From a8d5fdd4d2702d0c7ec125bd3bbce3fc589afa67 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Wed, 21 Jun 2023 18:57:28 +0800 Subject: [PATCH] raid10: avoid spin_lock from fastpath from raid10_unplug() Commit 0c0be98bbe67 ("md/raid10: prevent unnecessary calls to wake_up() in fast path") missed one place, for example, with: fio -direct=1 -rw=write/randwrite -iodepth=1 ... Plug and unplug are called for each io, then wake_up() from raid10_unplug() will cause lock contention as well. Avoid this contention by using wake_up_barrier() instead of wake_up(), where spin_lock is not held if waitqueue is empty. Fio test script: [global] name=random reads and writes ioengine=libaio direct=1 readwrite=randrw rwmixread=70 iodepth=64 buffered=0 filename=/dev/md0 size=1G runtime=30 time_based randrepeat=0 norandommap refill_buffers ramp_time=10 bs=4k numjobs=400 group_reporting=1 [job1] Test result with ramdisk raid10(By Ali): Before this patch With this patch READ IOPS=2033k IOPS=3642k WRITE IOPS=871k IOPS=1561K By the way, in this scenario, blk_plug_cb() will be allocated and freed for each io, this seems need to be optimized as well. Reported-and-tested-by: Ali Gholami Rudi Closes: https://lore.kernel.org/all/20231606122233@laper.mirepesht/ Signed-off-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230621105728.1268542-1-yukuai1@huaweicloud.com --- drivers/md/raid10.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 7906776..5051149 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1118,7 +1118,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); spin_unlock_irq(&conf->device_lock); - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); md_wakeup_thread(mddev->thread); kfree(plug); return; @@ -1127,7 +1127,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) /* we aren't scheduling, so we can do the write-out directly. */ bio = bio_list_get(&plug->pending); raid1_prepare_flush_writes(mddev->bitmap); - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; -- 2.7.4