bdev_get_integrity(reference->bdev));
pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
- if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) {
+ if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) ||
+ bioset_integrity_create(&mddev->io_acct_set, BIO_POOL_SIZE)) {
pr_err("md: failed to create integrity pool for %s\n",
mdname(mddev));
return -EINVAL;
bioset_exit(&mddev->bio_set);
bioset_exit(&mddev->sync_set);
+ bioset_exit(&mddev->io_acct_set);
kfree(mddev);
}
if (!bioset_initialized(&mddev->sync_set)) {
err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (err)
- return err;
+ goto exit_bio_set;
+ }
+ if (!bioset_initialized(&mddev->io_acct_set)) {
+ err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE,
+ offsetof(struct md_io_acct, bio_clone), 0);
+ if (err)
+ goto exit_sync_set;
}
spin_lock(&pers_lock);
blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
else
blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
+ blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);
}
if (pers->sync_request) {
if (mddev->kobj.sd &&
module_put(pers->owner);
md_bitmap_destroy(mddev);
abort:
- bioset_exit(&mddev->bio_set);
+ bioset_exit(&mddev->io_acct_set);
+exit_sync_set:
bioset_exit(&mddev->sync_set);
+exit_bio_set:
+ bioset_exit(&mddev->bio_set);
return err;
}
EXPORT_SYMBOL_GPL(md_run);
__md_stop(mddev);
bioset_exit(&mddev->bio_set);
bioset_exit(&mddev->sync_set);
+ bioset_exit(&mddev->io_acct_set);
}
EXPORT_SYMBOL_GPL(md_stop);
}
EXPORT_SYMBOL_GPL(md_submit_discard_bio);
+static void md_end_io_acct(struct bio *bio)
+{
+ struct md_io_acct *md_io_acct = bio->bi_private;
+ struct bio *orig_bio = md_io_acct->orig_bio;
+
+ orig_bio->bi_status = bio->bi_status;
+
+ bio_end_io_acct(orig_bio, md_io_acct->start_time);
+ bio_put(bio);
+ bio_endio(orig_bio);
+}
+
+/* used by personalities (raid0 and raid5) to account io stats */
+void md_account_bio(struct mddev *mddev, struct bio **bio)
+{
+ struct md_io_acct *md_io_acct;
+ struct bio *clone;
+
+ if (!blk_queue_io_stat((*bio)->bi_bdev->bd_disk->queue))
+ return;
+
+ clone = bio_clone_fast(*bio, GFP_NOIO, &mddev->io_acct_set);
+ md_io_acct = container_of(clone, struct md_io_acct, bio_clone);
+ md_io_acct->orig_bio = *bio;
+ md_io_acct->start_time = bio_start_io_acct(*bio);
+
+ clone->bi_end_io = md_end_io_acct;
+ clone->bi_private = md_io_acct;
+ *bio = clone;
+}
+EXPORT_SYMBOL_GPL(md_account_bio);
+
/* md_allow_write(mddev)
* Calling this ensures that the array is marked 'active' so that writes
* may proceed without blocking. It is important to call this before
struct bio_set sync_set; /* for sync operations like
* metadata and bitmap writes
*/
+ struct bio_set io_acct_set; /* for raid0 and raid5 io accounting */
/* Generic flush handling.
* The last to finish preflush schedules a worker to submit
void *private;
};
+struct md_io_acct {
+ struct bio *orig_bio;
+ unsigned long start_time;
+ struct bio bio_clone;
+};
+
#define THREAD_WAKEUP 0
static inline void safe_put_page(struct page *p)
extern void md_finish_reshape(struct mddev *mddev);
void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
struct bio *bio, sector_t start, sector_t size);
+void md_account_bio(struct mddev *mddev, struct bio **bio);
extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
sector_t sector = raid_bio->bi_iter.bi_sector;
unsigned chunk_sects = mddev->chunk_sectors;
unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
+ struct r5conf *conf = mddev->private;
if (sectors < bio_sectors(raid_bio)) {
struct r5conf *conf = mddev->private;
raid_bio = split;
}
+ if (raid_bio->bi_pool != &conf->bio_split)
+ md_account_bio(mddev, &raid_bio);
+
if (!raid5_read_one_chunk(mddev, raid_bio))
return raid_bio;
DEFINE_WAIT(w);
bool do_prepare;
bool do_flush = false;
+ bool do_clone = false;
if (unlikely(bi->bi_opf & REQ_PREFLUSH)) {
int ret = log_handle_flush_request(conf, bi);
if (rw == READ && mddev->degraded == 0 &&
mddev->reshape_position == MaxSector) {
bi = chunk_aligned_read(mddev, bi);
+ do_clone = true;
if (!bi)
return true;
}
last_sector = bio_end_sector(bi);
bi->bi_next = NULL;
+ if (!do_clone)
+ md_account_bio(mddev, &bi);
+
prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) {
int previous;