a too small value may prevent the cluster from being able to -# elect a slave at all. +# elect a replica at all. # -# For maximum availability, it is possible to set the slave-validity-factor -# to a value of 0, which means, that slaves will always try to failover the +# For maximum availability, it is possible to set the cluster-replica-validity-factor +# to a value of 0, which means, that replicas will always try to failover the # master regardless of the last time they interacted with the master. # (However they'll always try to apply a delay proportional to their # offset rank). @@ -870,29 +1634,38 @@ lua-time-limit 5000 # Zero is the only value able to guarantee that when all the partitions heal # the cluster will always be able to continue. # -# cluster-slave-validity-factor 10 +# cluster-replica-validity-factor 10 -# Cluster slaves are able to migrate to orphaned masters, that are masters -# that are left without working slaves. This improves the cluster ability +# Cluster replicas are able to migrate to orphaned masters, that are masters +# that are left without working replicas. This improves the cluster ability # to resist to failures as otherwise an orphaned master can't be failed over -# in case of failure if it has no working slaves. +# in case of failure if it has no working replicas. # -# Slaves migrate to orphaned masters only if there are still at least a -# given number of other working slaves for their old master. This number -# is the "migration barrier". A migration barrier of 1 means that a slave -# will migrate only if there is at least 1 other working slave for its master -# and so forth. It usually reflects the number of slaves you want for every +# Replicas migrate to orphaned masters only if there are still at least a +# given number of other working replicas for their old master. This number +# is the "migration barrier". A migration barrier of 1 means that a replica +# will migrate only if there is at least 1 other working replica for its master +# and so forth. It usually reflects the number of replicas you want for every # master in your cluster. # -# Default is 1 (slaves migrate only if their masters remain with at least -# one slave). To disable migration just set it to a very large value. +# Default is 1 (replicas migrate only if their masters remain with at least +# one replica). To disable migration just set it to a very large value or +# set cluster-allow-replica-migration to 'no'. # A value of 0 can be set but is useful only for debugging and dangerous # in production. # # cluster-migration-barrier 1 -# By default Redis Cluster nodes stop accepting queries if they detect there -# is at least an hash slot uncovered (no available node is serving it). +# Turning off this option allows to use less automatic cluster configuration. +# It both disables migration to orphaned masters and migration from masters +# that became empty. +# +# Default is 'yes' (allow automatic migrations). +# +# cluster-allow-replica-migration yes + +# By default cluster nodes stop accepting queries if they detect there +# is at least a hash slot uncovered (no available node is serving it). # This way if the cluster is partially down (for example a range of hash slots # are no longer covered) all the cluster becomes, eventually, unavailable. # It automatically returns available as soon as all the slots are covered again. @@ -904,62 +1677,135 @@ lua-time-limit 5000 # # cluster-require-full-coverage yes -# This option, when set to yes, prevents slaves from trying to failover its -# master during master failures. However the master can still perform a +# This option, when set to yes, prevents replicas from trying to failover its +# master during master failures. However the replica can still perform a # manual failover, if forced to do so. # # This is useful in different scenarios, especially in the case of multiple # data center operations, where we want one side to never be promoted if not # in the case of a total DC failure. # -# cluster-slave-no-failover no +# cluster-replica-no-failover no + +# This option, when set to yes, allows nodes to serve read traffic while the +# cluster is in a down state, as long as it believes it owns the slots. +# +# This is useful for two cases. The first case is for when an application +# doesn't require consistency of data during node failures or network partitions. +# One example of this is a cache, where as long as the node has the data it +# should be able to serve it. +# +# The second use case is for configurations that don't meet the recommended +# three shards but want to enable cluster mode and scale later. A +# master outage in a 1 or 2 shard configuration causes a read/write outage to the +# entire cluster without this option set, with it set there is only a write outage. +# Without a quorum of masters, slot ownership will not change automatically. +# +# cluster-allow-reads-when-down no + +# This option, when set to yes, allows nodes to serve pubsub shard traffic while +# the cluster is in a down state, as long as it believes it owns the slots. +# +# This is useful if the application would like to use the pubsub feature even when +# the cluster global stable state is not OK. If the application wants to make sure only +# one shard is serving a given channel, this feature should be kept as yes. +# +# cluster-allow-pubsubshard-when-down yes + +# Cluster link send buffer limit is the limit on the memory usage of an individual +# cluster bus link's send buffer in bytes. Cluster links would be freed if they exceed +# this limit. This is to primarily prevent send buffers from growing unbounded on links +# toward slow peers (E.g. PubSub messages being piled up). +# This limit is disabled by default. Enable this limit when 'mem_cluster_links' INFO field +# and/or 'send-buffer-allocated' entries in the 'CLUSTER LINKS` command output continuously increase. +# Minimum limit of 1gb is recommended so that cluster link buffer can fit in at least a single +# PubSub message by default. (client-query-buffer-limit default value is 1gb) +# +# cluster-link-sendbuf-limit 0 + +# Clusters can configure their announced hostname using this config. This is a common use case for +# applications that need to use TLS Server Name Indication (SNI) or dealing with DNS based +# routing. By default this value is only shown as additional metadata in the CLUSTER SLOTS +# command, but can be changed using 'cluster-preferred-endpoint-type' config. This value is +# communicated along the clusterbus to all nodes, setting it to an empty string will remove +# the hostname and also propagate the removal. +# +# cluster-announce-hostname "" + +# Clusters can configure an optional nodename to be used in addition to the node ID for +# debugging and admin information. This name is broadcasted between nodes, so will be used +# in addition to the node ID when reporting cross node events such as node failures. +# cluster-announce-human-nodename "" + +# Clusters can advertise how clients should connect to them using either their IP address, +# a user defined hostname, or by declaring they have no endpoint. Which endpoint is +# shown as the preferred endpoint is set by using the cluster-preferred-endpoint-type +# config with values 'ip', 'hostname', or 'unknown-endpoint'. This value controls how +# the endpoint returned for MOVED/ASKING requests as well as the first field of CLUSTER SLOTS. +# If the preferred endpoint type is set to hostname, but no announced hostname is set, a '?' +# will be returned instead. +# +# When a cluster advertises itself as having an unknown endpoint, it's indicating that +# the server doesn't know how clients can reach the cluster. This can happen in certain +# networking situations where there are multiple possible routes to the node, and the +# server doesn't know which one the client took. In this case, the server is expecting +# the client to reach out on the same endpoint it used for making the last request, but use +# the port provided in the response. +# +# cluster-preferred-endpoint-type ip # In order to setup your cluster make sure to read the documentation -# available at http://redis.io web site. +# available at https://valkey.io web site. ########################## CLUSTER DOCKER/NAT support ######################## -# In certain deployments, Redis Cluster nodes address discovery fails, because +# In certain deployments, cluster node's address discovery fails, because # addresses are NAT-ted or because ports are forwarded (the typical case is # Docker and other containers). # -# In order to make Redis Cluster working in such environments, a static +# In order to make a cluster work in such environments, a static # configuration where each node knows its public address is needed. The -# following two options are used for this scope, and are: +# following four options are used for this scope, and are: # # * cluster-announce-ip # * cluster-announce-port +# * cluster-announce-tls-port # * cluster-announce-bus-port # -# Each instruct the node about its address, client port, and cluster message -# bus port. The information is then published in the header of the bus packets -# so that other nodes will be able to correctly map the address of the node -# publishing the information. +# Each instructs the node about its address, client ports (for connections +# without and with TLS) and cluster message bus port. The information is then +# published in the header of the bus packets so that other nodes will be able to +# correctly map the address of the node publishing the information. # -# If the above options are not used, the normal Redis Cluster auto-detection +# If tls-cluster is set to yes and cluster-announce-tls-port is omitted or set +# to zero, then cluster-announce-port refers to the TLS port. Note also that +# cluster-announce-tls-port has no effect if tls-cluster is set to no. +# +# If the above options are not used, the normal cluster auto-detection # will be used instead. # # Note that when remapped, the bus port may not be at the fixed offset of # clients port + 10000, so you can specify any port and bus-port depending # on how they get remapped. If the bus-port is not set, a fixed offset of -# 10000 will be used as usually. +# 10000 will be used as usual. # # Example: # # cluster-announce-ip 10.1.1.5 -# cluster-announce-port 6379 +# cluster-announce-tls-port 6379 +# cluster-announce-port 0 # cluster-announce-bus-port 6380 ################################## SLOW LOG ################################### -# The Redis Slow Log is a system to log queries that exceeded a specified +# The server Slow Log is a system to log queries that exceeded a specified # execution time. The execution time does not include the I/O operations # like talking with the client, sending the reply and so forth, # but just the time needed to actually execute the command (this is the only # stage of command execution where the thread is blocked and can not serve # other requests in the meantime). # -# You can configure the slow log with two parameters: one tells Redis +# You can configure the slow log with two parameters: one tells the server # what is the execution time, in microseconds, to exceed in order for the # command to get logged, and the other parameter is the length of the # slow log. When a new command is logged the oldest one is removed from the @@ -976,9 +1822,9 @@ slowlog-max-len 128 ################################ LATENCY MONITOR ############################## -# The Redis latency monitoring subsystem samples different operations +# The server latency monitoring subsystem samples different operations # at runtime in order to collect data related to possible sources of -# latency of a Redis instance. +# latency of a server instance. # # Via the LATENCY command this information is available to the user that can # print graphs and obtain reports. @@ -995,10 +1841,24 @@ slowlog-max-len 128 # "CONFIG SET latency-monitor-threshold " if needed. latency-monitor-threshold 0 +################################ LATENCY TRACKING ############################## + +# The server's extended latency monitoring tracks the per command latencies and enables +# exporting the percentile distribution via the INFO latencystats command, +# and cumulative latency distributions (histograms) via the LATENCY command. +# +# By default, the extended latency monitoring is enabled since the overhead +# of keeping track of the command latency is very small. +# latency-tracking yes + +# By default the exported latency percentiles via the INFO latencystats command +# are the p50, p99, and p999. +# latency-tracking-info-percentiles 50 99 99.9 + ############################# EVENT NOTIFICATION ############################## -# Redis can notify Pub/Sub clients about events happening in the key space. -# This feature is documented at http://redis.io/topics/notifications +# The server can notify Pub/Sub clients about events happening in the key space. +# This feature is documented at https://valkey.io/topics/notifications # # For instance if keyspace events notification is enabled, and a client # performs a DEL operation on key "foo" stored in the Database 0, two @@ -1007,7 +1867,7 @@ latency-monitor-threshold 0 # PUBLISH __keyspace@0__:foo del # PUBLISH __keyevent@0__:del foo # -# It is possible to select the events that Redis will notify among a set +# It is possible to select the events that the server will notify among a set # of classes. Every class is identified by a single character: # # K Keyspace events, published with __keyspace@__ prefix. @@ -1020,7 +1880,13 @@ latency-monitor-threshold 0 # z Sorted set commands # x Expired events (events generated every time a key expires) # e Evicted events (events generated when a key is evicted for maxmemory) -# A Alias for g$lshzxe, so that the "AKE" string means all the events. +# n New key events (Note: not included in the 'A' class) +# t Stream commands +# d Module key type events +# m Key-miss events (Note: It is not included in the 'A' class) +# A Alias for g$lshzxetd, so that the "AKE" string means all the events +# (Except key-miss events which are excluded from 'A' due to their +# unique nature). # # The "notify-keyspace-events" takes as argument a string that is composed # of zero or multiple characters. The empty string means that notifications @@ -1046,8 +1912,8 @@ notify-keyspace-events "" # Hashes are encoded using a memory efficient data structure when they have a # small number of entries, and the biggest entry does not exceed a given # threshold. These thresholds can be configured using the following directives. -hash-max-ziplist-entries 512 -hash-max-ziplist-value 64 +hash-max-listpack-entries 512 +hash-max-listpack-value 64 # Lists are also encoded in a special way to save a lot of space. # The number of entries allowed per internal list node can be specified @@ -1062,7 +1928,7 @@ hash-max-ziplist-value 64 # per list node. # The highest performing option is usually -2 (8 Kb size) or -1 (4 Kb size), # but if your use case is unique, adjust the settings as necessary. -list-max-ziplist-size -2 +list-max-listpack-size -2 # Lists may also be compressed. # Compress depth is the number of quicklist ziplist nodes from *each* side of @@ -1080,21 +1946,28 @@ list-max-ziplist-size -2 # etc. list-compress-depth 0 -# Sets have a special encoding in just one case: when a set is composed +# Sets have a special encoding when a set is composed # of just strings that happen to be integers in radix 10 in the range # of 64 bit signed integers. # The following configuration setting sets the limit in the size of the # set in order to use this special memory saving encoding. set-max-intset-entries 512 +# Sets containing non-integer values are also encoded using a memory efficient +# data structure when they have a small number of entries, and the biggest entry +# does not exceed a given threshold. These thresholds can be configured using +# the following directives. +set-max-listpack-entries 128 +set-max-listpack-value 64 + # Similarly to hashes and lists, sorted sets are also specially encoded in # order to save a lot of space. This encoding is only used when the length and # elements of a sorted set are below the following limits: -zset-max-ziplist-entries 128 -zset-max-ziplist-value 64 +zset-max-listpack-entries 128 +zset-max-listpack-value 64 # HyperLogLog sparse representation bytes limit. The limit includes the -# 16 bytes header. When an HyperLogLog using the sparse representation crosses +# 16 bytes header. When a HyperLogLog using the sparse representation crosses # this limit, it is converted into the dense representation. # # A value greater than 16000 is totally useless, since at that point the @@ -1107,9 +1980,20 @@ zset-max-ziplist-value 64 # composed of many HyperLogLogs with cardinality in the 0 - 15000 range. hll-sparse-max-bytes 3000 +# Streams macro node max size / items. The stream data structure is a radix +# tree of big nodes that encode multiple items inside. Using this configuration +# it is possible to configure how big a single node can be in bytes, and the +# maximum number of items it may contain before switching to a new node when +# appending new stream entries. If any of the following settings are set to +# zero, the limit is ignored, so for instance it is possible to set just a +# max entries limit by setting max-bytes to 0 and max-entries to the desired +# value. +stream-node-max-bytes 4096 +stream-node-max-entries 100 + # Active rehashing uses 1 millisecond every 100 milliseconds of CPU time in -# order to help rehashing the main Redis hash table (the one mapping top-level -# keys to values). The hash table implementation Redis uses (see dict.c) +# order to help rehashing the main server hash table (the one mapping top-level +# keys to values). The hash table implementation the server uses (see dict.c) # performs a lazy rehashing: the more operation you run into a hash table # that is rehashing, the more rehashing "steps" are performed, so if the # server is idle the rehashing is never complete and some more memory is used @@ -1120,7 +2004,7 @@ hll-sparse-max-bytes 3000 # # If unsure: # use "activerehashing no" if you have hard latency requirements and it is -# not a good thing in your environment that Redis can reply from time to time +# not a good thing in your environment that the server can reply from time to time # to queries with 2 milliseconds delay. # # use "activerehashing yes" if you don't have such hard requirements but @@ -1135,7 +2019,7 @@ activerehashing yes # The limit can be set differently for the three different classes of clients: # # normal -> normal clients including MONITOR clients -# slave -> slave clients +# replica -> replica clients # pubsub -> clients subscribed to at least one pubsub channel or pattern # # The syntax of every client-output-buffer-limit directive is the following: @@ -1156,12 +2040,19 @@ activerehashing yes # asynchronous clients may create a scenario where data is requested faster # than it