In NUMA machine, prepare_to_wait/finish_wait in make_request exposes a lot of
contention for sequential workload (or big request size workload). For such
workload, each bio includes several stripes. So we can just do
prepare_to_wait/finish_wait once for the whold bio instead of every stripe.
This reduces the lock contention completely for such workload. Random workload
might have the similar lock contention too, but I didn't see it yet, maybe
because my stroage is still not fast enough.
Signed-off-by: Shaohua Li <shli@xxxxxxxxxxxx>
---
drivers/md/raid5.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
Index: linux/drivers/md/raid5.c
===================================================================
--- linux.orig/drivers/md/raid5.c 2014-04-08 09:04:20.000000000 +0800
+++ linux/drivers/md/raid5.c 2014-04-08 09:11:08.201533487 +0800
@@ -4552,6 +4552,8 @@ static void make_request(struct mddev *m
struct stripe_head *sh;
const int rw = bio_data_dir(bi);
int remaining;
+ DEFINE_WAIT(w);
+ bool do_prepare;
if (unlikely(bi->bi_rw & REQ_FLUSH)) {
md_flush_request(mddev, bi);
@@ -4575,15 +4577,19 @@ static void make_request(struct mddev *m
bi->bi_next = NULL;
bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
+ prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
DEFINE_WAIT(w);
int previous;
int seq;
+ do_prepare = false;
retry:
seq = read_seqcount_begin(&conf->gen_lock);
previous = 0;
- prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
+ if (do_prepare)
+ prepare_to_wait(&conf->wait_for_overlap, &w,
+ TASK_UNINTERRUPTIBLE);
if (unlikely(conf->reshape_progress != MaxSector)) {
/* spinlock is needed as reshape_progress may be
* 64bit on a 32bit platform, and so it might be
@@ -4604,6 +4610,7 @@ static void make_request(struct mddev *m
: logical_sector >= conf->reshape_safe) {
spin_unlock_irq(&conf->device_lock);
schedule();
+ do_prepare = true;
goto retry;
}
}
@@ -4640,6 +4647,7 @@ static void make_request(struct mddev *m
if (must_retry) {
release_stripe(sh);
schedule();
+ do_prepare = true;
goto retry;
}
}
@@ -4663,8 +4671,10 @@ static void make_request(struct mddev *m
prepare_to_wait(&conf->wait_for_overlap,
&w, TASK_INTERRUPTIBLE);
if (logical_sector >= mddev->suspend_lo &&
- logical_sector < mddev->suspend_hi)
+ logical_sector < mddev->suspend_hi) {
schedule();
+ do_prepare = true;
+ }
goto retry;
}
@@ -4677,9 +4687,9 @@ static void make_request(struct mddev *m
md_wakeup_thread(mddev->thread);
release_stripe(sh);
schedule();
+ do_prepare = true;
goto retry;
}
- finish_wait(&conf->wait_for_overlap, &w);
set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
if ((bi->bi_rw & REQ_SYNC) &&
@@ -4689,10 +4699,10 @@ static void make_request(struct mddev *m
} else {
/* cannot get stripe for read-ahead, just give-up */
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- finish_wait(&conf->wait_for_overlap, &w);
break;
}
}
+ finish_wait(&conf->wait_for_overlap, &w);
remaining = raid5_dec_bi_active_stripes(bi);
if (remaining == 0) {
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
