llvm-project/compiler-rt
Dmitry Vyukov 9f2c6207d5 tsan: optimize sync clock memory consumption
This change implements 2 optimizations of sync clocks that reduce memory consumption:

Use previously unused first level block space to store clock elements.
Currently a clock for 100 threads consumes 3 512-byte blocks:

2 64-bit second level blocks to store clock elements
+1 32-bit first level block to store indices to second level blocks
Only 8 bytes of the first level block are actually used.
With this change such clock consumes only 2 blocks.

Share similar clocks differing only by a single clock entry for the current thread.
When a thread does several release operations on fresh sync objects without intervening
acquire operations in between (e.g. initialization of several fields in ctor),
the resulting clocks differ only by a single entry for the current thread.
This change reuses a single clock for such release operations. The current thread time
(which is different for different clocks) is stored in dirty entries.

We are experiencing issues with a large program that eats all 64M clock blocks
(32GB of non-flushable memory) and crashes with dense allocator overflow.
Max number of threads in the program is ~170 which is currently quite unfortunate
(consume 4 blocks per clock). Currently it crashes after consuming 60+ GB of memory.
The first optimization brings clock block consumption down to ~40M and
allows the program to work. The second optimization further reduces block consumption
to "modest" 16M blocks (~8GB of RAM) and reduces overall RAM consumption to ~30GB.

Measurements on another real world C++ RPC benchmark show RSS reduction
from 3.491G to 3.186G and a modest speedup of ~5%.

Go parallel client/server HTTP benchmark:
https://github.com/golang/benchmarks/blob/master/http/http.go
shows RSS reduction from 320MB to 240MB and a few percent speedup.

Reviewed in https://reviews.llvm.org/D35323

llvm-svn: 308018
2017-07-14 11:30:06 +00:00
..
cmake On Darwin, start building the TSan iOS dylib by default. 2017-07-12 20:25:14 +00:00
docs [sanitizers] Make it possible to XFAIL on the effective target, not just the default. 2016-08-09 11:50:53 +00:00
include [XRay][compiler-rt][NFC] Add a name for argument to __xray_set_handler_arg1(...) 2017-06-19 01:30:04 +00:00
lib tsan: optimize sync clock memory consumption 2017-07-14 11:30:06 +00:00
test [ubsan] Teach the pointer overflow check that "p - <unsigned> <= p" (compiler-rt) 2017-07-13 20:55:41 +00:00
unittests Add missing import 2017-04-07 01:24:48 +00:00
www Update references to new lists.llvm.org mailing lists. 2015-08-05 03:58:00 +00:00
.arcconfig Upgrade all the .arcconfigs to https. 2016-07-14 13:15:37 +00:00
.gitignore
CMakeLists.txt Make sure SANITIZER_MIN_OSX_VERSION is defined before using it. 2017-07-07 22:40:13 +00:00
CODE_OWNERS.TXT [sanitizers] remove earthdok@ from owners 2016-05-18 18:52:18 +00:00
CREDITS.TXT
LICENSE.TXT Update copyright year to 2016. 2016-03-30 22:38:50 +00:00
README.txt

README.txt

Compiler-RT
================================

This directory and its subdirectories contain source code for the compiler
support routines.

Compiler-RT is open source software. You may freely distribute it under the
terms of the license agreement found in LICENSE.txt.

================================