From 6be9d4940134b36f9ed020aead36f831f19b49f1 Mon Sep 17 00:00:00 2001 From: Bernd Schubert Date: Fri, 23 May 2008 13:04:34 -0700 Subject: md: md: raid5 rate limit error printk Last night we had scsi problems and a hardware raid unit was offlined during heavy i/o. While this happened we got for about 3 minutes a huge number messages like these Apr 12 03:36:07 pfs1n14 kernel: [197510.696595] raid5:md7: read error not correctable (sector 2993096568 on sdj2). I guess the high error rate is responsible for not scheduling other events - during this time the system was not pingable and in the end also other devices run into scsi command timeouts causing problems on these unrelated devices as well. Signed-off-by: Bernd Schubert Signed-off-by: Dan Williams Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/raid5.c | 34 ++++++++++++++++++++++------------ 1 file changed, 22 insertions(+), 12 deletions(-) (limited to 'drivers/md/raid5.c') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 93fde48c0f42..2f28745dacf9 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -94,6 +94,8 @@ #define __inline__ #endif +#define printk_rl(args...) ((void) (printk_ratelimit() && printk(args))) + #if !RAID6_USE_EMPTY_ZERO_PAGE /* In .bss so it's zeroed */ const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256))); @@ -1143,10 +1145,12 @@ static void raid5_end_read_request(struct bio * bi, int error) set_bit(R5_UPTODATE, &sh->dev[i].flags); if (test_bit(R5_ReadError, &sh->dev[i].flags)) { rdev = conf->disks[i].rdev; - printk(KERN_INFO "raid5:%s: read error corrected (%lu sectors at %llu on %s)\n", - mdname(conf->mddev), STRIPE_SECTORS, - (unsigned long long)(sh->sector + rdev->data_offset), - bdevname(rdev->bdev, b)); + printk_rl(KERN_INFO "raid5:%s: read error corrected" + " (%lu sectors at %llu on %s)\n", + mdname(conf->mddev), STRIPE_SECTORS, + (unsigned long long)(sh->sector + + rdev->data_offset), + bdevname(rdev->bdev, b)); clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); } @@ -1160,16 +1164,22 @@ static void raid5_end_read_request(struct bio * bi, int error) clear_bit(R5_UPTODATE, &sh->dev[i].flags); atomic_inc(&rdev->read_errors); if (conf->mddev->degraded) - printk(KERN_WARNING "raid5:%s: read error not correctable (sector %llu on %s).\n", - mdname(conf->mddev), - (unsigned long long)(sh->sector + rdev->data_offset), - bdn); + printk_rl(KERN_WARNING + "raid5:%s: read error not correctable " + "(sector %llu on %s).\n", + mdname(conf->mddev), + (unsigned long long)(sh->sector + + rdev->data_offset), + bdn); else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) /* Oh, no!!! */ - printk(KERN_WARNING "raid5:%s: read error NOT corrected!! (sector %llu on %s).\n", - mdname(conf->mddev), - (unsigned long long)(sh->sector + rdev->data_offset), - bdn); + printk_rl(KERN_WARNING + "raid5:%s: read error NOT corrected!! " + "(sector %llu on %s).\n", + mdname(conf->mddev), + (unsigned long long)(sh->sector + + rdev->data_offset), + bdn); else if (atomic_read(&rdev->read_errors) > conf->max_nr_stripes) printk(KERN_WARNING -- cgit v1.2.2 From dfc7064500061677720fa26352963c772d3ebe6b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 23 May 2008 13:04:39 -0700 Subject: md: restart recovery cleanly after device failure. When we get any IO error during a recovery (rebuilding a spare), we abort the recovery and restart it. For RAID6 (and multi-drive RAID1) it may not be best to restart at the beginning: when multiple failures can be tolerated, the recovery may be able to continue and re-doing all that has already been done doesn't make sense. We already have the infrastructure to record where a recovery is up to and restart from there, but it is not being used properly. This is because: - We sometimes abort with MD_RECOVERY_ERR rather than just MD_RECOVERY_INTR, which causes the recovery not be be checkpointed. - We remove spares and then re-added them which loses important state information. The distinction between MD_RECOVERY_ERR and MD_RECOVERY_INTR really isn't needed. If there is an error, the relevant drive will be marked as Faulty, and that is enough to ensure correct handling of the error. So we first remove MD_RECOVERY_ERR, changing some of the uses of it to MD_RECOVERY_INTR. Then we cause the attempt to remove a non-faulty device from an array to fail (unless recovery is impossible as the array is too degraded). Then when remove_and_add_spares attempts to remove the devices on which recovery can continue, it will fail, they will remain in place, and recovery will continue on them as desired. Issue: If we are halfway through rebuilding a spare and another drive fails, and a new spare is immediately available, do we want to: 1/ complete the current rebuild, then go back and rebuild the new spare or 2/ restart the rebuild from the start and rebuild both devices in parallel. Both options can be argued for. The code currently takes option 2 as a/ this requires least code change b/ this results in a minimally-degraded array in minimal time. Cc: "Eivind Sarto" Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/raid5.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'drivers/md/raid5.c') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2f28745dacf9..425958a76b84 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1268,7 +1268,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) /* * if recovery was running, make sure it aborts. */ - set_bit(MD_RECOVERY_ERR, &mddev->recovery); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); } set_bit(Faulty, &rdev->flags); printk (KERN_ALERT @@ -4574,6 +4574,14 @@ static int raid5_remove_disk(mddev_t *mddev, int number) err = -EBUSY; goto abort; } + /* Only remove non-faulty devices if recovery + * isn't possible. + */ + if (!test_bit(Faulty, &rdev->flags) && + mddev->degraded <= conf->max_degraded) { + err = -EBUSY; + goto abort; + } p->rdev = NULL; synchronize_rcu(); if (atomic_read(&rdev->nr_pending)) { -- cgit v1.2.2