diff options
author | Ingo Molnar <mingo@elte.hu> | 2008-11-08 16:19:55 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2008-11-08 16:48:19 +0100 |
commit | 0d12cdd5f883f508d33b85c1bae98fa28987c8c7 (patch) | |
tree | e07bb1f9ef49062fbd9817fe41cab66964bedf03 /arch/x86/include/asm/tsc.h | |
parent | 52c642f33b14bfa1b00ef2b68296effb34a573f3 (diff) | |
download | linux-stable-0d12cdd5f883f508d33b85c1bae98fa28987c8c7.tar.gz linux-stable-0d12cdd5f883f508d33b85c1bae98fa28987c8c7.tar.bz2 linux-stable-0d12cdd5f883f508d33b85c1bae98fa28987c8c7.zip |
sched: improve sched_clock() performance
in scheduler-intense workloads native_read_tsc() overhead accounts for
20% of the system overhead:
659567 system_call 41222.9375
686796 schedule 435.7843
718382 __switch_to 665.1685
823875 switch_mm 4526.7857
1883122 native_read_tsc 55385.9412
9761990 total 2.8468
this is large part due to the rdtsc_barrier() that is done before
and after reading the TSC.
But sched_clock() is not a precise clock in the GTOD sense, using such
barriers is completely pointless. So remove the barriers and only use
them in vget_cycles().
This improves lat_ctx performance by about 5%.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86/include/asm/tsc.h')
-rw-r--r-- | arch/x86/include/asm/tsc.h | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 38ae163cc91b..9cd83a8e40d5 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -34,6 +34,8 @@ static inline cycles_t get_cycles(void) static __always_inline cycles_t vget_cycles(void) { + cycles_t cycles; + /* * We only do VDSOs on TSC capable CPUs, so this shouldnt * access boot_cpu_data (which is not VDSO-safe): @@ -42,7 +44,11 @@ static __always_inline cycles_t vget_cycles(void) if (!cpu_has_tsc) return 0; #endif - return (cycles_t)__native_read_tsc(); + rdtsc_barrier(); + cycles = (cycles_t)__native_read_tsc(); + rdtsc_barrier(); + + return cycles; } extern void tsc_init(void); |