From 19052c0e85a3e9d3b7d190b29fcdbf0e6c105381 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 5 Aug 2008 15:54:13 +1000 Subject: Make writes to md/safe_mode_delay immediately effective. If we reduce the 'safe_mode_delay', it could still wait for the old delay to completely expire before doing anything about safe_mode. Thus the effect if the change is delayed. To make the effect more immediate, run the timeout function immediately if the delay was reduced. This may cause it to run slightly earlier that required, but that is the safer option. Signed-off-by: NeilBrown --- drivers/md/md.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index c7aae66c6f9b..48afe4f7ad4c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2393,6 +2393,8 @@ static void analyze_sbs(mddev_t * mddev) } +static void md_safemode_timeout(unsigned long data); + static ssize_t safe_delay_show(mddev_t *mddev, char *page) { @@ -2432,9 +2434,12 @@ safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len) if (msec == 0) mddev->safemode_delay = 0; else { + unsigned long old_delay = mddev->safemode_delay; mddev->safemode_delay = (msec*HZ)/1000; if (mddev->safemode_delay == 0) mddev->safemode_delay = 1; + if (mddev->safemode_delay < old_delay) + md_safemode_timeout((unsigned long)mddev); } return len; } -- cgit v1.2.3 From 2b25000bf5157c28d8591f03f0575248a8cbd900 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 5 Aug 2008 15:54:13 +1000 Subject: Restore force switch of md array to readonly at reboot time. A recent patch allowed do_md_stop to know whether it was being called via an ioctl or not, and thus where to allow for an extra open file descriptor when checking if it is in use. This broke then switch to readonly performed by the shutdown notifier, which needs to work even when the array is still (apparently) active (as md doesn't get told when the filesystem becomes readonly). So restore this feature by pretending that there can be lots of file descriptors open, but we still want do_md_stop to switch to readonly. Signed-off-by: NeilBrown --- drivers/md/md.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 48afe4f7ad4c..8d11cd1a0d8b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6237,7 +6237,11 @@ static int md_notify_reboot(struct notifier_block *this, for_each_mddev(mddev, tmp) if (mddev_trylock(mddev)) { - do_md_stop (mddev, 1, 0); + /* Force a switch to readonly even array + * appears to still be in use. Hence + * the '100'. + */ + do_md_stop (mddev, 1, 100); mddev_unlock(mddev); } /* -- cgit v1.2.3 From dba034eef2456d2a9f9a76806846c97acf6c3ad1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 5 Aug 2008 15:54:13 +1000 Subject: Fail safely when trying to grow an array with a write-intent bitmap. We cannot currently change the size of a write-intent bitmap. So if we change the size of an array which has such a bitmap, it tries to set bits beyond the end of the bitmap. For now, simply reject any request to change the size of an array which has a bitmap. mdadm can remove the bitmap and add a new one after the array has changed size. Signed-off-by: NeilBrown --- drivers/md/md.c | 5 +++++ drivers/md/raid5.c | 3 +++ 2 files changed, 8 insertions(+) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 8d11cd1a0d8b..6eb95451f161 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4639,6 +4639,11 @@ static int update_size(mddev_t *mddev, sector_t num_sectors) */ if (mddev->sync_thread) return -EBUSY; + if (mddev->bitmap) + /* Sorry, cannot grow a bitmap yet, just remove it, + * grow, and re-add. + */ + return -EBUSY; rdev_for_each(rdev, tmp, mddev) { sector_t avail; avail = rdev->size * 2; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 40e939675657..17e0953c3c06 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4446,6 +4446,9 @@ static int raid5_check_reshape(mddev_t *mddev) return -EINVAL; /* Cannot shrink array or change level yet */ if (mddev->delta_disks == 0) return 0; /* nothing to do */ + if (mddev->bitmap) + /* Cannot grow a bitmap yet */ + return -EBUSY; /* Can only proceed if there are plenty of stripe_heads. * We need a minimum of one full stripe,, and for sensible progress -- cgit v1.2.3 From c89a8eee61540df04fc83f32f51ef0f46ec018b1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 5 Aug 2008 15:54:13 +1000 Subject: Allow faulty devices to be removed from a readonly array. Removing faulty devices from an array is a two stage process. First the device is moved from being a part of the active array to being similar to a spare device. Then it can be removed by a request from user space. The first step is currently not performed for read-only arrays, so the second step can never succeed. So allow readonly arrays to remove failed devices (which aren't blocked). Signed-off-by: NeilBrown --- drivers/md/md.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 6eb95451f161..25b893ec562e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6003,7 +6003,7 @@ static int remove_and_add_spares(mddev_t *mddev) } } - if (mddev->degraded) { + if (mddev->degraded && ! mddev->ro) { rdev_for_each(rdev, rtmp, mddev) { if (rdev->raid_disk >= 0 && !test_bit(In_sync, &rdev->flags) && @@ -6077,6 +6077,8 @@ void md_check_recovery(mddev_t *mddev) flush_signals(current); } + if (mddev->ro && !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) + return; if ( ! ( (mddev->flags && !mddev->external) || test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) || @@ -6090,6 +6092,15 @@ void md_check_recovery(mddev_t *mddev) if (mddev_trylock(mddev)) { int spares = 0; + if (mddev->ro) { + /* Only thing we do on a ro array is remove + * failed devices. + */ + remove_and_add_spares(mddev); + clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + goto unlock; + } + if (!mddev->external) { int did_change = 0; spin_lock_irq(&mddev->write_lock); -- cgit v1.2.3 From 56ac36d722d0d27c03599d1245ac0ab59e474e5c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 7 Aug 2008 10:02:47 -0700 Subject: md: cancel check/repair requests when recovery is needed If a 'repair' is requested when an array is in a position to 'recover' raid1 will perform the repair while md believes a recovery is happening. Address this at both ends, i.e. cancel check/repair requests upon detecting a recover condition and do not call ->spare_active after completing a check/repair. Signed-off-by: Dan Williams --- drivers/md/md.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 25b893ec562e..8cfadc5bd2ba 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6138,7 +6138,8 @@ void md_check_recovery(mddev_t *mddev) /* resync has finished, collect result */ md_unregister_thread(mddev->sync_thread); mddev->sync_thread = NULL; - if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { + if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && + !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { /* success...*/ /* activate any spares */ if (mddev->pers->spare_active(mddev)) @@ -6190,6 +6191,7 @@ void md_check_recovery(mddev_t *mddev) } else if ((spares = remove_and_add_spares(mddev))) { clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); + clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); } else if (mddev->recovery_cp < MaxSector) { set_bit(MD_RECOVERY_SYNC, &mddev->recovery); -- cgit v1.2.3