xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

md/r5cache: disable write back for degraded array

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

46
drivers/md/raid5-cache.c
View File

@@ -162,6 +162,8 @@ struct r5l_log {
/* to submit async io_units, to fulfill ordering of flush */
struct work_struct deferred_io_work;
/* to disable write back during in degraded mode */
struct work_struct disable_writeback_work;
};
/*
@@ -611,6 +613,21 @@ static void r5l_submit_io_async(struct work_struct *work)
r5l_do_submit_io(log, io);
}
static void r5c_disable_writeback_async(struct work_struct *work)
{
struct r5l_log *log = container_of(work, struct r5l_log,
disable_writeback_work);
struct mddev *mddev = log->rdev->mddev;
if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH)
return;
pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n",
mdname(mddev));
mddev_suspend(mddev);
log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
mddev_resume(mddev);
}
static void r5l_submit_current_io(struct r5l_log *log)
{
struct r5l_io_unit *io = log->current_io;
@@ -2269,6 +2286,10 @@ static ssize_t r5c_journal_mode_store(struct mddev *mddev,
val > R5C_JOURNAL_MODE_WRITE_BACK)
return -EINVAL;
if (raid5_calc_degraded(conf) > 0 &&
val == R5C_JOURNAL_MODE_WRITE_BACK)
return -EINVAL;
mddev_suspend(mddev);
conf->log->r5c_journal_mode = val;
mddev_resume(mddev);
@@ -2323,6 +2344,16 @@ int r5c_try_caching_write(struct r5conf *conf,
set_bit(STRIPE_R5C_CACHING, &sh->state);
}
/*
* When run in degraded mode, array is set to write-through mode.
* This check helps drain pending write safely in the transition to
* write-through mode.
*/
if (s->failed) {
r5c_make_stripe_write_out(sh);
return -EAGAIN;
}
for (i = disks; i--; ) {
dev = &sh->dev[i];
/* if non-overwrite, use writing-out phase */
@@ -2579,6 +2610,19 @@ ioerr:
return ret;
}
void r5c_update_on_rdev_error(struct mddev *mddev)
{
struct r5conf *conf = mddev->private;
struct r5l_log *log = conf->log;
if (!log)
return;
if (raid5_calc_degraded(conf) > 0 &&
conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
schedule_work(&log->disable_writeback_work);
}
int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
{
struct request_queue *q = bdev_get_queue(rdev->bdev);
@@ -2651,6 +2695,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
spin_lock_init(&log->no_space_stripes_lock);
INIT_WORK(&log->deferred_io_work, r5l_submit_io_async);
INIT_WORK(&log->disable_writeback_work, r5c_disable_writeback_async);
log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
INIT_LIST_HEAD(&log->stripe_in_journal_list);
@@ -2683,6 +2728,7 @@ io_kc:
void r5l_exit_log(struct r5l_log *log)
{
flush_work(&log->disable_writeback_work);
md_unregister_thread(&log->reclaim_thread);
mempool_destroy(log->meta_pool);
bioset_free(log->bs);