chg: update all the things

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]

ranking/kvrocks.conf

@@ -1,52 +1,79 @@
 ################################ GENERAL #####################################
 
-# By default kvrocks listens for connections from all the network interfaces
+# By default kvrocks listens for connections from localhost interface.
-# available on the server. It is possible to listen to just one or multiple
+# It is possible to listen to just one or multiple interfaces using
-# interfaces using the "bind" configuration directive, followed by one or
+# the "bind" configuration directive, followed by one or more IP addresses.
-# 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.
+# By default, kvrocks does not run as a daemon. Use 'yes' if you need it.
-# Default: 1
+# Note that kvrocks will write a PID file in /var/run/kvrocks.pid when daemonized
-repl-workers 1
+daemonize yes
 
-# By default kvrocks does not run as a daemon. Use 'yes' if you need it.
+# Kvrocks implements the cluster solution that is similar to the Redis cluster solution.
-# 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.
 # 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.
+# 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
+# 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
+# CRC16 and modulo 16384, encoding key with its slot id makes it efficient to
-# migrate keys based on slot. So if you enabled at first time, cluster mode must
+# 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
+# You can configure where to store your server logs by the log-dir.
-# one directory, by default, we store logs in the working directory that set
+# If you don't specify one, we will use the above `dir` as our default log directory.
-# by 'dir' above.
+# We also can send logs to stdout/stderr is as simple as:
-# log-dir /tmp/kvrocks
+#
+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
+# Default: 0
-max-io-mb 500
+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.
+# max-bitmap-to-string-mb use to limit the max size of bitmap to string transformation(MB).
-# we simply use the rand to determine whether to record the sample or not.
 #
-# Default: 0
+# Default: 16
-profiling-sample-ratio 0
+max-bitmap-to-string-mb 16
 
-# There is no limit to this length. Just be aware that it will consume memory.
+# Whether to enable SCAN-like cursor compatible with Redis.
-# You can reclaim memory used by the perf log with PERFLOG RESET.
+# If enabled, the cursor will be unsigned 64-bit integers.
-#
+# If disabled, the cursor will be a string.
-# Default: 256
+# Default: no
-profiling-sample-record-max-len 256
+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
+# Default: no
-profiling-sample-record-threshold-ms 100
+# 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
+################################ MIGRATE #####################################
-# may cause data loading(large index/filter block) ineffective when the key-value was too small.
+# Slot migration supports two ways:
-# kvrocks supports user-defined SST file in config(rocksdb.target_file_size_base),
+# - redis-command: Migrate data by redis serialization protocol(RESP).
-# but it still too trivial and inconvenient to adjust the different sizes for different instances.
+# - raw-key-value: Migrate the raw key value data of the storage engine directly.
-# so we want to periodic auto-adjust the SST size in-flight with user avg key-value size.
+#                  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
+# Default: redis-command
-# and rocksdb.write_buffer_size in-flight with user avg key-value size.
+migrate-type redis-command
-# Please see #118.
+
+# 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
+# Default: 4096
-auto-resize-block-and-sst yes
+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
+# Specify the capacity of column family block cache. A larger block cache
-# may make request faster while more keys would be cached. Max Size is 200*1024.
+# may make requests faster while more keys would be cached. Max Size is 400*1024.
-# Default: 2048MB
+# Default: 4096MB
-rocksdb.metadata_block_cache_size 2048
+rocksdb.block_cache_size 4096
 
-# Specify the capacity  of subkey column family block cache. Larger block cache
+# Specify the type of cache used in the block cache.
-# may make request faster while more keys would be cached. Max Size is 200*1024.
+# Accept value: "lru", "hcc"
-# Default: 2048MB
+# "lru" stands for the cache with the LRU(Least Recently Used) replacement policy.
-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
 #
-# Default: yes
+# "hcc" stands for the Hyper Clock Cache, a lock-free cache alternative
-rocksdb.share_metadata_and_subkey_block_cache yes
+# 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.
+# 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 logswill be deleted.
+# 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#
 #
@@ -431,16 +717,16 @@ rocksdb.wal_size_limit_mb 16384
 # actual size of the unit read from disk may be smaller if
 # compression is enabled.
 #
-# Default: 4KB
+# Default: 16KB
-rocksdb.block_size 2048
+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 ./

storage/kvrocks.conf

@@ -1,52 +1,79 @@
 ################################ GENERAL #####################################
 
-# By default kvrocks listens for connections from all the network interfaces
+# By default kvrocks listens for connections from localhost interface.
-# available on the server. It is possible to listen to just one or multiple
+# It is possible to listen to just one or multiple interfaces using
-# interfaces using the "bind" configuration directive, followed by one or
+# the "bind" configuration directive, followed by one or more IP addresses.
-# 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.
+# By default, kvrocks does not run as a daemon. Use 'yes' if you need it.
-# Default: 1
+# Note that kvrocks will write a PID file in /var/run/kvrocks.pid when daemonized
-repl-workers 1
+daemonize yes
 
