Commit 0f0709e6 authored by Coly Li's avatar Coly Li Committed by Jens Axboe

bcache: stop bcache device when backing device is offline

Currently bcache does not handle backing device failure, if backing
device is offline and disconnected from system, its bcache device can still
be accessible. If the bcache device is in writeback mode, I/O requests even
can success if the requests hit on cache device. That is to say, when and
how bcache handles offline backing device is undefined.

This patch tries to handle backing device offline in a rather simple way,
- Add cached_dev->status_update_thread kernel thread to update backing
  device status in every 1 second.
- Add cached_dev->offline_seconds to record how many seconds the backing
  device is observed to be offline. If the backing device is offline for
  BACKING_DEV_OFFLINE_TIMEOUT (30) seconds, set dc->io_disable to 1 and
  call bcache_device_stop() to stop the bache device which linked to the
  offline backing device.

Now if a backing device is offline for BACKING_DEV_OFFLINE_TIMEOUT seconds,
its bcache device will be removed, then user space application writing on
it will get error immediately, and handler the device failure in time.

This patch is quite simple, does not handle more complicated situations.
Once the bcache device is stopped, users need to recovery the backing
device, register and attach it manually.

Changelog:
v3: call wait_for_kthread_stop() before exits kernel thread.
v2: remove "bcache: " prefix when calling pr_warn().
v1: initial version.
Signed-off-by: default avatarColy Li <colyli@suse.de>
Reviewed-by: default avatarHannes Reinecke <hare@suse.com>
Cc: Michael Lyle <mlyle@lyle.org>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 6723d8dc
......@@ -345,6 +345,7 @@ struct cached_dev {
struct keybuf writeback_keys;
struct task_struct *status_update_thread;
/*
* Order the write-half of writeback operations strongly in dispatch
* order. (Maintain LBA order; don't allow reads completing out of
......@@ -392,6 +393,7 @@ struct cached_dev {
#define DEFAULT_CACHED_DEV_ERROR_LIMIT 64
atomic_t io_errors;
unsigned error_limit;
unsigned offline_seconds;
char backing_dev_name[BDEVNAME_SIZE];
};
......
......@@ -654,6 +654,11 @@ static int ioctl_dev(struct block_device *b, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct bcache_device *d = b->bd_disk->private_data;
struct cached_dev *dc = container_of(d, struct cached_dev, disk);
if (dc->io_disable)
return -EIO;
return d->ioctl(d, mode, cmd, arg);
}
......@@ -864,6 +869,44 @@ static void calc_cached_dev_sectors(struct cache_set *c)
c->cached_dev_sectors = sectors;
}
#define BACKING_DEV_OFFLINE_TIMEOUT 5
static int cached_dev_status_update(void *arg)
{
struct cached_dev *dc = arg;
struct request_queue *q;
/*
* If this delayed worker is stopping outside, directly quit here.
* dc->io_disable might be set via sysfs interface, so check it
* here too.
*/
while (!kthread_should_stop() && !dc->io_disable) {
q = bdev_get_queue(dc->bdev);
if (blk_queue_dying(q))
dc->offline_seconds++;
else
dc->offline_seconds = 0;
if (dc->offline_seconds >= BACKING_DEV_OFFLINE_TIMEOUT) {
pr_err("%s: device offline for %d seconds",
dc->backing_dev_name,
BACKING_DEV_OFFLINE_TIMEOUT);
pr_err("%s: disable I/O request due to backing "
"device offline", dc->disk.name);
dc->io_disable = true;
/* let others know earlier that io_disable is true */
smp_mb();
bcache_device_stop(&dc->disk);
break;
}
schedule_timeout_interruptible(HZ);
}
wait_for_kthread_stop();
return 0;
}
void bch_cached_dev_run(struct cached_dev *dc)
{
struct bcache_device *d = &dc->disk;
......@@ -906,6 +949,14 @@ void bch_cached_dev_run(struct cached_dev *dc)
if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache"))
pr_debug("error creating sysfs link");
dc->status_update_thread = kthread_run(cached_dev_status_update,
dc, "bcache_status_update");
if (IS_ERR(dc->status_update_thread)) {
pr_warn("failed to create bcache_status_update kthread, "
"continue to run without monitoring backing "
"device status");
}
}
/*
......@@ -1139,6 +1190,8 @@ static void cached_dev_free(struct closure *cl)
kthread_stop(dc->writeback_thread);
if (dc->writeback_write_wq)
destroy_workqueue(dc->writeback_write_wq);
if (!IS_ERR_OR_NULL(dc->status_update_thread))
kthread_stop(dc->status_update_thread);
if (atomic_read(&dc->running))
bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment