Commit Graph

8 Commits

Author SHA1 Message Date
Alexander Kuzmenkov
030419db90 Try 12 threads max in perf test.
This will allow us to use more machines, not only Gold 6320.
2020-11-09 19:14:05 +03:00
Alexander Kuzmenkov
764f19820b max threads 2020-10-19 17:39:52 +03:00
Alexey Milovidov
35e8a895b6 Calculate profiler data in separate query runs 2020-09-19 20:38:21 +03:00
Alexander Kuzmenkov
000326b627 Avoid timeouts in perf test 2020-08-19 18:08:23 +03:00
Alexander Kuzmenkov
f514d0da77
Revert "Run perf tests with memory sampling (for allocations >1M)" 2020-07-07 19:59:42 +03:00
Azat Khuzhin
307c3c92a5 Run perf tests with memory sampling (for allocations >1M)
This is to know the memory allocation size distribution, that can be
obtained later from left-metric-log.tsv.

This is an attempt to tune tcmalloc (new CPP version by google) to use
lock-free part of the allocator for typical allocations (and it is a bad
idea just to increase kMaxSize there, since number of allocation for
each size class is also important).

P.S. hope that this file will be applied, if no, then the same effect
can be reached by tunning defaults in Settings.h

Refs: #11590
Cc: @akuzm
2020-07-05 12:43:12 +03:00
Alexander Kuzmenkov
377da4656d cleanup 2020-06-04 18:51:34 +03:00
Alexander Kuzmenkov
ebe70f5bcb performance comparison 2020-02-25 16:12:26 +03:00