md/r5cache: disable write back for degraded array

write-back cache in degraded mode introduces corner cases to the array.
Although we try to cover all these corner cases, it is safer to just
disable write-back cache when the array is in degraded mode.

In this patch, we disable writeback cache for degraded mode:
1. On device failure, if the array enters degraded mode, raid5_error()
   will submit async job r5c_disable_writeback_async to disable
   writeback;
2. In r5c_journal_mode_store(), it is invalid to enable writeback in
   degraded mode;
3. In r5c_try_caching_write(), stripes with s->failed>0 will be handled
   in write-through mode.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
This commit is contained in:
Song Liu
2017-01-24 10:45:30 -08:00
committed by Shaohua Li
parent 07e8336484
commit 2e38a37f23
3 changed files with 56 additions and 7 deletions

View File

@@ -556,7 +556,7 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
* of the two sections, and some non-in_sync devices may
* be insync in the section most affected by failed devices.
*/
static int calc_degraded(struct r5conf *conf)
int raid5_calc_degraded(struct r5conf *conf)
{
int degraded, degraded2;
int i;
@@ -619,7 +619,7 @@ static int has_failed(struct r5conf *conf)
if (conf->mddev->reshape_position == MaxSector)
return conf->mddev->degraded > conf->max_degraded;
degraded = calc_degraded(conf);
degraded = raid5_calc_degraded(conf);
if (degraded > conf->max_degraded)
return 1;
return 0;
@@ -2555,7 +2555,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
spin_lock_irqsave(&conf->device_lock, flags);
clear_bit(In_sync, &rdev->flags);
mddev->degraded = calc_degraded(conf);
mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
@@ -2569,6 +2569,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
bdevname(rdev->bdev, b),
mdname(mddev),
conf->raid_disks - mddev->degraded);
r5c_update_on_rdev_error(mddev);
}
/*
@@ -7091,7 +7092,7 @@ static int raid5_run(struct mddev *mddev)
/*
* 0 for a fully functional array, 1 or 2 for a degraded array.
*/
mddev->degraded = calc_degraded(conf);
mddev->degraded = raid5_calc_degraded(conf);
if (has_failed(conf)) {
pr_crit("md/raid:%s: not enough operational devices (%d/%d failed)\n",
@@ -7338,7 +7339,7 @@ static int raid5_spare_active(struct mddev *mddev)
}
}
spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded = calc_degraded(conf);
mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
print_raid5_conf(conf);
return count;
@@ -7698,7 +7699,7 @@ static int raid5_start_reshape(struct mddev *mddev)
* pre and post number of devices.
*/
spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded = calc_degraded(conf);
mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
mddev->raid_disks = conf->raid_disks;
@@ -7786,7 +7787,7 @@ static void raid5_finish_reshape(struct mddev *mddev)
} else {
int d;
spin_lock_irq(&conf->device_lock);
mddev->degraded = calc_degraded(conf);
mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irq(&conf->device_lock);
for (d = conf->raid_disks ;
d < conf->raid_disks - mddev->delta_disks;