From 34b753007d646482a4125a7095e1d1986d395f95 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 16 Oct 2016 21:08:02 +0200 Subject: [PATCH] perf bench futex: Cache align the worker struct It popped up in perf testing that the worker consumes some amount of CPU. It boils down to the increment of `ops` which causes cache line bouncing between the individual threads. This patch aligns the struct by 256 bytes to ensure that not a cache line is shared among CPUs. 128 byte is the x86 worst case and grep says that L1_CACHE_SHIFT is set to 8 on s390. Signed-off-by: Sebastian Andrzej Siewior Cc: Davidlohr Bueso Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20161016190803.3392-1-bigeasy@linutronix.de Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/futex-hash.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index 8024cd5febd2..d9e5e80bb4d0 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -39,12 +39,15 @@ static unsigned int threads_starting; static struct stats throughput_stats; static pthread_cond_t thread_parent, thread_worker; +#define SMP_CACHE_BYTES 256 +#define __cacheline_aligned __attribute__ ((aligned (SMP_CACHE_BYTES))) + struct worker { int tid; u_int32_t *futex; pthread_t thread; unsigned long ops; -}; +} __cacheline_aligned; static const struct option options[] = { OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), -- 2.20.1