can read. # -# Instead there is a default limit for pubsub and slave clients, since -# subscribers and slaves receive data in a push fashion. +# Instead there is a default limit for pubsub and replica clients, since +# subscribers and replicas receive data in a push fashion. +# +# Note that it doesn't make sense to set the replica clients output buffer +# limit lower than the repl-backlog-size config (partial sync will succeed +# and then replica will get disconnected). +# Such a configuration is ignored (the size of repl-backlog-size will be used). +# This doesn't have memory consumption implications since the replica client +# will share the backlog buffers memory. # # Both the hard or the soft limit can be disabled by setting them to zero. client-output-buffer-limit normal 0 0 0 -client-output-buffer-limit slave 256mb 64mb 60 +client-output-buffer-limit replica 256mb 64mb 60 client-output-buffer-limit pubsub 32mb 8mb 60 # Client query buffers accumulate new commands. They are limited to a fixed @@ -1172,21 +2063,40 @@ client-output-buffer-limit pubsub 32mb 8mb 60 # # client-query-buffer-limit 1gb -# In the Redis protocol, bulk requests, that are, elements representing single -# strings, are normally limited ot 512 mb. However you can change this limit -# here. +# In some scenarios client connections can hog up memory leading to OOM +# errors or data eviction. To avoid this we can cap the accumulated memory +# used by all client connections (all pubsub and normal clients). Once we +# reach that limit connections will be dropped by the server freeing up +# memory. The server will attempt to drop the connections using the most +# memory first. We call this mechanism "client eviction". +# +# Client eviction is configured using the maxmemory-clients setting as follows: +# 0 - client eviction is disabled (default) +# +# A memory value can be used for the client eviction threshold, +# for example: +# maxmemory-clients 1g +# +# A percentage value (between 1% and 100%) means the client eviction threshold +# is based on a percentage of the maxmemory setting. For example to set client +# eviction at 5% of maxmemory: +# maxmemory-clients 5% + +# In the server protocol, bulk requests, that are, elements representing single +# strings, are normally limited to 512 mb. However you can change this limit +# here, but must be 1mb or greater # # proto-max-bulk-len 512mb -# Redis calls an internal function to perform many background tasks, like +# The server calls an internal function to perform many background tasks, like # closing connections of clients in timeout, purging expired keys that are # never requested, and so forth. # -# Not all tasks are performed with the same frequency, but Redis checks for +# Not all tasks are performed with the same frequency, but the server checks for # tasks to perform according to the specified "hz" value. # # By default "hz" is set to 10. Raising the value will use more CPU when -# Redis is idle, but at the same time will make Redis more responsive when +# the server is idle, but at the same time will make the server more responsive when # there are many keys expiring at the same time, and timeouts may be # handled with more precision. # @@ -1195,22 +2105,44 @@ client-output-buffer-limit pubsub 32mb 8mb 60 # 100 only in environments where very low latency is required. hz 10 +# Normally it is useful to have an HZ value which is proportional to the +# number of clients connected. This is useful in order, for instance, to +# avoid too many clients are processed for each background task invocation +# in order to avoid latency spikes. +# +# Since the default HZ value by default is conservatively set to 10, the server +# offers, and enables by default, the ability to use an adaptive HZ value +# which will temporarily raise when there are many connected clients. +# +# When dynamic HZ is enabled, the actual configured HZ will be used +# as a baseline, but multiples of the configured HZ value will be actually +# used as needed once more clients are connected. In this way an idle +# instance will use very little CPU time while a busy instance will be +# more responsive. +dynamic-hz yes + # When a child rewrites the AOF file, if the following option is enabled -# the file will be fsync-ed every 32 MB of data generated. This is useful +# the file will be fsync-ed every 4 MB of data generated. This is useful # in order to commit the file to the disk more incrementally and avoid # big latency spikes. aof-rewrite-incremental-fsync yes -# Redis LFU eviction (see maxmemory setting) can be tuned. However it is a good +# When the server saves RDB file, if the following option is enabled +# the file will be fsync-ed every 4 MB of data generated. This is useful +# in order to commit the file to the disk more incrementally and avoid +# big latency spikes. +rdb-save-incremental-fsync yes + +# The server's LFU eviction (see maxmemory setting) can be tuned. However it is a good # idea to start with the default settings and only change them after investigating # how to improve the performances and how the keys LFU change over time, which # is possible to inspect via the OBJECT FREQ command. # -# There are two tunable parameters in the Redis LFU implementation: the +# There are two tunable parameters in the server LFU implementation: the # counter logarithm factor and the counter decay time. It is important to # understand what the two parameters mean before changing them. # -# The LFU counter is just 8 bits per key, it's maximum value is 255, so Redis +# The LFU counter is just 8 bits per key, it's maximum value is 255, so the server # uses a probabilistic increment with logarithmic behavior. Given the value # of the old counter, when a key is accessed, the counter is incremented in # this way: @@ -1237,32 +2169,27 @@ aof-rewrite-incremental-fsync yes # # NOTE: The above table was obtained by running the following commands: # -# redis-benchmark -n 1000000 incr foo -# redis-cli object freq foo +# valkey-benchmark -n 1000000 incr foo +# valkey-cli object freq foo # # NOTE 2: The counter initial value is 5 in order to give new objects a chance # to accumulate hits. # # The counter decay time is the time, in minutes, that must elapse in order -# for the key counter to be divided by two (or decremented if it has a value -# less <= 10). +# for the key counter to be decremented. # -# The default value for the lfu-decay-time is 1. A Special value of 0 means to -# decay the counter every time it happens to be scanned. +# The default value for the lfu-decay-time is 1. A special value of 0 means we +# will never decay the counter. # # lfu-log-factor 10 # lfu-decay-time 1 ########################### ACTIVE DEFRAGMENTATION ####################### # -# WARNING THIS FEATURE IS EXPERIMENTAL. However it was stress tested -# even in production and manually tested by multiple engineers for some -# time. -# # What is active defragmentation? # ------------------------------- # -# Active (online) defragmentation allows a Redis server to compact the +# Active (online) defragmentation allows a server to compact the # spaces left between small allocations and deallocations of data in memory, # thus allowing to reclaim back memory. # @@ -1270,11 +2197,11 @@ aof-rewrite-incremental-fsync yes # less so with Jemalloc, fortunately) and certain workloads. Normally a server # restart is needed in order to lower the fragmentation, or at least to flush # away all the data and create it again. However thanks to this feature -# implemented by Oran Agra for Redis 4.0 this process can happen at runtime -# in an "hot" way, while the server is running. +# implemented by Oran Agra, this process can happen at runtime +# in a "hot" way, while the server is running. # # Basically when the fragmentation is over a certain level (see the -# configuration options below) Redis will start to create new copies of the +# configuration options below) the server will start to create new copies of the # values in contiguous memory regions by exploiting certain specific Jemalloc # features (in order to understand if an allocation is causing fragmentation # and to allocate it in a better place), and at the same time, will release the @@ -1283,8 +2210,8 @@ aof-rewrite-incremental-fsync yes # # Important things to understand: # -# 1. This feature is disabled by default, and only works if you compiled Redis -# to use the copy of Jemalloc we ship with the source code of Redis. +# 1. This feature is disabled by default, and only works if you compiled the server +# to use the copy of Jemalloc we ship with the source code of the server. # This is the default with Linux builds. # # 2. You never need to enable this feature if you don't have fragmentation @@ -1297,8 +2224,8 @@ aof-rewrite-incremental-fsync yes # defragmentation process. If you are not sure about what they mean it is # a good idea to leave the defaults untouched. -# Enabled active defragmentation -# activedefrag yes +# Active defragmentation is disabled by default +# activedefrag no # Minimum amount of fragmentation waste to start active defrag # active-defrag-ignore-bytes 100mb @@ -1309,9 +2236,49 @@ aof-rewrite-incremental-fsync yes # Maximum percentage of fragmentation at which we use maximum effort # active-defrag-threshold-upper 100 -# Minimal effort for defrag in CPU percentage -# active-defrag-cycle-min 25 +# Minimal effort for defrag in CPU percentage, to be used when the lower +# threshold is reached +# active-defrag-cycle-min 1 -# Maximal effort for defrag in CPU percentage -# active-defrag-cycle-max 75 +# Maximal effort for defrag in CPU percentage, to be used when the upper +# threshold is reached +# active-defrag-cycle-max 25 +# Maximum number of set/hash/zset/list fields that will be processed from +# the main dictionary scan +# active-defrag-max-scan-fields 1000 + +# Jemalloc background thread for purging will be enabled by default +jemalloc-bg-thread yes + +# It is possible to pin different threads and processes of the server to specific +# CPUs in your system, in order to maximize the performances of the server. +# This is useful both in order to pin different server threads in different +# CPUs, but also in order to make sure that multiple server instances running +# in the same host will be pinned to different CPUs. +# +# Normally you can do this using the "taskset" command, however it is also +# possible to do this via the server configuration directly, both in Linux and FreeBSD. +# +# You can pin the server/IO threads, bio threads, aof rewrite child process, and +# the bgsave child process. The syntax to specify the cpu list is the same as +# the taskset command: +# +# Set redis server/io threads to cpu affinity 0,2,4,6: +# server_cpulist 0-7:2 +# +# Set bio threads to cpu affinity 1,3: +# bio_cpulist 1,3 +# +# Set aof rewrite child process to cpu affinity 8,9,10,11: +# aof_rewrite_cpulist 8-11 +# +# Set bgsave child process to cpu affinity 1,10,11 +# bgsave_cpulist 1,10-11 + +# In some cases the server will emit warnings and even refuse to start if it detects +# that the system is in bad state, it is possible to suppress these warnings +# by setting the following config which takes a space delimited list of warnings +# to suppress +# +# ignore-warnings ARM64-COW-BUG diff --git a/temp/prepare.conf b/temp/prepare.conf index 48f22e7..e6cab2a 100644 --- a/temp/prepare.conf +++ b/temp/prepare.conf @@ -1,9 +1,9 @@ -# Redis configuration file example. +# Valkey configuration file example. # -# Note that in order to read the configuration file, Redis must be +# Note that in order to read the configuration file, the server must be # started with the file path as first argument: # -# ./redis-server /path/to/redis.conf +# ./valkey-server /path/to/valkey.conf # Note on units: when memory size is needed, it is possible to specify # it in the usual form of 1k 5GB 4M and so forth: @@ -20,20 +20,29 @@ ################################## INCLUDES ################################### # Include one or more other config files here. This is useful if you -# have a standard template that goes to all Redis servers but also need +# have a standard template that goes to all servers but also need # to customize a few per-server settings. Include files can include # other files, so use this wisely. # -# Notice option "include" won't be rewritten by command "CONFIG REWRITE" -# from admin or Redis Sentinel. Since Redis always uses the last processed +# Note that option "include" won't be rewritten by command "CONFIG REWRITE" +# from admin or Sentinel. Since the server always uses the last processed # line as value of a configuration directive, you'd better put includes # at the beginning of this file to avoid overwriting config change at runtime. # # If instead you are interested in using includes to override configuration # options, it is better to use include as the last line. # +# Included paths may contain wildcards. All files matching the wildcards will +# be included in alphabetical order. +# Note that if an include path contains a wildcards but no files match it when +# the server is started, the include statement will be ignored and no error will +# be emitted. It is safe, therefore, to include wildcard files from empty +# directories. +# # include /path/to/local.conf # include /path/to/other.conf +# include /path/to/fragments/*.conf +# ################################## MODULES ##################################### @@ -45,56 +54,93 @@ ################################## NETWORK ##################################### -# By default, if no "bind" configuration directive is specified, Redis listens -# for connections from all the network interfaces available on the server. +# By default, if no "bind" configuration directive is specified, the server listens +# for connections from all available network interfaces on the host machine. # It is possible to listen to just one or multiple selected interfaces using # the "bind" configuration directive, followed by one or more IP addresses. +# Each address can be prefixed by "-", which means that the server will not fail to +# start if the address is not available. Being not available only refers to +# addresses that does not correspond to any network interface. Addresses that +# are already in use will always fail, and unsupported protocols will always BE +# silently skipped. # # Examples: # -# bind 192.168.1.100 10.0.0.1 -# bind 127.0.0.1 ::1 +# bind 192.168.1.100 10.0.0.1 # listens on two specific IPv4 addresses +# bind 127.0.0.1 ::1 # listens on loopback IPv4 and IPv6 +# bind * -::* # like the default, all available interfaces # -# ~~~ WARNING ~~~ If the computer running Redis is directly exposed to the +# ~~~ WARNING ~~~ If the computer running the server is directly exposed to the # internet, binding to all the interfaces is dangerous and will expose the # instance to everybody on the internet. So by default we uncomment the -# following bind directive, that will force Redis to listen only into -# the IPv4 lookback interface address (this means Redis will be able to -# accept connections only from clients running into the same computer it -# is running). +# following bind directive, that will force the server to listen only on the +# IPv4 and IPv6 (if available) loopback interface addresses (this means the server +# will only be able to accept client connections from the same host that it is +# running on). # # IF YOU ARE SURE YOU WANT YOUR INSTANCE TO LISTEN TO ALL THE INTERFACES -# JUST COMMENT THE FOLLOWING LINE. +# COMMENT OUT THE FOLLOWING LINE. +# +# You will also need to set a password unless you explicitly disable protected +# mode. # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -bind 127.0.0.1 +bind 127.0.0.1 -::1 + +# By default, outgoing connections (from replica to master, from Sentinel to +# instances, cluster bus, etc.) are not bound to a specific local address. In +# most cases, this means the operating system will handle that based on routing +# and the interface through which the connection goes out. +# +# Using bind-source-addr it is possible to configure a specific address to bind +# to, which may also affect how the connection gets routed. +# +# Example: +# +# bind-source-addr 10.0.0.1 # Protected mode is a layer of security protection, in order to avoid that -# Redis instances left open on the internet are accessed and exploited. +# the server instances left open on the internet are accessed and exploited. # -# When protected mode is on and if: -# -# 1) The server is not binding explicitly to a set of addresses using the -# "bind" directive. -# 2) No password is configured. -# -# The server only accepts connections from clients connecting from the -# IPv4 and IPv6 loopback addresses 127.0.0.1 and ::1, and from Unix domain -# sockets. +# When protected mode is on and the default user has no password, the server +# only accepts local connections from the IPv4 address (127.0.0.1), IPv6 address +# (::1) or Unix domain sockets. # # By default protected mode is enabled. You should disable it only if -# you are sure you want clients from other hosts to connect to Redis -# even if no authentication is configured, nor a specific set of interfaces -# are explicitly listed using the "bind" directive. +# you are sure you want clients from other hosts to connect to the server +# even if no authentication is configured. protected-mode yes +# The server uses default hardened security configuration directives to reduce the +# attack surface on innocent users. Therefore, several sensitive configuration +# directives are immutable, and some potentially-dangerous commands are blocked. +# +# Configuration directives that control files that the server writes to (e.g., 'dir' +# and 'dbfilename') and that aren't usually modified during runtime +# are protected by making them immutable. +# +# Commands that can increase the attack surface of the server and that aren't usually +# called by users are blocked by default. +# +# These can be exposed to either all connections or just local ones by setting +# each of the configs listed below to either of these values: +# +# no - Block for any connection (remain immutable) +# yes - Allow for any connection (no protection) +# local - Allow only for local connections. Ones originating from the +# IPv4 address (127.0.0.1), IPv6 address (::1) or Unix domain sockets. +# +# enable-protected-configs no +# enable-debug-command no +# enable-module-command no + # Accept connections on the specified port, default is 6379 (IANA #815344). -# If port 0 is specified Redis will not listen on a TCP socket. +# If port 0 is specified the server will not listen on a TCP socket. port 0 # TCP listen() backlog. # -# In high requests-per-second environments you need an high backlog in order -# to avoid slow clients connections issues. Note that the Linux kernel +# In high requests-per-second environments you need a high backlog in order +# to avoid slow clients connection issues. Note that the Linux kernel # will silently truncate it to