The patch titled kernel/timekeeping: move xtime_cache to be in the same cache line as the lock has been added to the -mm tree. Its filename is kernel-timekeeping-move-xtime_cache-to-be-in-the-same-cache-line-as-the-lock.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: kernel/timekeeping: move xtime_cache to be in the same cache line as the lock From: Richard Kennedy <richard@xxxxxxxxxxxxxxx> Move xtime_cache to be in the same cache line as the lock, allowing current_kernel_time() to access only one cache line When running fio write tests on a 2 core machine, on some of the runs 'perf record -e cache_misses' shows current_kernel_time near the top of the list of cache_misses with 5.5%. On the other runs it's down at 0.05% so I'm assuming that the difference is just down to which core the test client get run on. This patch moves the xtime_cache variable near to the lock so that it only need to access one cache line. With this applied it drops the current_kernel_time cache_misses in the slow case to 4.5% Signed-off-by: Richard Kennedy <richard@xxxxxxxxxxxxxxx> Cc: John Stultz <johnstul@xxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- kernel/time/timekeeping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff -puN kernel/time/timekeeping.c~kernel-timekeeping-move-xtime_cache-to-be-in-the-same-cache-line-as-the-lock kernel/time/timekeeping.c --- a/kernel/time/timekeeping.c~kernel-timekeeping-move-xtime_cache-to-be-in-the-same-cache-line-as-the-lock +++ a/kernel/time/timekeeping.c @@ -137,6 +137,7 @@ static inline s64 timekeeping_get_ns_raw */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); +static struct timespec xtime_cache __attribute__ ((aligned (16))); /* * The current time @@ -165,7 +166,6 @@ struct timespec raw_time; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; -static struct timespec xtime_cache __attribute__ ((aligned (16))); void update_xtime_cache(u64 nsec) { xtime_cache = xtime; _ Patches currently in -mm which might be from richard@xxxxxxxxxxxxxxx are kernel-timekeeping-move-xtime_cache-to-be-in-the-same-cache-line-as-the-lock.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html