From: Bernd Schubert <bernd-schubert@xxxxxx>
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@xxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Signed-off-by: Neil Brown <neilb@xxxxxxx>
### Diffstat output
./drivers/md/raid5.c | 27 +++++++++++++++------------
./include/linux/raid/md_k.h | 3 +++
2 files changed, 18 insertions(+), 12 deletions(-)
diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
--- .prev/drivers/md/raid5.c 2008-04-29 12:27:50.000000000 +1000
+++ ./drivers/md/raid5.c 2008-04-29 12:27:58.000000000 +1000
@@ -1143,10 +1143,11 @@ static void raid5_end_read_request(struc
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 +1161,18 @@ static void raid5_end_read_request(struc
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
diff .prev/include/linux/raid/md_k.h ./include/linux/raid/md_k.h
--- .prev/include/linux/raid/md_k.h 2008-04-29 12:25:24.000000000 +1000
+++ ./include/linux/raid/md_k.h 2008-04-29 12:27:58.000000000 +1000
@@ -368,6 +368,9 @@ static inline void safe_put_page(struct
if (p) put_page(p);
}
+#define printk_rl printk_ratelimit() ?: printk
+
+
#endif /* CONFIG_BLOCK */
#endif
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