the value of /proc/sys/net/core/somaxconn so # make sure to raise both the value of somaxconn and tcp_max_syn_backlog # in order to get the desired effect. @@ -103,7 +149,7 @@ tcp-backlog 511 # Unix socket. # # Specify the path for the Unix socket that will be used to listen for -# incoming connections. There is no default, so Redis will not listen +# incoming connections. There is no default, so the server will not listen # on a unix socket when not specified. # unixsocket prepare.sock @@ -118,44 +164,178 @@ timeout 0 # of communication. This is useful for two reasons: # # 1) Detect dead peers. -# 2) Take the connection alive from the point of view of network -# equipment in the middle. +# 2) Force network equipment in the middle to consider the connection to be +# alive. # # On Linux, the specified value (in seconds) is the period used to send ACKs. # Note that to close the connection the double of the time is needed. # On other kernels the period depends on the kernel configuration. -# -# A reasonable value for this option is 300 seconds, which is the new -# Redis default starting with Redis 3.2.1. tcp-keepalive 300 +# Apply OS-specific mechanism to mark the listening socket with the specified +# ID, to support advanced routing and filtering capabilities. +# +# On Linux, the ID represents a connection mark. +# On FreeBSD, the ID represents a socket cookie ID. +# On OpenBSD, the ID represents a route table ID. +# +# The default value is 0, which implies no marking is required. +# socket-mark-id 0 + +################################# TLS/SSL ##################################### + +# By default, TLS/SSL is disabled. To enable it, the "tls-port" configuration +# directive can be used to define TLS-listening ports. To enable TLS on the +# default port, use: +# +# port 0 +# tls-port 6379 + +# Configure a X.509 certificate and private key to use for authenticating the +# server to connected clients, masters or cluster peers. These files should be +# PEM formatted. +# +# tls-cert-file valkey.crt +# tls-key-file valkey.key +# +# If the key file is encrypted using a passphrase, it can be included here +# as well. +# +# tls-key-file-pass secret + +# Normally the server uses the same certificate for both server functions (accepting +# connections) and client functions (replicating from a master, establishing +# cluster bus connections, etc.). +# +# Sometimes certificates are issued with attributes that designate them as +# client-only or server-only certificates. In that case it may be desired to use +# different certificates for incoming (server) and outgoing (client) +# connections. To do that, use the following directives: +# +# tls-client-cert-file client.crt +# tls-client-key-file client.key +# +# If the key file is encrypted using a passphrase, it can be included here +# as well. +# +# tls-client-key-file-pass secret + +# Configure a DH parameters file to enable Diffie-Hellman (DH) key exchange, +# required by older versions of OpenSSL (<3.0). Newer versions do not require +# this configuration and recommend against it. +# +# tls-dh-params-file valkey.dh + +# Configure a CA certificate(s) bundle or directory to authenticate TLS/SSL +# clients and peers. The server requires an explicit configuration of at least one +# of these, and will not implicitly use the system wide configuration. +# +# tls-ca-cert-file ca.crt +# tls-ca-cert-dir /etc/ssl/certs + +# By default, clients (including replica servers) on a TLS port are required +# to authenticate using valid client side certificates. +# +# If "no" is specified, client certificates are not required and not accepted. +# If "optional" is specified, client certificates are accepted and must be +# valid if provided, but are not required. +# +# tls-auth-clients no +# tls-auth-clients optional + +# By default, a replica does not attempt to establish a TLS connection +# with its master. +# +# Use the following directive to enable TLS on replication links. +# +# tls-replication yes + +# By default, the cluster bus uses a plain TCP connection. To enable +# TLS for the bus protocol, use the following directive: +# +# tls-cluster yes + +# By default, only TLSv1.2 and TLSv1.3 are enabled and it is highly recommended +# that older formally deprecated versions are kept disabled to reduce the attack surface. +# You can explicitly specify TLS versions to support. +# Allowed values are case insensitive and include "TLSv1", "TLSv1.1", "TLSv1.2", +# "TLSv1.3" (OpenSSL >= 1.1.1) or any combination. +# To enable only TLSv1.2 and TLSv1.3, use: +# +# tls-protocols "TLSv1.2 TLSv1.3" + +# Configure allowed ciphers. See the ciphers(1ssl) manpage for more information +# about the syntax of this string. +# +# Note: this configuration applies only to <= TLSv1.2. +# +# tls-ciphers DEFAULT:!MEDIUM + +# Configure allowed TLSv1.3 ciphersuites. See the ciphers(1ssl) manpage for more +# information about the syntax of this string, and specifically for TLSv1.3 +# ciphersuites. +# +# tls-ciphersuites TLS_CHACHA20_POLY1305_SHA256 + +# When choosing a cipher, use the server's preference instead of the client +# preference. By default, the server follows the client's preference. +# +# tls-prefer-server-ciphers yes + +# By default, TLS session caching is enabled to allow faster and less expensive +# reconnections by clients that support it. Use the following directive to disable +# caching. +# +# tls-session-caching no + +# Change the default number of TLS sessions cached. A zero value sets the cache +# to unlimited size. The default size is 20480. +# +# tls-session-cache-size 5000 + +# Change the default timeout of cached TLS sessions. The default timeout is 300 +# seconds. +# +# tls-session-cache-timeout 60 + ################################# GENERAL ##################################### -# By default Redis does not run as a daemon. Use 'yes' if you need it. -# Note that Redis will write a pid file in /var/run/redis.pid when daemonized. +# By default the server does not run as a daemon. Use 'yes' if you need it. +# Note that the server will write a pid file in /var/run/valkey.pid when daemonized. +# When the server is supervised by upstart or systemd, this parameter has no impact. daemonize yes -# If you run Redis from upstart or systemd, Redis can interact with your +# If you run the server from upstart or systemd, the server can interact with your # supervision tree. Options: # supervised no - no supervision interaction -# supervised upstart - signal upstart by putting Redis into SIGSTOP mode +# supervised upstart - signal upstart by putting the server into SIGSTOP mode +# requires "expect stop" in your upstart job config # supervised systemd - signal systemd by writing READY=1 to $NOTIFY_SOCKET +# on startup, and updating the server status on a regular +# basis. # supervised auto - detect upstart or systemd method based on # UPSTART_JOB or NOTIFY_SOCKET environment variables # Note: these supervision methods only signal "process is ready." -# They do not enable continuous liveness pings back to your supervisor. -supervised no +# They do not enable continuous pings back to your supervisor. +# +# The default is "no". To run under upstart/systemd, you can simply uncomment +# the line below: +# +# supervised auto -# If a pid file is specified, Redis writes it where specified at startup +# If a pid file is specified, the server writes it where specified at startup # and removes it at exit. # # When the server runs non daemonized, no pid file is created if none is # specified in the configuration. When the server is daemonized, the pid file # is used even if not specified, defaulting to "/var/run/redis.pid". # -# Creating a pid file is best effort: if Redis is not able to create it +# Creating a pid file is best effort: if the server is not able to create it # nothing bad happens, the server will start and run normally. -# pidfile /var/run/redis_6379.pid +# +# Note that on modern Linux systems "/run/valkey.pid" is more conforming +# and should be used instead. +pidfile prepare.pid # Specify the server verbosity level. # This can be one of: @@ -163,12 +343,13 @@ supervised no # verbose (many rarely useful info, but not a mess like the debug level) # notice (moderately verbose, what you want in production probably) # warning (only very important / critical messages are logged) +# nothing (nothing is logged) loglevel notice # Specify the log file name. Also the empty string can be used to force -# Redis to log on the standard output. Note that if you use standard +# the server to log on the standard output. Note that if you use standard # output for logging but daemonize, logs will be sent to /dev/null -logfile "prepare.log" +logfile "" # To enable logging to the system logger, just set 'syslog-enabled' to yes, # and optionally update the other syslog parameters to suit your needs. @@ -180,62 +361,97 @@ logfile "prepare.log" # Specify the syslog facility. Must be USER or between LOCAL0-LOCAL7. # syslog-facility local0 +# To disable the built in crash log, which will possibly produce cleaner core +# dumps when they are needed, uncomment the following: +# +# crash-log-enabled no + +# To disable the fast memory check that's run as part of the crash log, which +# will possibly let the server terminate sooner, uncomment the following: +# +# crash-memcheck-enabled no + # Set the number of databases. The default database is DB 0, you can select # a different one on a per-connection basis using SELECT where # dbid is a number between 0 and 'databases'-1 databases 16 -# By default Redis shows an ASCII art logo only when started to log to the -# standard output and if the standard output is a TTY. Basically this means -# that normally a logo is displayed only in interactive sessions. +# By default the server shows an ASCII art logo only when started to log to the +# standard output and if the standard output is a TTY and syslog logging is +# disabled. Basically this means that normally a logo is displayed only in +# interactive sessions. # # However it is possible to force the pre-4.0 behavior and always show a # ASCII art logo in startup logs by setting the following option to yes. -always-show-logo yes +always-show-logo no + +# By default, the server modifies the process title (as seen in 'top' and 'ps') to +# provide some runtime information. It is possible to disable this and leave +# the process name as executed by setting the following to no. +set-proc-title yes + +# When changing the process title, the server uses the following template to construct +# the modified title. +# +# Template variables are specified in curly brackets. The following variables are +# supported: +# +# {title} Name of process as executed if parent, or type of child process. +# {listen-addr} Bind address or '*' followed by TCP or TLS port listening on, or +# Unix socket if only that's available. +# {server-mode} Special mode, i.e. "[sentinel]" or "[cluster]". +# {port} TCP port listening on, or 0. +# {tls-port} TLS port listening on, or 0. +# {unixsocket} Unix domain socket listening on, or "". +# {config-file} Name of configuration file used. +# +proc-title-template "{title} {listen-addr} {server-mode}" + +# Set the local environment which is used for string comparison operations, and +# also affect the performance of Lua scripts. Empty String indicates the locale +# is derived from the environment variables. +locale-collate "" ################################ SNAPSHOTTING ################################ -# -# Save the DB on disk: -# -# save -# -# Will save the DB if both the given number of seconds and the given -# number of write operations against the DB occurred. -# -# In the example below the behaviour will be to save: -# after 900 sec (15 min) if at least 1 key changed -# after 300 sec (5 min) if at least 10 keys changed -# after 60 sec if at least 10000 keys changed -# -# Note: you can disable saving completely by commenting out all "save" lines. -# -# It is also possible to remove all the previously configured save -# points by adding a save directive with a single empty string argument -# like in the following example: -# -# save "" -#save 900 1 -#save 300 10 -save 600 10000 +# Save the DB to disk. +# +# save [ ...] +# +# The server will save the DB if the given number of seconds elapsed and it +# surpassed the given number of write operations against the DB. +# +# Snapshotting can be completely disabled with a single empty string argument +# as in following example: +# +# save "" +# +# Unless specified otherwise, by default the server will save the DB: +# * After 3600 seconds (an hour) if at least 1 change was performed +# * After 300 seconds (5 minutes) if at least 100 changes were performed +# * After 60 seconds if at least 10000 changes were performed +# +# You can set these explicitly by uncommenting the following line. +# +save 3600 1 -# By default Redis will stop accepting writes if RDB snapshots are enabled +# By default the server will stop accepting writes if RDB snapshots are enabled # (at least one save point) and the latest background save failed. # This will make the user aware (in a hard way) that data is not persisting # on disk properly, otherwise chances are that no one will notice and some # disaster will happen. # -# If the background saving process will start working again Redis will +# If the background saving process will start working again, the server will # automatically allow writes again. # -# However if you have setup your proper monitoring of the Redis server -# and persistence, you may want to disable this feature so that Redis will +# However if you have setup your proper monitoring of the server +# and persistence, you may want to disable this feature so that the server will # continue to work as usual even if there are problems with disk, # permissions, and so forth. stop-writes-on-bgsave-error yes # Compress string objects using LZF when dump .rdb databases? -# For default that's set to 'yes' as it's almost always a win. +# By default compression is enabled as it's almost always a win. # If you want to save some CPU in the saving child set it to 'no' but # the dataset will likely be bigger if you have compressible values or keys. rdbcompression yes @@ -249,8 +465,36 @@ rdbcompression yes # tell the loading code to skip the check. rdbchecksum yes +# Enables or disables full sanitization checks for ziplist and listpack etc when +# loading an RDB or RESTORE payload. This reduces the chances of a assertion or +# crash later on while processing commands. +# Options: +# no - Never perform full sanitization +# yes - Always perform full sanitization +# clients - Perform full sanitization only for user connections. +# Excludes: RDB files, RESTORE commands received from the master +# connection, and client connections which have the +# skip-sanitize-payload ACL flag. +# The default should be 'clients' but since it currently affects cluster +# resharding via MIGRATE, it is temporarily set to 'no' by default. +# +# sanitize-dump-payload no + # The filename where to dump the DB -dbfilename prepare.rdb +dbfilename dump.rdb + +# Remove RDB files used by replication in instances without persistence +# enabled. By default this option is disabled, however there are environments +# where for regulations or other security concerns, RDB files persisted on +# disk by masters in order to feed replicas, or stored on disk by replicas +# in order to load them for the initial synchronization, should be deleted +# ASAP. Note that this option ONLY WORKS in instances that have both AOF +# and RDB persistence disabled, otherwise is completely ignored. +# +# An alternative (and sometimes better) way to obtain the same effect is +# to use diskless replication on both master and replicas instances. However +# in the case of replicas, diskless is not always an option. +rdb-del-sync-files no # The working directory. # @@ -264,242 +508,550 @@ dir ./ ################################# REPLICATION ################################# -# Master-Slave replication. Use slaveof to make a Redis instance a copy of -# another Redis server. A few things to understand ASAP about Redis replication. +# Master-Replica replication. Use replicaof to make a server a copy of +# another server. A few things to understand ASAP about replication. # -# 1) Redis replication is asynchronous, but you can configure a master to +# +------------------+ +---------------+ +# | Master | ---> | Replica | +# | (receive writes) | | (exact copy) | +# +------------------+ +---------------+ +# +# 1) Replication is asynchronous, but you can configure a master to # stop accepting writes if it appears to be not connected with at least -# a given number of slaves. -# 2) Redis slaves are able to perform a partial resynchronization with the +# a given number of replicas. +# 2) Replicas are able to perform a partial resynchronization with the # master if the replication link is lost for a relatively small amount of # time. You may want to configure the replication backlog size (see the next # sections of this file) with a sensible value depending on your needs. # 3) Replication is automatic and does not need user intervention. After a -# network partition slaves automatically try to reconnect to masters +# network partition replicas automatically try to reconnect to masters # and resynchronize with them. # -# slaveof +# replicaof # If the master is password protected (using the "requirepass" configuration -# directive below) it is possible to tell the slave to authenticate before +# directive below) it is possible to tell the replica to authenticate before # starting the replication synchronization process, otherwise the master will -# refuse the slave request. +# refuse the replica request. # # masterauth - -# When a slave loses its connection with the master, or when the replication -# is still in progress, the slave can act in two different ways: # -# 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will +# However this is not enough if you are using ACLs +# and the default user is not capable of running the PSYNC +# command and/or other commands needed for replication. In this case it's +# better to configure a special user to use with replication, and specify the +# masteruser configuration as such: +# +# masteruser +# +# When masteruser is specified, the replica will authenticate against its +# master using the new AUTH form: AUTH . + +# When a replica loses its connection with the master, or when the replication +# is still in progress, the replica can act in two different ways: +# +# 1) if replica-serve-stale-data is set to 'yes' (the default) the replica will # still reply to client requests, possibly with out of date data, or the # data set may just be empty if this is the first synchronization. # -# 2) if slave-serve-stale-data is set to 'no' the slave will reply with -# an error "SYNC with master in progress" to all the kind of commands -# but to INFO and SLAVEOF. +# 2) If replica-serve-stale-data is set to 'no' the replica will reply with error +# "MASTERDOWN Link with MASTER is down and replica-serve-stale-data is set to 'no'" +# to all data access commands, excluding commands such as: +# INFO, REPLICAOF, AUTH, SHUTDOWN, REPLCONF, ROLE, CONFIG, SUBSCRIBE, +# UNSUBSCRIBE, PSUBSCRIBE, PUNSUBSCRIBE, PUBLISH, PUBSUB, COMMAND, POST, +# HOST and LATENCY. # -slave-serve-stale-data yes +replica-serve-stale-data yes -# You can configure a slave instance to accept writes or not. Writing against -# a slave instance may be useful to store some ephemeral data (because data -# written on a slave will be easily deleted after resync with the master) but +# You can configure a replica instance to accept writes or not. Writing against +# a replica instance may be useful to store some ephemeral data (because data +# written on a replica will be easily deleted after resync with the master) but # may also cause problems if clients are writing to it because of a # misconfiguration. # -# Since Redis 2.6 by default slaves are read-only. +# By default, replicas are read-only. # -# Note: read only slaves are not designed to be exposed to untrusted clients +# Note: read only replicas are not designed to be exposed to untrusted clients # on the internet. It's just a protection layer against misuse of the instance. -# Still a read only slave exports by default all the administrative commands +# Still a read only replica exports by default all the administrative commands # such as CONFIG, DEBUG, and so forth. To a limited extent you can improve -# security of read only slaves using 'rename-command' to shadow all the +# security of read only replicas using 'rename-command' to shadow all the # administrative / dangerous commands. -slave-read-only yes +replica-read-only yes # Replication SYNC strategy: disk or socket. # -# ------------------------------------------------------- -# WARNING: DISKLESS REPLICATION IS EXPERIMENTAL CURRENTLY -# ------------------------------------------------------- +# New replicas and reconnecting replicas that are not able to continue the +# replication process just receiving differences, need to do what is called a +# "full synchronization". An RDB file is transmitted from the master to the +# replicas. # -# New slaves and reconnecting slaves that are not able to continue the replication -# process just receiving differences, need to do what is called a "full -# synchronization". An RDB file is transmitted from the master to the slaves. # The transmission can happen in two different ways: # -# 1) Disk-backed: The Redis master creates a new process that writes the RDB +# 1) Disk-backed: The master creates a new process that writes the RDB # file on disk. Later the file is transferred by the parent -# process to the slaves incrementally. -# 2) Diskless: The Redis master creates a new process that directly writes the -# RDB file to slave sockets, without touching the disk at all. +# process to the replicas incrementally. +# 2) Diskless: The master creates a new process that directly writes the +# RDB file to replica sockets, without touching the disk at all. # -# With disk-backed replication, while the RDB file is generated, more slaves -# can be queued and served with the RDB file as soon as the current child producing -# the RDB file finishes its work. With diskless replication instead once -# the transfer starts, new slaves arriving will be queued and a new transfer -# will start when the current one terminates. +# With disk-backed replication, while the RDB file is generated, more replicas +# can be queued and served with the RDB file as soon as the current child +# producing the RDB file finishes its work. With diskless replication instead +# once the transfer starts, new replicas arriving will be queued and a new +# transfer will start when the current one terminates. # # When diskless replication is used, the master waits a configurable amount of -# time (in seconds) before starting the transfer in the hope that multiple slaves -# will arrive and the transfer can be parallelized. +# time (in seconds) before starting the transfer in the hope that multiple +# replicas will arrive and the transfer can be parallelized. # # With slow disks and fast (large bandwidth) networks, diskless replication # works better. -repl-diskless-sync no +repl-diskless-sync yes # When diskless replication is enabled, it is possible to configure the delay # the server waits in order to spawn the child that transfers the RDB via socket -# to the slaves. +# to the replicas. # # This is important since once the transfer starts, it is not possible to serve -# new slaves arriving, that will be queued for the next RDB transfer, so the server -# waits a delay in order to let more slaves arrive. +# new replicas arriving, that will be queued for the next RDB transfer, so the +# server waits a delay in order to let more replicas arrive. # # The delay is specified in seconds, and by default is 5 seconds. To disable # it entirely just set it to 0 seconds and the transfer will start ASAP. repl-diskless-sync-delay 5 -# Slaves send PINGs to server in a predefined interval. It's possible to change -# this interval with the repl_ping_slave_period option. The default value is 10 -# seconds. +# When diskless replication is enabled with a delay, it is possible to let +# the replication start before the maximum delay is reached if the maximum +# number of replicas expected have connected. Default of 0 means that the +# maximum is not defined and the server will wait the full delay. +repl-diskless-sync-max-replicas 0 + +# ----------------------------------------------------------------------------- +# WARNING: Since in this setup the replica does not immediately store an RDB on +# disk, it may cause data loss during failovers. RDB diskless load + server +# modules not handling I/O reads may cause the server to abort in case of I/O errors +# during the initial synchronization stage with the master. +# ----------------------------------------------------------------------------- # -# repl-ping-slave-period 10 +# Replica can load the RDB it reads from the replication link directly from the +# socket, or store the RDB to a file and read that file after it was completely +# received from the master. +# +# In many cases the disk is slower than the network, and storing and loading +# the RDB file may increase replication time (and even increase the master's +# Copy on Write memory and replica buffers). +# However, when parsing the RDB file directly from the socket, in order to avoid +# data loss it's only safe to flush the current dataset when the new dataset is +# fully loaded in memory, resulting in higher memory usage. +# For this reason we have the following options: +# +# "disabled" - Don't use diskless load (store the rdb file to the disk first) +# "swapdb" - Keep current db contents in RAM while parsing the data directly +# from the socket. Replicas in this mode can keep serving current +# dataset while replication is in progress, except for cases where +# they can't recognize master as having a data set from same +# replication history. +# Note that this requires sufficient memory, if you don't have it, +# you risk an OOM kill. +# "on-empty-db" - Use diskless load only when current dataset is empty. This is +# safer and avoid having old and new dataset loaded side by side +# during replication. +repl-diskless-load disabled + +# Master send PINGs to its replicas in a predefined interval. It's possible to +# change this interval with the repl_ping_replica_period option. The default +# value is 10 seconds. +# +# repl-ping-replica-period 10 # The following option sets the replication timeout for: # -# 1) Bulk transfer I/O during SYNC, from the point of view of slave. -# 2) Master timeout from the point of view of slaves (data, pings). -# 3) Slave timeout from the point of view of masters (REPLCONF ACK pings). +# 1) Bulk transfer I/O during SYNC, from the point of view of replica. +# 2) Master timeout from the point of view of replicas (data, pings). +# 3) Replica timeout from the point of view of masters (REPLCONF ACK pings). # # It is important to make sure that this value is greater than the value -# specified for repl-ping-slave-period otherwise a timeout will be detected -# every time there is low traffic between the master and the slave. +# specified for repl-ping-replica-period otherwise a timeout will be detected +# every time there is low traffic between the master and the replica. The default +# value is 60 seconds. # # repl-timeout 60 -# Disable TCP_NODELAY on the slave socket after SYNC? +# Disable TCP_NODELAY on the replica socket after SYNC? # -# If you select "yes" Redis will use a smaller number of TCP packets and -# less bandwidth to send data to slaves. But this can add a delay for -# the data to appear on the slave side, up to 40 milliseconds with +# If you select "yes", the server will use a smaller number of TCP packets and +# less bandwidth to send data to replicas. But this can add a delay for +# the data to appear on the replica side, up to 40 milliseconds with # Linux kernels using a default configuration. # -# If you select "no" the delay for data to appear on the slave side will +# If you select "no" the delay for data to appear on the replica side will # be reduced but more bandwidth will be used for replication. # # By default we optimize for low latency, but in very high traffic conditions -# or when the master and slaves are many hops away, turning this to "yes" may +# or when the master and replicas are many hops away, turning this to "yes" may # be a good idea. repl-disable-tcp-nodelay no # Set the replication backlog size. The backlog is a buffer that accumulates -# slave data when slaves are disconnected for some time, so that when a slave -# wants to reconnect again, often a full resync is not needed, but a partial -# resync is enough, just passing the portion of data the slave missed while -# disconnected. +# replica data when replicas are disconnected for some time, so that when a +# replica wants to reconnect again, often a full resync is not needed, but a +# partial resync is enough, just passing the portion of data the replica +# missed while disconnected. # -# The bigger the replication backlog, the longer the time the slave can be -# disconnected and later be able to perform a partial resynchronization. +# The bigger the replication backlog, the longer the replica can endure the +# disconnect and later be able to perform a partial resynchronization. # -# The backlog is only allocated once there is at least a slave connected. +# The backlog is only allocated if there is at least one replica connected. # # repl-backlog-size 1mb -# After a master has no longer connected slaves for some time, the backlog -# will be freed. The following option configures the amount of seconds that -# need to elapse, starting from the time the last slave disconnected, for -# the backlog buffer to be freed. +# After a master has no connected replicas for some time, the backlog will be +# freed. The following option configures the amount of seconds that need to +# elapse, starting from the time the last replica disconnected, for the backlog +# buffer to be freed. # -# Note that slaves never free the backlog for timeout, since they may be +# Note that replicas never free the backlog for timeout, since they may be # promoted to masters later, and should be able to correctly "partially -# resynchronize" with the slaves: hence they should always accumulate backlog. +# resynchronize" with other replicas: hence they should always accumulate backlog. # # A value of 0 means to never release the backlog. # # repl-backlog-ttl 3600 -# The slave priority is an integer number published by Redis in the INFO output. -# It is used by Redis Sentinel in order to select a slave to promote into a -# master if the master is no longer working correctly. +# The replica priority is an integer number published by the server in the INFO +# output. It is used by Sentinel in order to select a replica to promote +# into a master if the master is no longer working correctly. # -# A slave with a low priority number is considered better for promotion, so -# for instance if there are three slaves with priority 10, 100, 25 Sentinel will -# pick the one with priority 10, that is the lowest. +# A replica with a low priority number is considered better for promotion, so +# for instance if there are three replicas with priority 10, 100, 25 Sentinel +# will pick the one with priority 10, that is the lowest. # -# However a special priority of 0 marks the slave as not able to perform the -# role of master, so a slave with priority of 0 will never be selected by -# Redis Sentinel for promotion. +# However a special priority of 0 marks the replica as not able to perform the +# role of master, so a replica with priority of 0 will never be selected by +# Sentinel for promotion. # # By default the priority is 100. -slave-priority 100 +replica-priority 100 + +# The propagation error behavior controls how the server will behave when it is +# unable to handle a command being processed in the replication stream from a master +# or processed while reading from an AOF file. Errors that occur during propagation +# are unexpected, and can cause data inconsistency. +# +# If an application wants to ensure there is no data divergence, this configuration +# should be set to 'panic' instead. The value can also be set to 'panic-on-replicas' +# to only panic when a replica encounters an error on the replication stream. One of +# these two panic values will become the default value in the future once there are +# sufficient safety mechanisms in place to prevent false positive crashes. +# +# propagation-error-behavior ignore + +# Replica ignore disk write errors controls the behavior of a replica when it is +# unable to persist a write command received from its master to disk. By default, +# this configuration is set to 'no' and will crash the replica in this condition. +# It is not recommended to change this default. +# +# replica-ignore-disk-write-errors no + +# ----------------------------------------------------------------------------- +# By default, Sentinel includes all replicas in its reports. A replica +# can be excluded from Sentinel's announcements. An unannounced replica +# will be ignored by the 'sentinel replicas ' command and won't be +# exposed to Sentinel's clients. +# +# This option does not change the behavior of replica-priority. Even with +# replica-announced set to 'no', the replica can be promoted to master. To +# prevent this behavior, set replica-priority to 0. +# +# replica-announced yes # It is possible for a master to stop accepting writes if there are less than -# N slaves connected, having a lag less or equal than M seconds. +# N replicas connected, having a lag less or equal than M seconds. # -# The N slaves need to be in "online" state. +# The N replicas need to be in "online" state. # # The lag in seconds, that must be <= the specified value, is calculated from -# the last ping received from the slave, that is usually sent every second. +# the last ping received from the replica, that is usually sent every second. # # This option does not GUARANTEE that N replicas will accept the write, but -# will limit the window of exposure for lost writes in case not enough slaves +# will limit the window of exposure for lost writes in case not enough replicas # are available, to the specified number of seconds. # -# For example to require at least 3 slaves with a lag <= 10 seconds use: +# For example to require at least 3 replicas with a lag <= 10 seconds use: # -# min-slaves-to-write 3 -# min-slaves-max-lag 10 +# min-replicas-to-write 3 +# min-replicas-max-lag 10 # # Setting one or the other to 0 disables the feature. # -# By default min-slaves-to-write is set to 0 (feature disabled) and -# min-slaves-max-lag is set to 10. +# By default min-replicas-to-write is set to 0 (feature disabled) and +# min-replicas-max-lag is set to 10. -# A Redis master is able to list the address and port of the attached -# slaves in different ways. For example the "INFO replication" section +# A master is able to list the address and port of the attached +# replicas in different ways. For example the "INFO replication" section # offers this information, which is used, among other tools, by -# Redis Sentinel in order to discover slave instances. +# Sentinel in order to discover replica instances. # Another place where this info is available is in the output of the # "ROLE" command of a master. # -# The listed IP and address normally reported by a slave is obtained -# in the following way: +# The listed IP address and port normally reported by a replica is +# obtained in the following way: # # IP: The address is auto detected by checking the peer address -# of the socket used by the slave to connect with the master. +# of the socket used by the replica to connect with the master. # -# Port: The port is communicated by the slave during the replication -# handshake, and is normally the port that the slave is using to -# list for connections. +# Port: The port is communicated by the replica during the replication +# handshake, and is normally the port that the replica is using to +# listen for connections. # # However when port forwarding or Network Address Translation (NAT) is -# used, the slave may be actually reachable via different IP and port -# pairs. The following two options can be used by a slave in order to +# used, the replica may actually be reachable via different IP and port +# pairs. The following two options can be used by a replica in order to # report to its master a specific set of IP and port, so that both INFO # and ROLE will report those values. # # There is no need to use both the options if you need to override just # the port or the IP address. # -# slave-announce-ip 5.5.5.5 -# slave-announce-port 1234 +# replica-announce-ip 5.5.5.5 +# replica-announce-port 1234 + +############################### KEYS TRACKING ################################# + +# The client side caching of values is assisted via server-side support. +# This is implemented using an invalidation table that remembers, using +# a radix key indexed by key name, what clients have which keys. In turn +# this is used in order to send invalidation messages to clients. Please +# check this page to understand more about the feature: +# +# https://valkey.io/topics/client-side-caching +# +# When tracking is enabled for a client, all the read only queries are assumed +# to be cached: this will force the server to store information in the invalidation +# table. When keys are modified, such information is flushed away, and +# invalidation messages are sent to the clients. However if the workload is +# heavily dominated by reads, the server could use more and more memory in order +# to track the keys fetched by many clients. +# +# For this reason it is possible to configure a maximum fill value for the +# invalidation table. By default it is set to 1M of