Revision 48e7effa79d1ab165e83b2f96455f77ffd79cca3 authored by Siying Dong on 26 March 2019, 02:14:04 UTC, committed by Facebook Github Bot on 26 March 2019, 02:18:04 UTC
Summary:
With https://github.com/facebook/rocksdb/pull/3009 we go through every CF
to check whether a bottommost compaction is needed to be triggered. This is done
within DB mutex. What we do within DB mutex may heavily influece the write throughput
we can achieve, so we always want to minimize work there.

Here we try to avoid this for-loop by first check a global threshold. In most of
the time, the CF loop can be avoided.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5090

Differential Revision: D14582684

Pulled By: siying

fbshipit-source-id: 968f6d9bb6affe1a5ebc4910b418300b076f166f
1 parent 52e6404
History
File Mode Size
win
README -rw-r--r-- 405 bytes
dirent.h -rw-r--r-- 1.0 KB
jemalloc_helper.h -rw-r--r-- 2.5 KB
likely.h -rw-r--r-- 690 bytes
port.h -rw-r--r-- 834 bytes
port_example.h -rw-r--r-- 3.5 KB
port_posix.cc -rw-r--r-- 6.0 KB
port_posix.h -rw-r--r-- 5.4 KB
stack_trace.cc -rw-r--r-- 3.5 KB
stack_trace.h -rw-r--r-- 648 bytes
sys_time.h -rw-r--r-- 1.1 KB
util_logger.h -rw-r--r-- 819 bytes
xpress.h -rw-r--r-- 687 bytes

README

back to top