From mboxrd@z Thu Jan 1 00:00:00 1970 From: Shaohua Li Subject: [patch 01/10 v3] raid5: use wake_up_all for overlap waking Date: Mon, 25 Jun 2012 15:24:48 +0800 Message-ID: <20120625072553.970838108@kernel.org> References: <20120625072447.268095276@kernel.org> Return-path: Content-Disposition: inline; filename=raid5-wakeupall.patch Sender: linux-raid-owner@vger.kernel.org To: linux-raid@vger.kernel.org Cc: neilb@suse.de, axboe@kernel.dk, dan.j.williams@intel.com, shli@fusionio.com List-Id: linux-raid.ids It's possible several tasks are waiting for stripe overlap. We clear R5_Overlap bit and wake_up, but wake_up just wakes one task. So if there are several tasks in the wait queue, some tasks will not be woken up even its strip R5_Overlap clear. The end result is tasks hang in make_request. wake_up_all should not introduce performance issue here, since overlap case is rare. Signed-off-by: Shaohua Li --- drivers/md/raid5.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) Index: linux/drivers/md/raid5.c =================================================================== --- linux.orig/drivers/md/raid5.c 2012-06-19 08:11:10.021688417 +0800 +++ linux/drivers/md/raid5.c 2012-06-19 08:11:29.833439339 +0800 @@ -1399,7 +1399,7 @@ static void __raid_run_ops(struct stripe for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (test_and_clear_bit(R5_Overlap, &dev->flags)) - wake_up(&sh->raid_conf->wait_for_overlap); + wake_up_all(&sh->raid_conf->wait_for_overlap); } put_cpu(); } @@ -2436,7 +2436,7 @@ handle_failed_stripe(struct r5conf *conf } if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) { @@ -2474,7 +2474,7 @@ handle_failed_stripe(struct r5conf *conf bi = sh->dev[i].toread; sh->dev[i].toread = NULL; if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); if (bi) s->to_read--; while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) { @@ -3572,7 +3572,7 @@ static void handle_stripe(struct stripe_ } else if (s.expanded && !sh->reconstruct_state && s.locked == 0) { clear_bit(STRIPE_EXPAND_READY, &sh->state); atomic_dec(&conf->reshape_stripes); - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); md_done_sync(conf->mddev, STRIPE_SECTORS, 1); } @@ -4249,7 +4249,7 @@ static sector_t reshape_request(struct m spin_lock_irq(&conf->device_lock); conf->reshape_safe = mddev->reshape_position; spin_unlock_irq(&conf->device_lock); - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } @@ -4340,7 +4340,7 @@ static sector_t reshape_request(struct m spin_lock_irq(&conf->device_lock); conf->reshape_safe = mddev->reshape_position; spin_unlock_irq(&conf->device_lock); - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } return reshape_sectors; @@ -5718,7 +5718,7 @@ static void end_reshape(struct r5conf *c smp_wmb(); conf->reshape_progress = MaxSector; spin_unlock_irq(&conf->device_lock); - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); /* read-ahead size must cover two whole stripes, which is * 2 * (datadisks) * chunksize where 'n' is the number of raid devices @@ -5776,7 +5776,7 @@ static void raid5_quiesce(struct mddev * switch(state) { case 2: /* resume for a suspend */ - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); break; case 1: /* stop all writes */ @@ -5792,14 +5792,14 @@ static void raid5_quiesce(struct mddev * conf->quiesce = 1; spin_unlock_irq(&conf->device_lock); /* allow reshape to continue */ - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); break; case 0: /* re-enable writes */ spin_lock_irq(&conf->device_lock); conf->quiesce = 0; wake_up(&conf->wait_for_stripe); - wake_up(&conf->wait_for_overlap); + wake_up_all(&conf->wait_for_overlap); spin_unlock_irq(&conf->device_lock); break; }