diff options
| author | Rik van Riel <[email protected]> | 2018-07-16 19:03:37 +0000 |
|---|---|---|
| committer | Ingo Molnar <[email protected]> | 2018-07-17 07:35:34 +0000 |
| commit | e9d8c61557687b7126101e9550bdf243223f0d8f (patch) | |
| tree | 2d467669575e3dbecc972a3c4922f6a615686acb /tools/perf/util/llvm-utils.c | |
| parent | x86/mm/tlb: Always use lazy TLB mode (diff) | |
| download | kernel-e9d8c61557687b7126101e9550bdf243223f0d8f.tar.gz kernel-e9d8c61557687b7126101e9550bdf243223f0d8f.zip | |
x86/mm/tlb: Skip atomic operations for 'init_mm' in switch_mm_irqs_off()
Song Liu noticed switch_mm_irqs_off() taking a lot of CPU time in recent
kernels,using 1.8% of a 48 CPU system during a netperf to localhost run.
Digging into the profile, we noticed that cpumask_clear_cpu and
cpumask_set_cpu together take about half of the CPU time taken by
switch_mm_irqs_off().
However, the CPUs running netperf end up switching back and forth
between netperf and the idle task, which does not require changes
to the mm_cpumask. Furthermore, the init_mm cpumask ends up being
the most heavily contended one in the system.
Simply skipping changes to mm_cpumask(&init_mm) reduces overhead.
Reported-and-tested-by: Song Liu <[email protected]>
Signed-off-by: Rik van Riel <[email protected]>
Acked-by: Dave Hansen <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
Diffstat (limited to 'tools/perf/util/llvm-utils.c')
0 files changed, 0 insertions, 0 deletions