Currently the raid5-cache code is heavily relying on GFP_NOFAIL allocations.
I've looked into replacing these with mempools and biosets, and for the
bio and the meta_page that's pretty trivial as they have short life times
and do make guaranteed progress. I'm massively struggling with the iounit
allocation, though. These can live on for a long time over log I/O, cache
flushing and last but not least RAID I/O, and every attempt at something
mempool-like results in reproducible deadlocks. I wonder if we need to
figure out some more efficient data structure to communicate the completion
status that doesn't rely on these fairly long living allocations from
the I/O path.
FYI, my last attempt to use the bio frontpad is below, but a mempool showed
pretty similar results:
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 2e3f22a..d2438be 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -33,12 +33,12 @@
*/
#define RECLAIM_MAX_FREE_SPACE (10 * 1024 * 1024 * 2) /* sector */
#define RECLAIM_MAX_FREE_SPACE_SHIFT (2)
-
+
/*
* We only need 2 bios per I/O unit to make progress, but ensure we
* have a few more available to not get too tight.
*/
-#define R5L_POOL_SIZE 1024
+#define R5L_POOL_SIZE 16384
struct r5l_log {
struct md_rdev *rdev;
@@ -75,7 +75,6 @@ struct r5l_log {
struct list_head finished_ios; /* io_units which settle down in log disk */
struct bio flush_bio;
- struct kmem_cache *io_kc;
struct bio_set *bs;
mempool_t *meta_pool;
@@ -120,6 +119,8 @@ struct r5l_io_unit {
int state;
bool need_split_bio;
+
+ struct bio bio;
};
/* r5l_io_unit state */
@@ -209,14 +210,13 @@ static void r5l_move_to_end_ios(struct r5l_log *log)
static void r5l_log_endio(struct bio *bio)
{
- struct r5l_io_unit *io = bio->bi_private;
+ struct r5l_io_unit *io = container_of(bio, struct r5l_io_unit, bio);
struct r5l_log *log = io->log;
unsigned long flags;
if (bio->bi_error)
md_error(log->rdev->mddev, log->rdev);
- bio_put(bio);
mempool_free(io->meta_page, log->meta_pool);
spin_lock_irqsave(&log->io_list_lock, flags);
@@ -284,11 +284,13 @@ static void r5_reserve_log_entry(struct r5l_log *log, struct r5l_io_unit *io)
static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
{
+ struct bio *bio;
struct r5l_io_unit *io;
struct r5l_meta_block *block;
- /* We can't handle memory allocate failure so far */
- io = kmem_cache_zalloc(log->io_kc, GFP_NOIO | __GFP_NOFAIL);
+ bio = r5l_bio_alloc(log);
+
+ io = container_of(bio, struct r5l_io_unit, bio);
io->log = log;
INIT_LIST_HEAD(&io->log_sibling);
INIT_LIST_HEAD(&io->stripe_list);
@@ -306,7 +308,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
io->meta_offset = sizeof(struct r5l_meta_block);
io->seq = log->seq++;
- io->current_bio = r5l_bio_alloc(log);
+ io->current_bio = bio;
io->current_bio->bi_end_io = r5l_log_endio;
io->current_bio->bi_private = io;
bio_add_page(io->current_bio, io->meta_page, PAGE_SIZE, 0);
@@ -556,7 +558,7 @@ static bool r5l_complete_finished_ios(struct r5l_log *log)
log->next_cp_seq = io->seq;
list_del(&io->log_sibling);
- kmem_cache_free(log->io_kc, io);
+ bio_put(&io->bio);
found = true;
}
@@ -1158,11 +1160,8 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
INIT_LIST_HEAD(&log->finished_ios);
bio_init(&log->flush_bio);
- log->io_kc = KMEM_CACHE(r5l_io_unit, 0);
- if (!log->io_kc)
- goto io_kc;
-
- log->bs = bioset_create(R5L_POOL_SIZE, 0);
+ log->bs = bioset_create(R5L_POOL_SIZE,
+ offsetof(struct r5l_io_unit, bio));
if (!log->bs)
goto io_bs;
@@ -1192,8 +1191,6 @@ reclaim_thread:
out_mempool:
bioset_free(log->bs);
io_bs:
- kmem_cache_destroy(log->io_kc);
-io_kc:
kfree(log);
return -EINVAL;
}
@@ -1203,6 +1200,5 @@ void r5l_exit_log(struct r5l_log *log)
md_unregister_thread(&log->reclaim_thread);
mempool_destroy(log->meta_pool);
bioset_free(log->bs);
- kmem_cache_destroy(log->io_kc);
kfree(log);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
