From cbd1998377504df005302ac90d49db72a48552a6 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 30 Dec 2009 12:08:49 +1100 Subject: md: Fix unfortunate interaction with evms evms configures md arrays by: open device send ioctl close device for each different ioctl needed. Since 2.6.29, the device can disappear after the 'close' unless a significant configuration has happened to the device. The change made by "SET_ARRAY_INFO" can too minor to stop the device from disappearing, but important enough that losing the change is bad. So: make sure SET_ARRAY_INFO sets mddev->ctime, and keep the device active as long as ctime is non-zero (it gets zeroed with lots of other things when the array is stopped). This is suitable for -stable kernels since 2.6.29. Signed-off-by: NeilBrown Cc: stable@kernel.org --- drivers/md/md.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index f4f5f82f9f5..7862231a075 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -386,7 +386,9 @@ static void mddev_put(mddev_t *mddev) if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock)) return; if (!mddev->raid_disks && list_empty(&mddev->disks) && - !mddev->hold_active) { + mddev->ctime == 0 && !mddev->hold_active) { + /* Array is not configured at all, and not held active, + * so destroy it */ list_del(&mddev->all_mddevs); if (mddev->gendisk) { /* we did a probe so need to clean up. @@ -5262,6 +5264,10 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info) mddev->minor_version = info->minor_version; mddev->patch_version = info->patch_version; mddev->persistent = !info->not_persistent; + /* ensure mddev_put doesn't delete this now that there + * is some minimal configuration. + */ + mddev->ctime = get_seconds(); return 0; } mddev->major_version = MD_MAJOR_VERSION; -- cgit v1.2.3-70-g09d2 From 0f9552b5dc4fe10da37fa3f4a4ca185d90fa41c9 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 30 Dec 2009 12:08:50 +1100 Subject: md: fix small irregularity with start_ro module parameter The start_ro modules parameter can be used to force arrays to be started in 'auto-readonly' in which they are read-only until the first write. This ensures that no resync/recovery happens until something else writes to the device. This is important for resume-from-disk off an md array. However if an array is started 'readonly' (by writing 'readonly' to the 'array_state' sysfs attribute) we want it to be really 'readonly', not 'auto-readonly'. So strengthen the condition to only set auto-readonly if the array is not already read-only. Signed-off-by: NeilBrown --- drivers/md/md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index 7862231a075..d2aff720907 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4357,7 +4357,7 @@ static int do_md_run(mddev_t * mddev) mddev->barriers_work = 1; mddev->ok_start_degraded = start_dirty_degraded; - if (start_readonly) + if (start_readonly && mddev->ro == 0) mddev->ro = 2; /* read-only, but switch on first write */ err = mddev->pers->run(mddev); -- cgit v1.2.3-70-g09d2 From a2d79c324ac0c26ae9995a312a7731067a7f01fc Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 21 Dec 2009 18:18:36 -0700 Subject: md: make recovery started by do_md_run() visible via sync_action By default md_do_sync() will perform recovery if no other actions are specified. However, action_show() relies on MD_RECOVERY_RECOVER to be set otherwise it returns 'idle'. So, add a missing set MD_RECOVERY_RECOVER when starting recovery. Signed-off-by: Dan Williams Signed-off-by: NeilBrown --- drivers/md/md.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index d2aff720907..fd55f2a555b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4436,6 +4436,7 @@ static int do_md_run(mddev_t * mddev) if (spares && mddev->pers->sync_request) { mddev->recovery = 0; set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); mddev->sync_thread = md_register_thread(md_do_sync, mddev, "resync"); -- cgit v1.2.3-70-g09d2 From 7fb9dadc91948ddd16d1d32e414b5e71ec63b97b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 30 Dec 2009 15:19:08 +1100 Subject: md: remove unnecessary code from do_md_run Since commit dfc7064500061677720fa26352963c772d3ebe6b, ->hot_remove_disks has not removed non-failed devices from an array until recovery is no longer possible. So the code in do_md_run to get around the fact that md_check_recovery (which calls ->hot_remove_disks) would remove partially-in-sync devices is no longer needed. So remove it. Signed-off-by: NeilBrown --- drivers/md/md.c | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index fd55f2a555b..c4bdf060175 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4421,34 +4421,6 @@ static int do_md_run(mddev_t * mddev) set_capacity(disk, mddev->array_sectors); - /* If there is a partially-recovered drive we need to - * start recovery here. If we leave it to md_check_recovery, - * it will remove the drives and not do the right thing - */ - if (mddev->degraded && !mddev->sync_thread) { - int spares = 0; - list_for_each_entry(rdev, &mddev->disks, same_set) - if (rdev->raid_disk >= 0 && - !test_bit(In_sync, &rdev->flags) && - !test_bit(Faulty, &rdev->flags)) - /* complete an interrupted recovery */ - spares++; - if (spares && mddev->pers->sync_request) { - mddev->recovery = 0; - set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, - mddev, - "resync"); - if (!mddev->sync_thread) { - printk(KERN_ERR "%s: could not start resync" - " thread...\n", - mdname(mddev)); - /* leave the spares where they are, it shouldn't hurt */ - mddev->recovery = 0; - } - } - } md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ -- cgit v1.2.3-70-g09d2 From 404e4b43fdd6daa7b4a9f81bc7e4358281d763fa Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 30 Dec 2009 15:25:23 +1100 Subject: md: allow a resync that is waiting for other resync to complete, to be aborted. If two arrays share a device, then they will not both resync at the same time. One will wait for the other to complete. While waiting, the MD_RECOVERY_INTR flag is not checked so a device failure, which would make the resync pointless, does not cause the resync to abort, so the failed device cannot be removed (as it cannot be remove while a resync is happening). So add a test for MD_RECOVERY_INTR. Reported-by: Brett Russ Signed-off-by: NeilBrown --- drivers/md/md.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index c4bdf060175..dd3dfe42d5a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6473,10 +6473,11 @@ void md_do_sync(mddev_t *mddev) mddev->curr_resync = 2; try_again: - if (kthread_should_stop()) { + if (kthread_should_stop()) set_bit(MD_RECOVERY_INTR, &mddev->recovery); + + if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) goto skip; - } for_each_mddev(mddev2, tmp) { if (mddev2 == mddev) continue; -- cgit v1.2.3-70-g09d2