keys, and once this limit +# is reached, the server will start to evict keys in the invalidation table +# even if they were not modified, just to reclaim memory: this will in turn +# force the clients to invalidate the cached values. Basically the table +# maximum size is a trade off between the memory you want to spend server +# side to track information about who cached what, and the ability of clients +# to retain cached objects in memory. +# +# If you set the value to 0, it means there are no limits, and the server will +# retain as many keys as needed in the invalidation table. +# In the "stats" INFO section, you can find information about the number of +# keys in the invalidation table at every given moment. +# +# Note: when key tracking is used in broadcasting mode, no memory is used +# in the server side so this setting is useless. +# +# tracking-table-max-keys 1000000 ################################## SECURITY ################################### -# Require clients to issue AUTH before processing any other -# commands. This might be useful in environments in which you do not trust -# others with access to the host running redis-server. +# Warning: since the server is pretty fast, an outside user can try up to +# 1 million passwords per second against a modern box. This means that you +# should use very strong passwords, otherwise they will be very easy to break. +# Note that because the password is really a shared secret between the client +# and the server, and should not be memorized by any human, the password +# can be easily a long string from /dev/urandom or whatever, so by using a +# long and unguessable password no brute force attack will be possible. + +# ACL users are defined in the following format: # -# This should stay commented out for backward compatibility and because most -# people do not need auth (e.g. they run their own servers). +# user ... acl rules ... # -# Warning: since Redis is pretty fast an outside user can try up to -# 150k passwords per second against a good box. This means that you should -# use a very strong password otherwise it will be very easy to break. +# For example: +# +# user worker +@list +@connection ~jobs:* on >ffa9203c493aa99 +# +# The special username "default" is used for new connections. If this user +# has the "nopass" rule, then new connections will be immediately authenticated +# as the "default" user without the need of any password provided via the +# AUTH command. Otherwise if the "default" user is not flagged with "nopass" +# the connections will start in not authenticated state, and will require +# AUTH (or the HELLO command AUTH option) in order to be authenticated and +# start to work. +# +# The ACL rules that describe what a user can do are the following: +# +# on Enable the user: it is possible to authenticate as this user. +# off Disable the user: it's no longer possible to authenticate +# with this user, however the already authenticated connections +# will still work. +# skip-sanitize-payload RESTORE dump-payload sanitization is skipped. +# sanitize-payload RESTORE dump-payload is sanitized (default). +# + Allow the execution of that command. +# May be used with `|` for allowing subcommands (e.g "+config|get") +# - Disallow the execution of that command. +# May be used with `|` for blocking subcommands (e.g "-config|set") +# +@ Allow the execution of all the commands in such category +# with valid categories are like @admin, @set, @sortedset, ... +# and so forth, see the full list in the server.c file where +# the server command table is described and defined. +# The special category @all means all the commands, but currently +# present in the server, and that will be loaded in the future +# via modules. +# +|first-arg Allow a specific first argument of an otherwise +# disabled command. It is only supported on commands with +# no sub-commands, and is not allowed as negative form +# like -SELECT|1, only additive starting with "+". This +# feature is deprecated and may be removed in the future. +# allcommands Alias for +@all. Note that it implies the ability to execute +# all the future commands loaded via the modules system. +# nocommands Alias for -@all. +# ~ Add a pattern of keys that can be mentioned as part of +# commands. For instance ~* allows all the keys. The pattern +# is a glob-style pattern like the one of KEYS. +# It is possible to specify multiple patterns. +# %R~ Add key read pattern that specifies which keys can be read +# from. +# %W~ Add key write pattern that specifies which keys can be +# written to. +# allkeys Alias for ~* +# resetkeys Flush the list of allowed keys patterns. +# & Add a glob-style pattern of Pub/Sub channels that can be +# accessed by the user. It is possible to specify multiple channel +# patterns. +# allchannels Alias for &* +# resetchannels Flush the list of allowed channel patterns. +# > Add this password to the list of valid password for the user. +# For example >mypass will add "mypass" to the list. +# This directive clears the "nopass" flag (see later). +# < Remove this password from the list of valid passwords. +# nopass All the set passwords of the user are removed, and the user +# is flagged as requiring no password: it means that every +# password will work against this user. If this directive is +# used for the default user, every new connection will be +# immediately authenticated with the default user without +# any explicit AUTH command required. Note that the "resetpass" +# directive will clear this condition. +# resetpass Flush the list of allowed passwords. Moreover removes the +# "nopass" status. After "resetpass" the user has no associated +# passwords and there is no way to authenticate without adding +# some password (or setting it as "nopass" later). +# reset Performs the following actions: resetpass, resetkeys, resetchannels, +# allchannels (if acl-pubsub-default is set), off, clearselectors, -@all. +# The user returns to the same state it has immediately after its creation. +# () Create a new selector with the options specified within the +# parentheses and attach it to the user. Each option should be +# space separated. The first character must be ( and the last +# character must be ). +# clearselectors Remove all of the currently attached selectors. +# Note this does not change the "root" user permissions, +# which are the permissions directly applied onto the +# user (outside the parentheses). +# +# ACL rules can be specified in any order: for instance you can start with +# passwords, then flags, or key patterns. However note that the additive +# and subtractive rules will CHANGE MEANING depending on the ordering. +# For instance see the following example: +# +# user alice on +@all -DEBUG ~* >somepassword +# +# This will allow "alice" to use all the commands with the exception of the +# DEBUG command, since +@all added all the commands to the set of the commands +# alice can use, and later DEBUG was removed. However if we invert the order +# of two ACL rules the result will be different: +# +# user alice on -DEBUG +@all ~* >somepassword +# +# Now DEBUG was removed when alice had yet no commands in the set of allowed +# commands, later all the commands are added, so the user will be able to +# execute everything. +# +# Basically ACL rules are processed left-to-right. +# +# The following is a list of command categories and their meanings: +# * keyspace - Writing or reading from keys, databases, or their metadata +# in a type agnostic way. Includes DEL, RESTORE, DUMP, RENAME, EXISTS, DBSIZE, +# KEYS, EXPIRE, TTL, FLUSHALL, etc. Commands that may modify the keyspace, +# key or metadata will also have `write` category. Commands that only read +# the keyspace, key or metadata will have the `read` category. +# * read - Reading from keys (values or metadata). Note that commands that don't +# interact with keys, will not have either `read` or `write`. +# * write - Writing to keys (values or metadata) +# * admin - Administrative commands. Normal applications will never need to use +# these. Includes REPLICAOF, CONFIG, DEBUG, SAVE, MONITOR, ACL, SHUTDOWN, etc. +# * dangerous - Potentially dangerous (each should be considered with care for +# various reasons). This includes FLUSHALL, MIGRATE, RESTORE, SORT, KEYS, +# CLIENT, DEBUG, INFO, CONFIG, SAVE, REPLICAOF, etc. +# * connection - Commands affecting the connection or other connections. +# This includes AUTH, SELECT, COMMAND, CLIENT, ECHO, PING, etc. +# * blocking - Potentially blocking the connection until released by another +# command. +# * fast - Fast O(1) commands. May loop on the number of arguments, but not the +# number of elements in the key. +# * slow - All commands that are not Fast. +# * pubsub - PUBLISH / SUBSCRIBE related +# * transaction - WATCH / MULTI / EXEC related commands. +# * scripting - Scripting related. +# * set - Data type: sets related. +# * sortedset - Data type: zsets related. +# * list - Data type: lists related. +# * hash - Data type: hashes related. +# * string - Data type: strings related. +# * bitmap - Data type: bitmaps related. +# * hyperloglog - Data type: hyperloglog related. +# * geo - Data type: geo related. +# * stream - Data type: streams related. +# +# For more information about ACL configuration please refer to +# the Valkey web site at https://valkey.io/topics/acl + +# ACL LOG +# +# The ACL Log tracks failed commands and authentication events associated +# with ACLs. The ACL Log is useful to troubleshoot failed commands blocked +# by ACLs. The ACL Log is stored in memory. You can reclaim memory with +# ACL LOG RESET. Define the maximum entry length of the ACL Log below. +acllog-max-len 128 + +# Using an external ACL file +# +# Instead of configuring users here in this file, it is possible to use +# a stand-alone file just listing users. The two methods cannot be mixed: +# if you configure users here and at the same time you activate the external +# ACL file, the server will refuse to start. +# +# The format of the external ACL user file is exactly the same as the +# format that is used inside valkey.conf to describe users. +# +# aclfile /etc/valkey/users.acl + +# IMPORTANT NOTE: "requirepass" is just a compatibility +# layer on top of the new ACL system. The option effect will be just setting +# the password for the default user. Clients will still authenticate using +# AUTH as usually, or more explicitly with AUTH default +# if they follow the new protocol: both will work. +# +# The requirepass is not compatible with aclfile option and the ACL LOAD +# command, these will cause requirepass to be ignored. # # requirepass foobared -# Command renaming. +# The default Pub/Sub channels permission for new users is controlled by the +# acl-pubsub-default configuration directive, which accepts one of these values: +# +# allchannels: grants access to all Pub/Sub channels +# resetchannels: revokes access to all Pub/Sub channels +# +# acl-pubsub-default defaults to 'resetchannels' permission. +# +# acl-pubsub-default resetchannels + +# Command renaming (DEPRECATED). +# +# ------------------------------------------------------------------------ +# WARNING: avoid using this option if possible. Instead use ACLs to remove +# commands from the default user, and put them only in some admin user you +# create for administrative purposes. +# ------------------------------------------------------------------------ # # It is possible to change the name of dangerous commands in a shared # environment. For instance the CONFIG command may be renamed into something @@ -516,56 +1068,61 @@ slave-priority 100 # rename-command CONFIG "" # # Please note that changing the name of commands that are logged into the -# AOF file or transmitted to slaves may cause problems. +# AOF file or transmitted to replicas may cause problems. ################################### CLIENTS #################################### # Set the max number of connected clients at the same time. By default -# this limit is set to 10000 clients, however if the Redis server is not +# this limit is set to 10000 clients, however if the server is not # able to configure the process file limit to allow for the specified limit # the max number of allowed clients is set to the current file limit -# minus 32 (as Redis reserves a few file descriptors for internal uses). +# minus 32 (as the server reserves a few file descriptors for internal uses). # -# Once the limit is reached Redis will close all the new connections sending +# Once the limit is reached the server will close all the new connections sending # an error 'max number of clients reached'. # +# IMPORTANT: With a cluster-enabled setup, the max number of connections is also +# shared with the cluster bus: every node in the cluster will use two +# connections, one incoming and another outgoing. It is important to size the +# limit accordingly in case of very large clusters. +# # maxclients 10000 ############################## MEMORY MANAGEMENT ################################ # Set a memory usage limit to the specified amount of bytes. -# When the memory limit is reached Redis will try to remove keys +# When the memory limit is reached the server will try to remove keys # according to the eviction policy selected (see maxmemory-policy). # -# If Redis can't remove keys according to the policy, or if the policy is -# set to 'noeviction', Redis will start to reply with errors to commands +# If the server can't remove keys according to the policy, or if the policy is +# set to 'noeviction', the server will start to reply with errors to commands # that would use more memory, like SET, LPUSH, and so on, and will continue # to reply to read-only commands like GET. # -# This option is usually useful when using Redis as an LRU or LFU cache, or to +# This option is usually useful when using the server as an LRU or LFU cache, or to # set a hard memory limit for an instance (using the 'noeviction' policy). # -# WARNING: If you have slaves attached to an instance with maxmemory on, -# the size of the output buffers needed to feed the slaves are subtracted +# WARNING: If you have replicas attached to an instance with maxmemory on, +# the size of the output buffers needed to feed the replicas are subtracted # from the used memory count, so that network problems / resyncs will # not trigger a loop where keys are evicted, and in turn the output -# buffer of slaves is full with DELs of keys evicted triggering the deletion +# buffer of replicas is full with DELs of keys evicted triggering the deletion # of more keys, and so forth until the database is completely emptied. # -# In short... if you have slaves attached it is suggested that you set a lower -# limit for maxmemory so that there is some free RAM on the system for slave +# In short... if you have replicas attached it is suggested that you set a lower +# limit for maxmemory so that there is some free RAM on the system for replica # output buffers (but this is not needed if the policy is 'noeviction'). # # maxmemory -# MAXMEMORY POLICY: how Redis will select what to remove when maxmemory -# is reached. You can select among five behaviors: +# MAXMEMORY POLICY: how the server will select what to remove when maxmemory +# is reached. You can select one from the following behaviors: # -# volatile-lru -> Evict using approximated LRU among the keys with an expire set. +# volatile-lru -> Evict using approximated LRU, only keys with an expire set. # allkeys-lru -> Evict any key using approximated LRU. -# volatile-lfu -> Evict using approximated LFU among the keys with an expire set. +# volatile-lfu -> Evict using approximated LFU, only keys with an expire set. # allkeys-lfu -> Evict any key using approximated LFU. -# volatile-random -> Remove a random key among the ones with an expire set. +# volatile-random -> Remove a random key having an expire set. # allkeys-random -> Remove a random key, any key. # volatile-ttl -> Remove the key with the nearest expire time (minor TTL) # noeviction -> Don't evict anything, just return an error on write operations. @@ -576,14 +1133,12 @@ slave-priority 100 # Both LRU, LFU and volatile-ttl are implemented using approximated # randomized algorithms. # -# Note: with any of the above policies, Redis will return an error on write -# operations, when there are no suitable keys for eviction. -# -# At the date of writing these commands are: set setnx setex append -# incr decr rpush lpush rpushx lpushx linsert lset rpoplpush sadd -# sinter sinterstore sunion sunionstore sdiff sdiffstore zadd zincrby -# zunionstore zinterstore hset hsetnx hmset hincrby incrby decrby -# getset mset msetnx exec sort +# Note: with any of the above policies, when there are no suitable keys for +# eviction, the server will return an error on write operations that require +# more memory. These are usually commands that create new keys, add data or +# modify existing keys. A few examples are: SET, INCR, HSET, LPUSH, SUNIONSTORE, +# SORT (due to the STORE argument), and EXEC (if the transaction includes any +# command that requires memory). # # The default is: # @@ -591,8 +1146,8 @@ slave-priority 100 # LRU, LFU and minimal TTL algorithms are not precise algorithms but approximated # algorithms (in order to save memory), so you can tune it for speed or -# accuracy. For default Redis will check five keys and pick the one that was -# used less recently, you can change the sample size using the following +# accuracy. By default the server will check five keys and pick the one that was +# used least recently, you can change the sample size using the following # configuration directive. # # The default of 5 produces good enough results. 