diff options
author | Bernd Schubert <bernd-schubert@gmx.de> | 2008-05-23 16:04:34 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-05-24 12:56:10 -0400 |
commit | 6be9d4940134b36f9ed020aead36f831f19b49f1 (patch) | |
tree | af74a03897cc8ee2ce4ae68a82a18f1d86d34f31 | |
parent | 6bcfd601861cce45ca73ac1d714f1286b6b3f0d4 (diff) |
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 93fde48c0f42..2f28745dacf9 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c | |||
@@ -94,6 +94,8 @@ | |||
94 | #define __inline__ | 94 | #define __inline__ |
95 | #endif | 95 | #endif |
96 | 96 | ||
97 | #define printk_rl(args...) ((void) (printk_ratelimit() && printk(args))) | ||
98 | |||
97 | #if !RAID6_USE_EMPTY_ZERO_PAGE | 99 | #if !RAID6_USE_EMPTY_ZERO_PAGE |
98 | /* In .bss so it's zeroed */ | 100 | /* In .bss so it's zeroed */ |
99 | const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256))); | 101 | 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) | |||
1143 | set_bit(R5_UPTODATE, &sh->dev[i].flags); | 1145 | set_bit(R5_UPTODATE, &sh->dev[i].flags); |
1144 | if (test_bit(R5_ReadError, &sh->dev[i].flags)) { | 1146 | if (test_bit(R5_ReadError, &sh->dev[i].flags)) { |
1145 | rdev = conf->disks[i].rdev; | 1147 | rdev = conf->disks[i].rdev; |
1146 | printk(KERN_INFO "raid5:%s: read error corrected (%lu sectors at %llu on %s)\n", | 1148 | printk_rl(KERN_INFO "raid5:%s: read error corrected" |
1147 | mdname(conf->mddev), STRIPE_SECTORS, | 1149 | " (%lu sectors at %llu on %s)\n", |
1148 | (unsigned long long)(sh->sector + rdev->data_offset), | 1150 | mdname(conf->mddev), STRIPE_SECTORS, |
1149 | bdevname(rdev->bdev, b)); | 1151 | (unsigned long long)(sh->sector |
1152 | + rdev->data_offset), | ||
1153 | bdevname(rdev->bdev, b)); | ||
1150 | clear_bit(R5_ReadError, &sh->dev[i].flags); | 1154 | clear_bit(R5_ReadError, &sh->dev[i].flags); |
1151 | clear_bit(R5_ReWrite, &sh->dev[i].flags); | 1155 | clear_bit(R5_ReWrite, &sh->dev[i].flags); |
1152 | } | 1156 | } |
@@ -1160,16 +1164,22 @@ static void raid5_end_read_request(struct bio * bi, int error) | |||
1160 | clear_bit(R5_UPTODATE, &sh->dev[i].flags); | 1164 | clear_bit(R5_UPTODATE, &sh->dev[i].flags); |
1161 | atomic_inc(&rdev->read_errors); | 1165 | atomic_inc(&rdev->read_errors); |
1162 | if (conf->mddev->degraded) | 1166 | if (conf->mddev->degraded) |
1163 | printk(KERN_WARNING "raid5:%s: read error not correctable (sector %llu on %s).\n", | 1167 | printk_rl(KERN_WARNING |
1164 | mdname(conf->mddev), | 1168 | "raid5:%s: read error not correctable " |
1165 | (unsigned long long)(sh->sector + rdev->data_offset), | 1169 | "(sector %llu on %s).\n", |
1166 | bdn); | 1170 | mdname(conf->mddev), |
1171 | (unsigned long long)(sh->sector | ||
1172 | + rdev->data_offset), | ||
1173 | bdn); | ||
1167 | else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) | 1174 | else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) |
1168 | /* Oh, no!!! */ | 1175 | /* Oh, no!!! */ |
1169 | printk(KERN_WARNING "raid5:%s: read error NOT corrected!! (sector %llu on %s).\n", | 1176 | printk_rl(KERN_WARNING |
1170 | mdname(conf->mddev), | 1177 | "raid5:%s: read error NOT corrected!! " |
1171 | (unsigned long long)(sh->sector + rdev->data_offset), | 1178 | "(sector %llu on %s).\n", |
1172 | bdn); | 1179 | mdname(conf->mddev), |
1180 | (unsigned long long)(sh->sector | ||
1181 | + rdev->data_offset), | ||
1182 | bdn); | ||
1173 | else if (atomic_read(&rdev->read_errors) | 1183 | else if (atomic_read(&rdev->read_errors) |
1174 | > conf->max_nr_stripes) | 1184 | > conf->max_nr_stripes) |
1175 | printk(KERN_WARNING | 1185 | printk(KERN_WARNING |