tsan: speed up race deduplication
Race deduplication code proved to be a performance bottleneck in the past if suppressions/annotations are used, or just some races left unaddressed. And we still get user complaints about this:
https://groups.google.com/forum/#!topic/thread-sanitizer/hB0WyiTI4e4
ReportRace already has several layers of caching for racy pcs/addresses to make deduplication faster. However, ReportRace still takes a global mutex (ThreadRegistry and ReportMutex) during deduplication and also calls mmap/munmap (which take process-wide semaphore in kernel), this makes deduplication non-scalable.
This patch moves race deduplication outside of global mutexes and also removes all mmap/munmap calls.
As the result, race_stress.cc with 100 threads and 10000 iterations become 30x faster:
before:
real 0m21.673s
user 0m5.932s
sys 0m34.885s
after:
real 0m0.720s
user 0m23.646s
sys 0m1.254s
http://reviews.llvm.org/D12554
llvm-svn: 246758
diff --git a/compiler-rt/lib/tsan/rtl/tsan_rtl.h b/compiler-rt/lib/tsan/rtl/tsan_rtl.h
index e51e466..ae44bc9 100644
--- a/compiler-rt/lib/tsan/rtl/tsan_rtl.h
+++ b/compiler-rt/lib/tsan/rtl/tsan_rtl.h
@@ -458,7 +458,7 @@
struct FiredSuppression {
ReportType type;
- uptr pc;
+ uptr pc_or_addr;
Suppression *supp;
};
@@ -480,9 +480,11 @@
ThreadRegistry *thread_registry;
+ Mutex racy_mtx;
Vector<RacyStacks> racy_stacks;
Vector<RacyAddress> racy_addresses;
// Number of fired suppressions may be large enough.
+ Mutex fired_suppressions_mtx;
InternalMmapVector<FiredSuppression> fired_suppressions;
DDetector *dd;
@@ -587,8 +589,7 @@
void ReportRace(ThreadState *thr);
bool OutputReport(ThreadState *thr, const ScopedReport &srep);
-bool IsFiredSuppression(Context *ctx, const ScopedReport &srep,
- StackTrace trace);
+bool IsFiredSuppression(Context *ctx, ReportType type, StackTrace trace);
bool IsExpectedReport(uptr addr, uptr size);
void PrintMatchedBenignRaces();