10 Approximates very closely @@ -600,18 +1155,63 @@ slave-priority 100 # # maxmemory-samples 5 +# Eviction processing is designed to function well with the default setting. +# If there is an unusually large amount of write traffic, this value may need to +# be increased. Decreasing this value may reduce latency at the risk of +# eviction processing effectiveness +# 0 = minimum latency, 10 = default, 100 = process without regard to latency +# +# maxmemory-eviction-tenacity 10 + +# By default a replica will ignore its maxmemory setting +# (unless it is promoted to master after a failover or manually). It means +# that the eviction of keys will be just handled by the master, sending the +# DEL commands to the replica as keys evict in the master side. +# +# This behavior ensures that masters and replicas stay consistent, and is usually +# what you want, however if your replica is writable, or you want the replica +# to have a different memory setting, and you are sure all the writes performed +# to the replica are idempotent, then you may change this default (but be sure +# to understand what you are doing). +# +# Note that since the replica by default does not evict, it may end using more +# memory than the one set via maxmemory (there are certain buffers that may +# be larger on the replica, or data structures may sometimes take more memory +# and so forth). So make sure you monitor your replicas and make sure they +# have enough memory to never hit a real out-of-memory condition before the +# master hits the configured maxmemory setting. +# +# replica-ignore-maxmemory yes + +# The server reclaims expired keys in two ways: upon access when those keys are +# found to be expired, and also in background, in what is called the +# "active expire key". The key space is slowly and interactively scanned +# looking for expired keys to reclaim, so that it is possible to free memory +# of keys that are expired and will never be accessed again in a short time. +# +# The default effort of the expire cycle will try to avoid having more than +# ten percent of expired keys still in memory, and will try to avoid consuming +# more than 25% of total memory and to add latency to the system. However +# it is possible to increase the expire "effort" that is normally set to +# "1", to a greater value, up to the value "10". At its maximum value the +# system will use more CPU, longer cycles (and technically may introduce +# more latency), and will tolerate less already expired keys still present +# in the system. It's a tradeoff between memory, CPU and latency. +# +# active-expire-effort 1 + ############################# LAZY FREEING #################################### -# Redis has two primitives to delete keys. One is called DEL and is a blocking +# The server has two primitives to delete keys. One is called DEL and is a blocking # deletion of the object. It means that the server stops processing new commands # in order to reclaim all the memory associated with an object in a synchronous # way. If the key deleted is associated with a small object, the time needed # in order to execute the DEL command is very small and comparable to most other -# O(1) or O(log_N) commands in Redis. However if the key is associated with an +# O(1) or O(log_N) commands in the server. However if the key is associated with an # aggregated value containing millions of elements, the server can block for # a long time (even seconds) in order to complete the operation. # -# For the above reasons Redis also offers non blocking deletion primitives +# For the above reasons the server also offers non blocking deletion primitives # such as UNLINK (non blocking DEL) and the ASYNC option of FLUSHALL and # FLUSHDB commands, in order to reclaim memory in background. Those commands # are executed in constant time. Another thread will incrementally free the @@ -619,9 +1219,9 @@ slave-priority 100 # # DEL, UNLINK and ASYNC option of FLUSHALL and FLUSHDB are user-controlled. # It's up to the design of the application to understand when it is a good -# idea to use one or the other. However the Redis server sometimes has to +# idea to use one or the other. However the server sometimes has to # delete keys or flush the whole database as a side effect of other operations. -# Specifically Redis deletes objects independently of a user call in the +# Specifically the server deletes objects independently of a user call in the # following scenarios: # # 1) On eviction, because of the maxmemory and maxmemory policy configurations, @@ -635,51 +1235,184 @@ slave-priority 100 # or SORT with STORE option may delete existing keys. The SET command # itself removes any old content of the specified key in order to replace # it with the specified string. -# 4) During replication, when a slave performs a full resynchronization with +# 4) During replication, when a replica performs a full resynchronization with # its master, the content of the whole database is removed in order to -# load the RDB file just transfered. +# load the RDB file just transferred. # # In all the above cases the default is to delete objects in a blocking way, # like if DEL was called. However you can configure each case specifically # in order to instead release memory in a non-blocking way like if UNLINK -# was called, using the following configuration directives: +# was called, using the following configuration directives. lazyfree-lazy-eviction no lazyfree-lazy-expire no lazyfree-lazy-server-del no -slave-lazy-flush no +replica-lazy-flush no + +# It is also possible, for the case when to replace the user code DEL calls +# with UNLINK calls is not easy, to modify the default behavior of the DEL +# command to act exactly like UNLINK, using the following configuration +# directive: + +lazyfree-lazy-user-del no + +# FLUSHDB, FLUSHALL, SCRIPT FLUSH and FUNCTION FLUSH support both asynchronous and synchronous +# deletion, which can be controlled by passing the [SYNC|ASYNC] flags into the +# commands. When neither flag is passed, this directive will be used to determine +# if the data should be deleted asynchronously. + +lazyfree-lazy-user-flush no + +################################ THREADED I/O ################################# + +# The server is mostly single threaded, however there are certain threaded +# operations such as UNLINK, slow I/O accesses and other things that are +# performed on side threads. +# +# Now it is also possible to handle the server clients socket reads and writes +# in different I/O threads. Since especially writing is so slow, normally +# users use pipelining in order to speed up the server performances per +# core, and spawn multiple instances in order to scale more. Using I/O +# threads it is possible to easily speedup two times the server without resorting +# to pipelining nor sharding of the instance. +# +# By default threading is disabled, we suggest enabling it only in machines +# that have at least 4 or more cores, leaving at least one spare core. +# Using more than 8 threads is unlikely to help much. We also recommend using +# threaded I/O only if you actually have performance problems, with +# instances being able to use a quite big percentage of CPU time, otherwise +# there is no point in using this feature. +# +# So for instance if you have a four cores boxes, try to use 2 or 3 I/O +# threads, if you have a 8 cores, try to use 6 threads. In order to +# enable I/O threads use the following configuration directive: +# +# io-threads 4 +# +# Setting io-threads to 1 will just use the main thread as usual. +# When I/O threads are enabled, we only use threads for writes, that is +# to thread the write(2) syscall and transfer the client buffers to the +# socket. However it is also possible to enable threading of reads and +# protocol parsing using the following configuration directive, by setting +# it to yes: +# +# io-threads-do-reads no +# +# Usually threading reads doesn't help much. +# +# NOTE 1: This configuration directive cannot be changed at runtime via +# CONFIG SET. Also, this feature currently does not work when SSL is +# enabled. +# +# NOTE 2: If you want to test the server speedup using valkey-benchmark, make +# sure you also run the benchmark itself in threaded mode, using the +# --threads option to match the number of server threads, otherwise you'll not +# be able to notice the improvements. + +############################ KERNEL OOM CONTROL ############################## + +# On Linux, it is possible to hint the kernel OOM killer on what processes +# should be killed first when out of memory. +# +# Enabling this feature makes the server actively control the oom_score_adj value +# for all its processes, depending on their role. The default scores will +# attempt to have background child processes killed before all others, and +# replicas killed before masters. +# +# The server supports these options: +# +# no: Don't make changes to oom-score-adj (default). +# yes: Alias to "relative" see below. +# absolute: Values in oom-score-adj-values are written as is to the kernel. +# relative: Values are used relative to the initial value of oom_score_adj when +# the server starts and are then clamped to a range of -1000 to 1000. +# Because typically the initial value is 0, they will often match the +# absolute values. +oom-score-adj no + +# When oom-score-adj is used, this directive controls the specific values used +# for master, replica and background child processes. Values range -2000 to +# 2000 (higher means more likely to be killed). +# +# Unprivileged processes (not root, and without CAP_SYS_RESOURCE capabilities) +# can freely increase their value, but not decrease it below its initial +# settings. This means that setting oom-score-adj to "relative" and setting the +# oom-score-adj-values to positive values will always succeed. +oom-score-adj-values 0 200 800 + + +#################### KERNEL transparent hugepage CONTROL ###################### + +# Usually the kernel Transparent Huge Pages control is set to "madvise" or +# or "never" by default (/sys/kernel/mm/transparent_hugepage/enabled), in which +# case this config has no effect. On systems in which it is set to "always", +# the server will attempt to disable it specifically for the server process in order +# to avoid latency problems specifically with fork(2) and CoW. +# If for some reason you prefer to keep it enabled, you can set this config to +# "no" and the kernel global to "always". + +disable-thp yes ############################## APPEND ONLY MODE ############################### -# By default Redis asynchronously dumps the dataset on disk. This mode is -# good enough in many applications, but an issue with the Redis process or +# By default the server asynchronously dumps the dataset on disk. This mode is +# good enough in many applications, but an issue with the server process or # a power outage may result into a few minutes of writes lost (depending on # the configured save points). # # The Append Only File is an alternative persistence mode that provides # much better durability. For instance using the default data fsync policy -# (see later in the config file) Redis can lose just one second of writes in a +# (see later in the config file) the server can lose just one second of writes in a # dramatic event like a server power outage, or a single write if something -# wrong with the Redis process itself happens, but the operating system is +# wrong with the process itself happens, but the operating system is # still running correctly. # # AOF and RDB persistence can be enabled at the same time without problems. -# If the AOF is enabled on startup Redis will load the AOF, that is the file +# If the AOF is enabled on startup the server will load the AOF, that is the file # with the better durability guarantees. # -# Please check http://redis.io/topics/persistence for more information. +# Please check https://valkey.io/topics/persistence for more information. appendonly no -# The name of the append only file (default: "appendonly.aof") +# The base name of the append only file. +# +# The server uses a set of append-only files to persist the dataset +# and changes applied to it. There are two basic types of files in use: +# +# - Base files, which are a snapshot representing the complete state of the +# dataset at the time the file was created. Base files can be either in +# the form of RDB (binary serialized) or AOF (textual commands). +# - Incremental files, which contain additional commands that were applied +# to the dataset following the previous file. +# +# In addition, manifest files are used to track the files and the order in +# which they were created and should be applied. +# +# Append-only file names are created by the server following a specific pattern. +# The file name's prefix is based on the 'appendfilename' configuration +# parameter, followed by additional information about the sequence and type. +# +# For example, if appendfilename is set to appendonly.aof, the following file +# names could be derived: +# +# - appendonly.aof.1.base.rdb as a base file. +# - appendonly.aof.1.incr.aof, appendonly.aof.2.incr.aof as incremental files. +# - appendonly.aof.manifest as a manifest file. appendfilename "appendonly.aof" +# For convenience, the server stores all persistent append-only files in a dedicated +# directory. The name of the directory is determined by the appenddirname +# configuration parameter. + +appenddirname "appendonlydir" + # The fsync() call tells the Operating System to actually write data on disk # instead of waiting for more data in the output buffer. Some OS will really flush # data on disk, some other OS will just try to do it ASAP. # -# Redis supports three different modes: +# The server supports three different modes: # # no: don't fsync, just let the OS flush the data when it wants. Faster. # always: fsync after every write to the append only log. Slow, Safest. @@ -705,7 +1438,7 @@ appendfsync everysec # When the AOF fsync policy is set to always or everysec, and a background # saving process (a background save or AOF log background rewriting) is # performing a lot of I/O against the disk, in some Linux configurations -# Redis may block too long on the fsync() call. Note that there is no fix for +# the server may block too long on the fsync() call. Note that there is no fix for # this currently, as even performing fsync in a different thread will block # our synchronous write(2) call. # @@ -713,8 +1446,8 @@ appendfsync everysec # that will prevent fsync() from being called in the main process while a # BGSAVE or BGREWRITEAOF is in progress. # -# This means that while another child is saving, the durability of Redis is -# the same as "appendfsync none". In practical terms, this means that it is +# This means that while another child is saving, the durability of the server is +# the same as "appendfsync no". In practical terms, this means that it is # possible to lose up to 30 seconds of log in the worst scenario (with the # default Linux settings). # @@ -724,10 +1457,10 @@ appendfsync everysec no-appendfsync-on-rewrite no # Automatic rewrite of the append only file. -# Redis is able to automatically rewrite the log file implicitly calling +# The server is able to automatically rewrite the log file implicitly calling # BGREWRITEAOF when the AOF log size grows by the specified percentage. # -# This is how it works: Redis remembers the size of the AOF file after the +# This is how it works: The server remembers the size of the AOF file after the # latest rewrite (if no rewrite has happened since the restart, the size of # the AOF at startup is used). # @@ -743,79 +1476,105 @@ no-appendfsync-on-rewrite no auto-aof-rewrite-percentage 100 auto-aof-rewrite-min-size 64mb -# An AOF file may be found to be truncated at the end during the Redis +# An AOF file may be found to be truncated at the end during the server # startup process, when the AOF data gets loaded back into memory. -# This may happen when the system where Redis is running +# This may happen when the system where the server is running # crashes, especially when an ext4 filesystem is mounted without the -# data=ordered option (however this can't happen when Redis itself +# data=ordered option (however this can't happen when the server itself # crashes or aborts but the operating system still works correctly). # -# Redis can either exit with an error when this happens, or load as much +# The server can either exit with an error when this happens, or load as much # data as possible (the default now) and start if the AOF file is found # to be truncated at the end. The following option controls this behavior. # # If aof-load-truncated is set to yes, a truncated AOF file is loaded and -# the Redis server starts emitting a log to inform the user of the event. +# the server starts emitting a log to inform the user of the event. # Otherwise if the option is set to no, the server aborts with an error # and refuses to start. When the option is set to no, the user requires -# to fix the AOF file using the "redis-check-aof" utility before to restart +# to fix the AOF file using the "valkey-check-aof" utility before to restart # the server. # # Note that if the AOF file will be found to be corrupted in the middle # the server will still exit with an error. This option only applies when -# Redis will try to read more data from the AOF file but not enough bytes +# the server will try to read more data from the AOF file but not enough bytes # will be found. aof-load-truncated yes -# When rewriting the AOF file, Redis is able to use an RDB preamble in the -# AOF file for faster rewrites and recoveries. When this option is turned -# on the rewritten AOF file is composed of two different stanzas: -# -# [RDB file][AOF tail] -# -# When loading Redis recognizes that the AOF file starts with the "REDIS" -# string and loads the prefixed RDB file, and continues loading the AOF -# tail. -# -# This is currently turned off by default in order to avoid the surprise -# of a format change, but will at some point be used as the default. -aof-use-rdb-preamble no +# The server can create append-only base files in either RDB or AOF formats. Using +# the RDB format is always faster and more efficient, and disabling it is only +# supported for backward compatibility purposes. +aof-use-rdb-preamble yes -################################ LUA SCRIPTING ############################### +# The server supports recording timestamp annotations in the AOF to support restoring +# the data from a specific point-in-time. However, using this capability changes +# the AOF format in a way that may not be compatible with existing AOF parsers. +aof-timestamp-enabled no -# Max execution time of a Lua script in milliseconds. -# -# If the maximum execution time is reached Redis will log that a script is -# still in execution after the maximum allowed time and will start to -# reply to queries with an error. -# -# When a long running script exceeds the maximum execution time only the -# SCRIPT KILL and SHUTDOWN NOSAVE commands are available. The first can be -# used to stop a script that did not yet called write commands. The second -# is the only way to shut down the server in the case a write command was -# already issued by the script but the user doesn't want to wait for the natural -# termination of the script. -# -# Set it to 0 or a negative value for unlimited execution without warnings. -lua-time-limit 5000 +################################ SHUTDOWN ##################################### -################################ REDIS CLUSTER ############################### +# Maximum time to wait for replicas when shutting down, in seconds. # -# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ -# WARNING EXPERIMENTAL: Redis Cluster is considered to be stable code, however -# in order to mark it as "mature" we need to wait for a non trivial percentage -# of users to deploy it in production. -# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ +# During shut down, a grace period allows any lagging replicas to catch up with +# the latest replication offset before the master exists. This period can +# prevent data loss, especially for deployments without configured disk backups. # -# Normal Redis instances can't be part of a Redis Cluster; only nodes that are -# started as cluster nodes can. In order to start