diff options
author | Josh Snyder <joshs@netflix.com> | 2017-12-18 16:15:10 +0000 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2018-01-16 03:29:36 +0100 |
commit | c96f5471ce7d2aefd0dda560cc23f08ab00bc65d (patch) | |
tree | 84feeca0e7b0819b55216e1fea50a3e0e79d445b /kernel/delayacct.c | |
parent | a8750ddca918032d6349adbf9a4b6555e7db20da (diff) | |
download | op-kernel-dev-c96f5471ce7d2aefd0dda560cc23f08ab00bc65d.zip op-kernel-dev-c96f5471ce7d2aefd0dda560cc23f08ab00bc65d.tar.gz |
delayacct: Account blkio completion on the correct task
Before commit:
e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler")
delayacct_blkio_end() was called after context-switching into the task which
completed I/O.
This resulted in double counting: the task would account a delay both waiting
for I/O and for time spent in the runqueue.
With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up().
In ttwu, we have not yet context-switched. This is more correct, in that
the delay accounting ends when the I/O is complete.
But delayacct_blkio_end() relies on 'get_current()', and we have not yet
context-switched into the task whose I/O completed. This results in the
wrong task having its delay accounting statistics updated.
Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(),
so that it can update the statistics of the correct task.
Signed-off-by: Josh Snyder <joshs@netflix.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Cc: <stable@vger.kernel.org>
Cc: Brendan Gregg <bgregg@netflix.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-block@vger.kernel.org
Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler")
Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/delayacct.c')
-rw-r--r-- | kernel/delayacct.c | 42 |
1 files changed, 26 insertions, 16 deletions
diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 4a1c334..e2764d7 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -51,16 +51,16 @@ void __delayacct_tsk_init(struct task_struct *tsk) * Finish delay accounting for a statistic using its timestamps (@start), * accumalator (@total) and @count */ -static void delayacct_end(u64 *start, u64 *total, u32 *count) +static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count) { s64 ns = ktime_get_ns() - *start; unsigned long flags; if (ns > 0) { - spin_lock_irqsave(¤t->delays->lock, flags); + spin_lock_irqsave(lock, flags); *total += ns; (*count)++; - spin_unlock_irqrestore(¤t->delays->lock, flags); + spin_unlock_irqrestore(lock, flags); } } @@ -69,17 +69,25 @@ void __delayacct_blkio_start(void) current->delays->blkio_start = ktime_get_ns(); } -void __delayacct_blkio_end(void) +/* + * We cannot rely on the `current` macro, as we haven't yet switched back to + * the process being woken. + */ +void __delayacct_blkio_end(struct task_struct *p) { - if (current->delays->flags & DELAYACCT_PF_SWAPIN) - /* Swapin block I/O */ - delayacct_end(¤t->delays->blkio_start, - ¤t->delays->swapin_delay, - ¤t->delays->swapin_count); - else /* Other block I/O */ - delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_delay, - ¤t->delays->blkio_count); + struct task_delay_info *delays = p->delays; + u64 *total; + u32 *count; + + if (p->delays->flags & DELAYACCT_PF_SWAPIN) { + total = &delays->swapin_delay; + count = &delays->swapin_count; + } else { + total = &delays->blkio_delay; + count = &delays->blkio_count; + } + + delayacct_end(&delays->lock, &delays->blkio_start, total, count); } int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) @@ -153,8 +161,10 @@ void __delayacct_freepages_start(void) void __delayacct_freepages_end(void) { - delayacct_end(¤t->delays->freepages_start, - ¤t->delays->freepages_delay, - ¤t->delays->freepages_count); + delayacct_end( + ¤t->delays->lock, + ¤t->delays->freepages_start, + ¤t->delays->freepages_delay, + ¤t->delays->freepages_count); } |