diff options
| author | Bernd Schubert <bernd-schubert@gmx.de> | 2008-05-23 13:04:34 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-05-24 09:56:10 -0700 |
| commit | 6be9d4940134b36f9ed020aead36f831f19b49f1 (patch) | |
| tree | af74a03897cc8ee2ce4ae68a82a18f1d86d34f31 | |
| parent | 6bcfd601861cce45ca73ac1d714f1286b6b3f0d4 (diff) | |
| download | linux-3.10-6be9d4940134b36f9ed020aead36f831f19b49f1.tar.gz linux-3.10-6be9d4940134b36f9ed020aead36f831f19b49f1.tar.bz2 linux-3.10-6be9d4940134b36f9ed020aead36f831f19b49f1.zip | |
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 <bernd-schubert@gmx.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
| -rw-r--r-- | drivers/md/raid5.c | 34 |
1 files changed, 22 insertions, 12 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 93fde48c0f4..2f28745dacf 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 |