a Redis instance as a +# The 'shutdown-timeout' value is the grace period's duration in seconds. It is +# only applicable when the instance has replicas. To disable the feature, set +# the value to 0. +# +# shutdown-timeout 10 + +# When the server receives a SIGINT or SIGTERM, shutdown is initiated and by default +# an RDB snapshot is written to disk in a blocking operation if save points are configured. +# The options used on signaled shutdown can include the following values: +# default: Saves RDB snapshot only if save points are configured. +# Waits for lagging replicas to catch up. +# save: Forces a DB saving operation even if no save points are configured. +# nosave: Prevents DB saving operation even if one or more save points are configured. +# now: Skips waiting for lagging replicas. +# force: Ignores any errors that would normally prevent the server from exiting. +# +# Any combination of values is allowed as long as "save" and "nosave" are not set simultaneously. +# Example: "nosave force now" +# +# shutdown-on-sigint default +# shutdown-on-sigterm default + +################ NON-DETERMINISTIC LONG BLOCKING COMMANDS ##################### + +# Maximum time in milliseconds for EVAL scripts, functions and in some cases +# modules' commands before the server can start processing or rejecting other clients. +# +# If the maximum execution time is reached the server will start to reply to most +# commands with a BUSY error. +# +# In this state the server will only allow a handful of commands to be executed. +# For instance, SCRIPT KILL, FUNCTION KILL, SHUTDOWN NOSAVE and possibly some +# module specific 'allow-busy' commands. +# +# SCRIPT KILL and FUNCTION KILL will only be able to stop a script that did not +# yet call any write commands, so SHUTDOWN NOSAVE may be the only way to stop +# the server in the case a write command was already issued by the script when +# the user doesn't want to wait for the natural termination of the script. +# +# The default is 5 seconds. It is possible to set it to 0 or a negative value +# to disable this mechanism (uninterrupted execution). Note that in the past +# this config had a different name, which is now an alias, so both of these do +# the same: +# lua-time-limit 5000 +# busy-reply-threshold 5000 + +################################ VALKEY CLUSTER ############################### + +# Normal server instances can't be part of a cluster; only nodes that are +# started as cluster nodes can. In order to start a server instance as a # cluster node enable the cluster support uncommenting the following: # # cluster-enabled yes # Every cluster node has a cluster configuration file. This file is not -# intended to be edited by hand. It is created and updated by Redis nodes. -# Every Redis Cluster node requires a different cluster configuration file. +# intended to be edited by hand. It is created and updated by each node. +# Every cluster node requires a different cluster configuration file. # Make sure that instances running in the same system do not have # overlapping cluster configuration file names. # @@ -823,46 +1582,51 @@ lua-time-limit 5000 # Cluster node timeout is the amount of milliseconds a node must be unreachable # for it to be considered in failure state. -# Most other internal time limits are multiple of the node timeout. +# Most other internal time limits are a multiple of the node timeout. # # cluster-node-timeout 15000 -# A slave of a failing master will avoid to start a failover if its data +# The cluster port is the port that the cluster bus will listen for inbound connections on. When set +# to the default value, 0, it will be bound to the command port + 10000. Setting this value requires +# you to specify the cluster bus port when executing cluster meet. +# cluster-port 0 + +# A replica of a failing master will avoid to start a failover if its data # looks too old. # -# There is no simple way for a slave to actually have an exact measure of +# There is no simple way for a replica to actually have an exact measure of # its "data age", so the following two checks are performed: # -# 1) If there are multiple slaves able to failover, they exchange messages -# in order to try to give an advantage to the slave with the best +# 1) If there are multiple replicas able to failover, they exchange messages +# in order to try to give an advantage to the replica with the best # replication offset (more data from the master processed). -# Slaves will try to get their rank by offset, and apply to the start +# Replicas will try to get their rank by offset, and apply to the start # of the failover a delay proportional to their rank. # -# 2) Every single slave computes the time of the last interaction with +# 2) Every single replica computes the time of the last interaction with # its master. This can be the last ping or command received (if the master # is still in the "connected" state), or the time that elapsed since the # disconnection with the master (if the replication link is currently down). -# If the last interaction is too old, the slave will not try to failover +# If the last interaction is too old, the replica will not try to failover # at all. # -# The point "2" can be tuned by user. Specifically a slave will not perform +# The point "2" can be tuned by user. Specifically a replica will not perform # the failover if, since the last interaction with the master, the time # elapsed is greater than: # -# (node-timeout * slave-validity-factor) + repl-ping-slave-period +# (node-timeout * cluster-replica-validity-factor) + repl-ping-replica-period # -# So for example if node-timeout is 30 seconds, and the slave-validity-factor -# is 10, and assuming a default repl-ping-slave-period of 10 seconds, the -# slave will not try to failover if it was not able to talk with the master +# So for example if node-timeout is 30 seconds, and the cluster-replica-validity-factor +# is 10, and assuming a default repl-ping-replica-period of 10 seconds, the +# replica will not try to failover if it was not able to talk with the master # for longer than 310 seconds. # -# A large slave-validity-factor may allow slaves with too old data to failover +# A large cluster-replica-validity-factor may allow replicas with too old data to failover # a master, while a too small value may prevent the cluster from being able to -# elect a slave at all. +# elect a replica at all. # -# For maximum availability, it is possible to set the slave-validity-factor -# to a value of 0, which means, that slaves will always try to failover the +# For maximum availability, it is possible to set the cluster-replica-validity-factor +# to a value of 0, which means, that replicas will always try to failover the # master regardless of the last time they interacted with the master. # (However they'll always try to apply a delay proportional to their # offset rank). @@ -870,29 +1634,38 @@ lua-time-limit 5000 # Zero is the only value able to guarantee that when all the partitions heal # the cluster will always be able to continue. # -# cluster-slave-validity-factor 10 +# cluster-replica-validity-factor 10 -# Cluster slaves are able to migrate to orphaned masters, that are masters -# that are left without working slaves. This improves the cluster ability +# Cluster replicas are able to migrate to orphaned masters, that are masters +# that are left without working replicas. This improves the cluster ability # to resist to failures as otherwise an orphaned master can't be failed over -# in case of failure if it has no working slaves. +# in case of failure if it has no working replicas. # -# Slaves migrate to orphaned masters only if there are still at least a -# given number of other working slaves for their old master. This number -# is the "migration barrier". A migration barrier of 1 means that a slave -# will migrate only if there is at least 1 other working slave for its master -# and so forth. It usually reflects the number of slaves you want for every +# Replicas migrate to orphaned masters only if there are still at least a +# given number of other working replicas for their old master. This number +# is the "migration barrier". A migration barrier of 1 means that a replica +# will migrate only if there is at least 1 other working replica for its master +# and so forth. It usually reflects the number of replicas you want for every # master in your cluster. # -# Default is 1 (slaves migrate only if their masters remain with at least -# one slave). To disable migration just set it to a very large value. +# Default is 1 (replicas migrate only if their masters remain with at least +# one replica). To disable migration just set it to a very large value or +# set cluster-allow-replica-migration to 'no'. # A value of 0 can be set but is useful only for debugging and dangerous # in production. # # cluster-migration-barrier 1 -# By default Redis Cluster nodes stop accepting queries if they detect there -# is at least an hash slot uncovered (no available node is serving it). +# Turning off this option allows to use less automatic cluster configuration. +# It both disables migration to orphaned masters and migration from masters +# that became empty. +# +# Default is 'yes' (allow automatic migrations). +# +# cluster-allow-replica-migration yes + +# By default cluster nodes stop accepting queries if they detect there +# is at least a hash slot uncovered (no available node is serving it). # This way if the cluster is partially down (for example a range of hash slots # are no longer covered) all the cluster becomes, eventually, unavailable. # It automatically returns available as soon as all the slots are covered again. @@ -904,62 +1677,135 @@ lua-time-limit 5000 # # cluster-require-full-coverage yes -# This option, when set to yes, prevents slaves from trying to failover its -# master during master failures. However the master can still perform a +# This option, when set to yes, prevents replicas from trying to failover its +# master during master failures. However the replica can still perform a # manual failover, if forced to do so. # # This is useful in different scenarios, especially in the case of multiple # data center operations, where we want one side to never be promoted if not # in the case of a total DC failure. # -# cluster-slave-no-failover no +# cluster-replica-no-failover no + +# This option, when set to yes, allows nodes to serve read traffic while the +# cluster is in a down state, as long as it believes it owns the slots. +# +# This is useful for two cases. The first case is for when an application +# doesn't require consistency of data during node failures or network partitions. +# One example of this is a cache, where as long as the node has the data it +# should be able to serve it. +# +# The second use case is for configurations that don't meet the recommended +# three shards but want to enable cluster mode and scale later. A +# master outage in a 1 or 2 shard configuration causes a read/write outage to the +# entire cluster without this option set, with it set there is only a write outage. +# Without a quorum of masters, slot ownership will not change automatically. +# +# cluster-allow-reads-when-down no + +# This option, when set to yes, allows nodes to serve pubsub shard traffic while +# the cluster is in a down state, as long as it believes it owns the slots. +# +# This is useful if the application would like to use the pubsub feature even when +# the cluster global stable state is not OK. If the application wants to make sure only +# one shard is serving a given channel, this feature should be kept as yes. +# +# cluster-allow-pubsubshard-when-down yes + +# Cluster link send buffer limit is the limit on the memory usage of an individual +# cluster bus link's send buffer in bytes. Cluster links would be freed if they exceed +# this limit. This is to primarily prevent send buffers from growing unbounded on links +# toward slow peers (E.g. PubSub messages being piled up). +# This limit is disabled by default. Enable this limit when 'mem_cluster_links' INFO field +# and/or 'send-buffer-allocated' entries in the 'CLUSTER LINKS` command output continuously increase. +# Minimum limit of 1gb is recommended so that cluster link buffer can fit in at least a single +# PubSub message by default. (client-query-buffer-limit default value is 1gb) +# +# cluster-link-sendbuf-limit 0 + +# Clusters can configure their announced hostname using this config. This is a common use case for +# applications that need to use TLS Server Name Indication (SNI) or dealing with DNS based +# routing. By default this value is only shown as additional metadata in the CLUSTER SLOTS +# command, but can be changed using 'cluster-preferred-endpoint-type' config. This value is +# communicated along the clusterbus to all nodes, setting it to an empty string will remove +# the hostname and also propagate the removal. +# +# cluster-announce-hostname "" + +# Clusters can configure an optional nodename to be used in addition to the node ID for +# debugging and admin information. This name is broadcasted between nodes, so will be used +# in addition to the node ID when reporting cross node events such as node failures. +# cluster-announce-human-nodename "" + +# Clusters can advertise how clients should connect to them using either their IP address, +# a user defined hostname, or by declaring they have no endpoint. Which endpoint is +# shown as the preferred endpoint is set by using the cluster-preferred-endpoint-type +# config with values 'ip', 'hostname', or 'unknown-endpoint'. This value controls how +# the endpoint returned for MOVED/ASKING requests as well as the first field of CLUSTER SLOTS. +# If the preferred endpoint type is set to hostname, but no announced hostname is set, a '?' +# will be returned instead. +# +# When a cluster advertises itself as having an unknown endpoint, it's indicating that +# the server doesn't know how clients can reach the cluster. This can happen in certain +# networking situations where there are multiple possible routes to the node, and the +# server doesn't know which one the client took. In this case, the server is expecting +# the client to reach out on the same endpoint it used for making the last request, but use +# the port provided in the response. +# +# cluster-preferred-endpoint-type ip # In order to setup your cluster make sure to read the documentation -# available at http://redis.io web site. +# available at https://valkey.io web site. ########################## CLUSTER DOCKER/NAT support ######################## -# In certain deployments, Redis Cluster nodes address discovery fails, because +# In certain deployments, cluster node's address discovery fails, because # addresses are NAT-ted or because ports are forwarded (the typical case is # Docker and other containers). # -# In order to make Redis Cluster working in such environments, a static +# In order to make a cluster work in such environments, a static # configuration where each node knows its public address is needed. The -# following two options are used for this scope, and are: +# following four options are used for this scope, and are: # # * cluster-announce-ip # * cluster-announce-port +# * cluster-announce-tls-port # * cluster-announce-bus-port # -# Each instruct the node about its address, client port, and cluster message -# bus port. The information is then published in the header of the bus packets -# so that other nodes will be able to correctly map the address of the node -# publishing the information. +# Each instructs the node about its address, client ports (for connections +# without and with TLS) and cluster message bus port. The information is then +# published in the header of the bus packets so that other nodes will be able to +# correctly map the address of the node publishing the information. # -# If the above options are not used, the normal Redis Cluster auto-detection +# If tls-cluster is set to yes and cluster-announce-tls-port is omitted or set +# to zero, then cluster-announce-port refers to the TLS port. Note also that +# cluster-announce-tls-port has no effect if tls-cluster is set to no. +# +# If the above options are not used, the normal cluster auto-detection # will be used instead. # # Note that when remapped, the bus port may not be at the fixed offset of # clients port + 10000, so you can specify any port and bus-port depending # on how they get remapped. If the bus-port is not set, a fixed offset of -# 10000 will be used as usually. +# 10000 will be used as usual. # # Example: # # cluster-announce-ip 10.1.1.5 -# cluster-announce-port 6379 +# cluster-announce-tls-port 6379 +# cluster-announce-port 0 # cluster-announce-bus-port 6380 ################################## SLOW LOG ################################### -# The Redis Slow Log is a system to log queries that exceeded a specified +# The server Slow Log is a system to log queries that exceeded a specified # execution time. The execution time does not include the I/O operations # like talking with the client, sending the reply and so forth, # but just the time needed to actually execute the command (this is the only # stage of command execution where the thread is blocked and can not serve # other requests in the meantime). # -# You can configure the slow log with two parameters: one tells Redis +# You can configure the slow log with two parameters: one tells the server # what is the execution time, in microseconds, to exceed in order for the # command to get logged, and the other parameter is the length of the # slow log. When a new command is logged the oldest one is removed from the @@ -976,9 +1822,9 @@ slowlog-max-len 128 ################################ LATENCY MONITOR ############################## -# The Redis latency monitoring subsystem samples different operations +# The server latency monitoring subsystem samples different operations # at runtime in order to collect data related to possible sources of -# latency of a Redis instance. +# latency of a server instance. # # Via the LATENCY command this information is available to the user that can # print graphs and obtain reports. @@ -995,10 +1841,24 @@ slowlog-max-len 128 # "CONFIG SET latency-monitor-threshold " if needed. latency-monitor-threshold 0 +################################ LATENCY TRACKING ############################## + +# The server's extended latency monitoring tracks the per command latencies and enables +# exporting the percentile distribution via the INFO latencystats command, +# and cumulative latency distributions (histograms) via the LATENCY command. +# +# By default, the extended latency monitoring is enabled since the overhead +# of keeping track of the command latency is very small. +# latency-tracking yes + +# By default the exported latency percentiles via the INFO latencystats command +# are the p50, p99, and p999. +# latency-tracking-info-percentiles 50 99 99.9 + ############################# EVENT NOTIFICATION ############################## -# Redis can