OpenCloud
/
MatrixSynapse
mirror of https://github.com/matrix-org/synapse
1
0
Fork 0
Code Issues Releases Wiki Activity

explain why CPU affinity is a good idea

matthew/hide-public-rooms
Matthew Hodgson 2017-08-15 18:27:42 +01:00
parent 963015005e
commit 92168cbbc5
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
synapse/config/server.py
View File

@ -153,10 +153,18 @@ class ServerConfig(Config):
# bit corresponding to the first logical CPU and the highest order bit # bit corresponding to the first logical CPU and the highest order bit
# corresponding to the last logical CPU. Not all CPUs may exist on a # corresponding to the last logical CPU. Not all CPUs may exist on a
# given system but a mask may specify more CPUs than are present. # given system but a mask may specify more CPUs than are present.
#
# For example: # For example:
# 0x00000001 is processor #0, # 0x00000001 is processor #0,
# 0x00000003 is processors #0 and #1, # 0x00000003 is processors #0 and #1,
# 0xFFFFFFFF is all processors (#0 through #31). # 0xFFFFFFFF is all processors (#0 through #31).
#
# This is desirable for Synapse processes (especially workers), which are
# inherently single-threaded due to the GIL and can suffer a 30-40% slowdown
# due to cache blow-out and thread context switching if the scheduler happens
# to schedule the underlying threads across different cores.
# See https://www.mirantis.com/blog/improve-performance-python-programs-restricting-single-cpu/
#
# cpu_affinity: 0xFFFFFFFF # cpu_affinity: 0xFFFFFFFF
# Whether to serve a web client from the HTTP/HTTPS root resource. # Whether to serve a web client from the HTTP/HTTPS root resource.