Commit 6be9d494 authored by Bernd Schubert's avatar Bernd Schubert Committed by Linus Torvalds
Browse files

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: default avatarBernd Schubert <bernd-schubert@gmx.de>
Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
Signed-off-by: default avatarNeil Brown <neilb@suse.de>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 6bcfd601

drivers/md/raid5.c

+22 −12
Original line number Diff line number Diff line
@@ -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)));
@@ -1143,9 +1145,11 @@ 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",

			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),

				  (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);
@@ -1160,15 +1164,21 @@ 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",

			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),

				  (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",

			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),

				  (unsigned long long)(sh->sector

						       + rdev->data_offset),

				  bdn);

		else if (atomic_read(&rdev->read_errors)

			 > conf->max_nr_stripes)

CRA Git | Maintained and supported by SUSTech CRA and CCSE