Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(242)

Unified Diff: third_party/tcmalloc/chromium/src/base/spinlock_linux-inl.h

Issue 9667026: Revert 126020 - Experiment for updating the tcmalloc chromium branch to r144 (gperftools 2.0). (Closed) Base URL: svn://svn.chromium.org/chrome/trunk/src/
Patch Set: Created 8 years, 9 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
Index: third_party/tcmalloc/chromium/src/base/spinlock_linux-inl.h
===================================================================
--- third_party/tcmalloc/chromium/src/base/spinlock_linux-inl.h (revision 126022)
+++ third_party/tcmalloc/chromium/src/base/spinlock_linux-inl.h (working copy)
@@ -31,7 +31,6 @@
* This file is a Linux-specific part of spinlock_internal.cc
*/
-#include <errno.h>
#include <sched.h>
#include <time.h>
#include <limits.h>
@@ -87,12 +86,12 @@
struct timespec tm;
tm.tv_sec = 0;
if (have_futex) {
- tm.tv_nsec = base::internal::SuggestedDelayNS(loop);
+ tm.tv_nsec = 1000000; // 1ms; really we're trying to sleep for one
+ // kernel clock tick
} else {
tm.tv_nsec = 2000001; // above 2ms so linux 2.4 doesn't spin
}
if (have_futex) {
- tm.tv_nsec *= 16; // increase the delay; we expect explicit wakeups
syscall(__NR_futex, reinterpret_cast<int *>(const_cast<Atomic32 *>(w)),
FUTEX_WAIT | futex_private_flag,
value, reinterpret_cast<struct kernel_timespec *>(&tm));

Powered by Google App Engine
This is Rietveld 408576698