notify Pub/Sub clients about events happening in the key space. -# This feature is documented at http://redis.io/topics/notifications +# The server can notify Pub/Sub clients about events happening in the key space. +# This feature is documented at https://valkey.io/topics/notifications # # For instance if keyspace events notification is enabled, and a client # performs a DEL operation on key "foo" stored in the Database 0, two @@ -1007,7 +1867,7 @@ latency-monitor-threshold 0 # PUBLISH __keyspace@0__:foo del # PUBLISH __keyevent@0__:del foo # -# It is possible to select the events that Redis will notify among a set +# It is possible to select the events that the server will notify among a set # of classes. Every class is identified by a single character: # # K Keyspace events, published with __keyspace@__ prefix. @@ -1020,7 +1880,13 @@ latency-monitor-threshold 0 # z Sorted set commands # x Expired events (events generated every time a key expires) # e Evicted events (events generated when a key is evicted for maxmemory) -# A Alias for g$lshzxe, so that the "AKE" string means all the events. +# n New key events (Note: not included in the 'A' class) +# t Stream commands +# d Module key type events +# m Key-miss events (Note: It is not included in the 'A' class) +# A Alias for g$lshzxetd, so that the "AKE" string means all the events +# (Except key-miss events which are excluded from 'A' due to their +# unique nature). # # The "notify-keyspace-events" takes as argument a string that is composed # of zero or multiple characters. The empty string means that notifications @@ -1046,8 +1912,8 @@ notify-keyspace-events "" # Hashes are encoded using a memory efficient data structure when they have a # small number of entries, and the biggest entry does not exceed a given # threshold. These thresholds can be configured using the following directives. -hash-max-ziplist-entries 512 -hash-max-ziplist-value 64 +hash-max-listpack-entries 512 +hash-max-listpack-value 64 # Lists are also encoded in a special way to save a lot of space. # The number of entries allowed per internal list node can be specified @@ -1062,7 +1928,7 @@ hash-max-ziplist-value 64 # per list node. # The highest performing option is usually -2 (8 Kb size) or -1 (4 Kb size), # but if your use case is unique, adjust the settings as necessary. -list-max-ziplist-size -2 +list-max-listpack-size -2 # Lists may also be compressed. # Compress depth is the number of quicklist ziplist nodes from *each* side of @@ -1080,21 +1946,28 @@ list-max-ziplist-size -2 # etc. list-compress-depth 0 -# Sets have a special encoding in just one case: when a set is composed +# Sets have a special encoding when a set is composed # of just strings that happen to be integers in radix 10 in the range # of 64 bit signed integers. # The following configuration setting sets the limit in the size of the # set in order to use this special memory saving encoding. set-max-intset-entries 512 +# Sets containing non-integer values are also encoded using a memory efficient +# data structure when they have a small number of entries, and the biggest entry +# does not exceed a given threshold. These thresholds can be configured using +# the following directives. +set-max-listpack-entries 128 +set-max-listpack-value 64 + # Similarly to hashes and lists, sorted sets are also specially encoded in # order to save a lot of space. This encoding is only used when the length and # elements of a sorted set are below the following limits: -zset-max-ziplist-entries 128 -zset-max-ziplist-value 64 +zset-max-listpack-entries 128 +zset-max-listpack-value 64 # HyperLogLog sparse representation bytes limit. The limit includes the -# 16 bytes header. When an HyperLogLog using the sparse representation crosses +# 16 bytes header. When a HyperLogLog using the sparse representation crosses # this limit, it is converted into the dense representation. # # A value greater than 16000 is totally useless, since at that point the @@ -1107,9 +1980,20 @@ zset-max-ziplist-value 64 # composed of many HyperLogLogs with cardinality in the 0 - 15000 range. hll-sparse-max-bytes 3000 +# Streams macro node max size / items. The stream data structure is a radix +# tree of big nodes that encode multiple items inside. Using this configuration +# it is possible to configure how big a single node can be in bytes, and the +# maximum number of items it may contain before switching to a new node when +# appending new stream entries. If any of the following settings are set to +# zero, the limit is ignored, so for instance it is possible to set just a +# max entries limit by setting max-bytes to 0 and max-entries to the desired +# value. +stream-node-max-bytes 4096 +stream-node-max-entries 100 + # Active rehashing uses 1 millisecond every 100 milliseconds of CPU time in -# order to help rehashing the main Redis hash table (the one mapping top-level -# keys to values). The hash table implementation Redis uses (see dict.c) +# order to help rehashing the main server hash table (the one mapping top-level +# keys to values). The hash table implementation the server uses (see dict.c) # performs a lazy rehashing: the more operation you run into a hash table # that is rehashing, the more rehashing "steps" are performed, so if the # server is idle the rehashing is never complete and some more memory is used @@ -1120,7 +2004,7 @@ hll-sparse-max-bytes 3000 # # If unsure: # use "activerehashing no" if you have hard latency requirements and it is -# not a good thing in your environment that Redis can reply from time to time +# not a good thing in your environment that the server can reply from time to time # to queries with 2 milliseconds delay. # # use "activerehashing yes" if you don't have such hard requirements but @@ -1135,7 +2019,7 @@ activerehashing yes # The limit can be set differently for the three different classes of clients: # # normal -> normal clients including MONITOR clients -# slave -> slave clients +# replica -> replica clients # pubsub -> clients subscribed to at least one pubsub channel or pattern # # The syntax of every client-output-buffer-limit directive is the following: @@ -1156,12 +2040,19 @@ activerehashing yes # asynchronous clients may create a scenario where data is requested faster # than it can read. # -# Instead there is a default limit for pubsub and slave clients, since -# subscribers and slaves receive data in a push fashion. +# Instead there is a default limit for pubsub and replica clients, since +# subscribers and replicas receive data in a push fashion. +# +# Note that it doesn't make sense to set the replica clients output buffer +# limit lower than the repl-backlog-size config (partial sync will succeed +# and then replica will get disconnected). +# Such a configuration is ignored (the size of repl-backlog-size will be used). +# This doesn't have memory consumption implications since the replica client +# will share the backlog buffers memory. # # Both the hard or the soft limit can be disabled by setting them to zero. client-output-buffer-limit normal 0 0 0 -client-output-buffer-limit slave 256mb 64mb 60 +client-output-buffer-limit replica 256mb 64mb 60 client-output-buffer-limit pubsub 32mb 8mb 60 # Client query buffers accumulate new commands. They are limited to a fixed @@ -1172,21 +2063,40 @@ client-output-buffer-limit pubsub 32mb 8mb 60 # # client-query-buffer-limit 1gb -# In the Redis protocol, bulk requests, that are, elements representing single -# strings, are normally limited ot 512 mb. However you can change this limit -# here. +# In some scenarios client connections can hog up memory leading to OOM +# errors or data eviction. To avoid this we can cap the accumulated memory +# used by all client connections (all pubsub and normal clients). Once we +# reach that limit connections will be dropped by the server freeing up +# memory. The server will attempt to drop the connections using the most +# memory first. We call this mechanism "client eviction". +# +# Client eviction is configured using the maxmemory-clients setting as follows: +# 0 - client eviction is disabled (default) +# +# A memory value can be used for the client eviction threshold, +# for example: +# maxmemory-clients 1g +# +# A percentage value (between 1% and 100%) means the client eviction threshold +# is based on a percentage of the maxmemory setting. For example to set client +# eviction at 5% of maxmemory: +# maxmemory-clients 5% + +# In the server protocol, bulk requests, that are, elements representing single +# strings, are normally limited to 512 mb. However you can change this limit +# here, but must be 1mb or greater # # proto-max-bulk-len 512mb -# Redis calls an internal function to perform many background tasks, like +# The server calls an internal function to perform many background tasks, like # closing connections of clients in timeout, purging expired keys that are # never requested, and so forth. # -# Not all tasks are performed with the same frequency, but Redis checks for +# Not all tasks are performed with the same frequency, but the server checks for # tasks to perform according to the specified "hz" value. # # By default "hz" is set to 10. Raising the value will use more CPU when -# Redis is idle, but at the same time will make Redis more responsive when +# the server is idle, but at the same time will make the server more responsive when # there are many keys expiring at the same time, and timeouts may be # handled with more precision. # @@ -1195,22 +2105,44 @@ client-output-buffer-limit pubsub 32mb 8mb 60 # 100 only in environments where very low latency is required. hz 10 +# Normally it is useful to have an HZ value which is proportional to the +# number of clients connected. This is useful in order, for instance, to +# avoid too many clients are processed for each background task invocation +# in order to avoid latency spikes. +# +# Since the default HZ value by default is conservatively set to 10, the server +# offers, and enables by default, the ability to use an adaptive HZ value +# which will temporarily raise when there are many connected clients. +# +# When dynamic HZ is enabled, the actual configured HZ will be used +# as a baseline, but multiples of the configured HZ value will be actually +# used as needed once more clients are connected. In this way an idle +# instance will use very little CPU time while a busy instance will be +# more responsive. +dynamic-hz yes + # When a child rewrites the AOF file, if the following option is enabled -# the file will be fsync-ed every 32 MB of data generated. This is useful +# the file will be fsync-ed every 4 MB of data generated. This is useful # in order to commit the file to the disk more incrementally and avoid # big latency spikes. aof-rewrite-incremental-fsync yes -# Redis LFU eviction (see maxmemory setting) can be tuned. However it is a good +# When the server saves RDB file, if the following option is enabled +# the file will be fsync-ed every 4 MB of data generated. This is useful +# in order to commit the file to the disk more incrementally and avoid +# big latency spikes. +rdb-save-incremental-fsync yes + +# The server's LFU eviction (see maxmemory setting) can be tuned. However it is a good # idea to start with the default settings and only change them after investigating # how to improve the performances and how the keys LFU change over time, which # is possible to inspect via the OBJECT FREQ command. # -# There are two tunable parameters in the Redis LFU implementation: the +# There are two tunable parameters in the server LFU implementation: the # counter logarithm factor and the counter decay time. It is important to # understand what the two parameters mean before changing them. # -# The LFU counter is just 8 bits per key, it's maximum value is 255, so Redis +# The LFU counter is just 8 bits per key, it's maximum value is 255, so the server # uses a probabilistic increment with logarithmic behavior. Given the value # of the old counter, when a key is accessed, the counter is incremented in # this way: @@ -1237,32 +2169,27 @@ aof-rewrite-incremental-fsync yes # # NOTE: The above table was obtained by running the following commands: # -# redis-benchmark -n 1000000 incr foo -# redis-cli object freq foo +# valkey-benchmark -n 1000000 incr foo +# valkey-cli object freq foo # # NOTE 2: The counter initial value is 5 in order to give new objects a chance # to accumulate hits. # # The counter decay time is the time, in minutes, that must elapse in order -# for the key counter to be divided by two (or decremented if it has a value -# less <= 10). +# for the key counter to be decremented. # -# The default value for the lfu-decay-time is 1. A Special value of 0 means to -# decay the counter every time it happens to be scanned. +# The default value for the lfu-decay-time is 1. A special value of 0 means we +# will never decay the counter. # # lfu-log-factor 10 # lfu-decay-time 1 ########################### ACTIVE DEFRAGMENTATION ####################### # -# WARNING THIS FEATURE IS EXPERIMENTAL. However it was stress tested -# even in production and manually tested by multiple engineers for some -# time. -# # What is active defragmentation? # ------------------------------- # -# Active (online) defragmentation allows a Redis server to compact the +# Active (online) defragmentation allows a server to compact the # spaces left between small allocations and deallocations of data in memory, # thus allowing to reclaim back memory. # @@ -1270,11 +2197,11 @@ aof-rewrite-incremental-fsync yes # less so with Jemalloc, fortunately) and certain workloads. Normally a server # restart is needed in order to lower the fragmentation, or at least to flush # away all the data and create it again. However thanks to this feature -# implemented by Oran Agra for Redis 4.0 this process can happen at runtime -# in an "hot" way, while the server is running. +# implemented by Oran Agra, this process can happen at runtime +# in a "hot" way, while the server is running. # # Basically when the fragmentation is over a certain level (see the -# configuration options below) Redis will start to create new copies of the +# configuration options below) the server will start to create new copies of the # values in contiguous memory regions by exploiting certain specific Jemalloc # features (in order to understand if an allocation is causing fragmentation # and to allocate it in a better place), and at the same time, will release the @@ -1283,8 +2210,8 @@ aof-rewrite-incremental-fsync yes # # Important things to understand: # -# 1. This feature is disabled by default, and only works if you compiled Redis -# to use the copy of Jemalloc we ship with the source code of Redis. +# 1. This feature is disabled by default, and only works if you compiled the server +# to use the copy of Jemalloc we ship with the source code of the server. # This is the default with Linux builds. # # 2. You never need to enable this feature if you don't have fragmentation @@ -1297,8 +2224,8 @@ aof-rewrite-incremental-fsync yes # defragmentation process. If you are not sure about what they mean it is # a good idea to leave the defaults untouched. -# Enabled active defragmentation -# activedefrag yes +# Active defragmentation is disabled by default +# activedefrag no # Minimum amount of fragmentation waste to start active defrag # active-defrag-ignore-bytes 100mb @@ -1309,9 +2236,49 @@ aof-rewrite-incremental-fsync yes # Maximum percentage of fragmentation at which we use maximum effort # active-defrag-threshold-upper 100 -# Minimal effort for defrag in CPU percentage -# active-defrag-cycle-min 25 +# Minimal effort for defrag in CPU percentage, to be used when the lower +# threshold is reached +# active-defrag-cycle-min 1 -# Maximal effort for defrag in CPU percentage -# active-defrag-cycle-max 75 +# Maximal effort for defrag in CPU percentage, to be used when the upper +# threshold is reached +# active-defrag-cycle-max 25 +# Maximum number of set/hash/zset/list fields that will be processed from +# the main dictionary scan +# active-defrag-max-scan-fields 1000 + +# Jemalloc background thread for purging will be enabled by default +jemalloc-bg-thread yes + +# It is possible to pin different threads and processes of the server to specific +# CPUs in your system, in order to maximize the performances of the server. +# This is useful both in order to pin different server threads in different +# CPUs, but also in order to make sure that multiple server instances running +# in the same host will be pinned to different CPUs. +# +# Normally you can do this using the "taskset" command, however it is also +# possible to do this via the server configuration directly, both in Linux and FreeBSD. +# +# You can pin the server/IO threads, bio threads, aof rewrite child process, and +# the bgsave child process. The syntax to specify the cpu list is the same as +# the taskset command: +# +# Set redis server/io threads to cpu affinity 0,2,4,6: +# server_cpulist 0-7:2 +# +# Set bio threads to cpu affinity 1,3: +# bio_cpulist 1,3 +# +# Set aof rewrite child process to cpu affinity 8,9,10,11: +# aof_rewrite_cpulist 8-11 +# +# Set bgsave child process to cpu affinity 1,10,11 +# bgsave_cpulist 1,10-11 + +# In some cases the server will emit warnings and even refuse to start if it detects +# that the system is in bad state, it is possible to suppress these warnings +# by setting the following config which takes a space delimited list of warnings +# to suppress +# +# ignore-warnings ARM64-COW-BUG diff --git a/temp/run_redis.sh b/temp/run_redis.sh index 5eb1308..acffdcb 100755 --- a/temp/run_redis.sh +++ b/temp/run_redis.sh @@ -3,5 +3,14 @@ set -e set -x -../../redis/src/redis-server ./intake.conf -../../redis/src/redis-server ./prepare.conf +if [ -f ../../valkey/src/valkey-server ]; then + ../../valkey/src/redis-server ./intake.conf + ../../valkey/src/redis-server ./prepare.conf +elif [ -f ../../redis/src/redis-server ]; then + ../../redis/src/redis-server ./intake.conf + ../../redis/src/redis-server ./prepare.conf +else + echo "Warning: using system redis-server. Valkey-server or redis-server from source is recommended." >&2 + /usr/bin/redis-server ./intake.conf + /usr/bin/redis-server ./prepare.conf +fi diff --git a/tools/clear_prepare_db.py b/tools/clear_prepare_db.py new file mode 100644 index 0000000..1b2021c --- /dev/null +++ b/tools/clear_prepare_db.py @@ -0,0 +1,21 @@ +#!/usr/bin/env python3 + +import uuid + +from redis import Redis +from bgpranking.default import get_socket_path + +redis_sanitized = Redis(unix_socket_path=get_socket_path('prepare'), db=0, decode_responses=True) +to_delete = [] +for name in redis_sanitized.scan_iter(_type='HASH', count=100): + try: + uuid.UUID(name) + except Exception as e: + continue + if not redis_sanitized.sismember('to_insert', name): + to_delete.append(name) + if len(to_delete) >= 100000: + redis_sanitized.delete(*to_delete) + to_delete = [] +if to_delete: + redis_sanitized.delete(*to_delete)