diff options
author | Thomas Gleixner <tglx@linutronix.de> | 2009-11-12 22:12:06 +0100 |
---|---|---|
committer | Thomas Gleixner <tglx@linutronix.de> | 2009-11-13 20:46:24 +0100 |
commit | 27185016b806d5a1181ff501cae120582b2b27dd (patch) | |
tree | 44b0da428fccaea1ad83c537bcc99a80b9251227 /kernel/time | |
parent | 98962465ed9e6ea99c38e0af63fe1dcb5a79dc25 (diff) | |
download | linux-27185016b806d5a1181ff501cae120582b2b27dd.tar.gz linux-27185016b806d5a1181ff501cae120582b2b27dd.tar.bz2 linux-27185016b806d5a1181ff501cae120582b2b27dd.zip |
nohz: Track last do_timer() cpu
The previous patch which limits the sleep time to the maximum
deferment time of the time keeping clocksource has some limitations on
SMP machines: if all CPUs are idle then for all CPUs the maximum sleep
time is limited.
Solve this by keeping track of which cpu had the do_timer() duty
assigned last and limit the sleep time only for this cpu.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <new-submission>
Cc: Jon Hunter <jon-hunter@ti.com>
Cc: John Stultz <johnstul@us.ibm.com>
Diffstat (limited to 'kernel/time')
-rw-r--r-- | kernel/time/tick-sched.c | 52 |
1 files changed, 28 insertions, 24 deletions
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index a80b4644fe6b..df133bc29f89 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -263,17 +263,7 @@ void tick_nohz_stop_sched_tick(int inidle) seq = read_seqbegin(&xtime_lock); last_update = last_jiffies_update; last_jiffies = jiffies; - - /* - * On SMP we really should only care for the CPU which - * has the do_timer duty assigned. All other CPUs can - * sleep as long as they want. - */ - if (cpu == tick_do_timer_cpu || - tick_do_timer_cpu == TICK_DO_TIMER_NONE) - time_delta = timekeeping_max_deferment(); - else - time_delta = KTIME_MAX; + time_delta = timekeeping_max_deferment(); } while (read_seqretry(&xtime_lock, seq)); if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) || @@ -296,6 +286,29 @@ void tick_nohz_stop_sched_tick(int inidle) if ((long)delta_jiffies >= 1) { /* + * If this cpu is the one which updates jiffies, then + * give up the assignment and let it be taken by the + * cpu which runs the tick timer next, which might be + * this cpu as well. If we don't drop this here the + * jiffies might be stale and do_timer() never + * invoked. Keep track of the fact that it was the one + * which had the do_timer() duty last. If this cpu is + * the one which had the do_timer() duty last, we + * limit the sleep time to the timekeeping + * max_deferement value which we retrieved + * above. Otherwise we can sleep as long as we want. + */ + if (cpu == tick_do_timer_cpu) { + tick_do_timer_cpu = TICK_DO_TIMER_NONE; + ts->do_timer_last = 1; + } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { + time_delta = KTIME_MAX; + ts->do_timer_last = 0; + } else if (!ts->do_timer_last) { + time_delta = KTIME_MAX; + } + + /* * calculate the expiry time for the next timer wheel * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals * that there is no timer pending or at least extremely @@ -312,21 +325,12 @@ void tick_nohz_stop_sched_tick(int inidle) */ time_delta = min_t(u64, time_delta, tick_period.tv64 * delta_jiffies); - expires = ktime_add_ns(last_update, time_delta); - } else { - expires.tv64 = KTIME_MAX; } - /* - * If this cpu is the one which updates jiffies, then - * give up the assignment and let it be taken by the - * cpu which runs the tick timer next, which might be - * this cpu as well. If we don't drop this here the - * jiffies might be stale and do_timer() never - * invoked. - */ - if (cpu == tick_do_timer_cpu) - tick_do_timer_cpu = TICK_DO_TIMER_NONE; + if (time_delta < KTIME_MAX) + expires = ktime_add_ns(last_update, time_delta); + else + expires.tv64 = KTIME_MAX; if (delta_jiffies > 1) cpumask_set_cpu(cpu, nohz_cpu_mask); |