-# By default kvrocks does not run as a daemon. Use 'yes' if you need it.
+# Kvrocks implements the cluster solution that is similar to the Redis cluster solution.
-# 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.
 # 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.
+# 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
+# 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
+# CRC16 and modulo 16384, encoding key with its slot id makes it efficient to
-# migrate keys based on slot. So if you enabled at first time, cluster mode must
+# 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
+# You can configure where to store your server logs by the log-dir.
-# one directory, by default, we store logs in the working directory that set
+# If you don't specify one, we will use the above `dir` as our default log directory.
-# by 'dir' above.
+# We also can send logs to stdout/stderr is as simple as:
-# log-dir /tmp/kvrocks
+#
+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
+# Default: 0
-max-io-mb 500
+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.
+# max-bitmap-to-string-mb use to limit the max size of bitmap to string transformation(MB).
-# we simply use the rand to determine whether to record the sample or not.
 #
-# Default: 0
+# Default: 16
-profiling-sample-ratio 0
+max-bitmap-to-string-mb 16
 
-# There is no limit to this length. Just be aware that it will consume memory.
+# Whether to enable SCAN-like cursor compatible with Redis.
-# You can reclaim memory used by the perf log with PERFLOG RESET.
+# If enabled, the cursor will be unsigned 64-bit integers.
-#
+# If disabled, the cursor will be a string.
-# Default: 256
+# Default: no
-profiling-sample-record-max-len 256
+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
+# Default: no
-profiling-sample-record-threshold-ms 100
+# 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
+################################ MIGRATE #####################################
-# may cause data loading(large index/filter block) ineffective when the key-value was too small.
+# Slot migration supports two ways:
-# kvrocks supports user-defined SST file in config(rocksdb.target_file_size_base),
+# - redis-command: Migrate data by redis serialization protocol(RESP).
-# but it still too trivial and inconvenient to adjust the different sizes for different instances.
+# - raw-key-value: Migrate the raw key value data of the storage engine directly.
-# so we want to periodic auto-adjust the SST size in-flight with user avg key-value size.
+#                  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
+# Default: redis-command
-# and rocksdb.write_buffer_size in-flight with user avg key-value size.
+migrate-type redis-command
-# Please see #118.
+
+# 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
+# Default: 4096
-auto-resize-block-and-sst yes
+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
+# Specify the capacity of column family block cache. A larger block cache
-# may make request faster while more keys would be cached. Max Size is 200*1024.
+# may make requests faster while more keys would be cached. Max Size is 400*1024.
-# Default: 2048MB
+# Default: 4096MB
-rocksdb.metadata_block_cache_size 2048
+rocksdb.block_cache_size 4096
 
-# Specify the capacity  of subkey column family block cache. Larger block cache
+# Specify the type of cache used in the block cache.
-# may make request faster while more keys would be cached. Max Size is 200*1024.
+# Accept value: "lru", "hcc"
-# Default: 2048MB
+# "lru" stands for the cache with the LRU(Least Recently Used) replacement policy.
-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
 #
-# Default: yes
+# "hcc" stands for the Hyper Clock Cache, a lock-free cache alternative
-rocksdb.share_metadata_and_subkey_block_cache yes
+# 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.
+# 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 logswill be deleted.
+# 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#
 #
@@ -431,16 +717,16 @@ rocksdb.wal_size_limit_mb 16384
 # actual size of the unit read from disk may be smaller if
 # compression is enabled.
 #
-# Default: 4KB
+# Default: 16KB
-rocksdb.block_size 2048
+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 ./

temp/run_redis.sh

@@ -3,5 +3,14 @@
 set -e
 set -x
 
-../../redis/src/redis-server ./intake.conf
+if [ -f  ../../valkey/src/valkey-server ]; then
-../../redis/src/redis-server ./prepare.conf
+    ../../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

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)