summaryrefslogtreecommitdiffstats
path: root/drivers/md/raid5.h
diff options
context:
space:
mode:
authorSong Liu <songliubraving@fb.com>2016-11-17 15:24:40 -0800
committerShaohua Li <shli@fb.com>2016-11-18 13:26:48 -0800
commita39f7afde358ca89e9fc09a5525d3f8631a98a3a (patch)
tree25c08dcdb44ee34bc670b54d7e5ca9d1d03275f4 /drivers/md/raid5.h
parent1e6d690b9334b7e1b31d25fd8d93e980e449a5f9 (diff)
downloadlinux-a39f7afde358ca89e9fc09a5525d3f8631a98a3a.tar.bz2
md/r5cache: write-out phase and reclaim support
There are two limited resources, stripe cache and journal disk space. For better performance, we priotize reclaim of full stripe writes. To free up more journal space, we free earliest data on the journal. In current implementation, reclaim happens when: 1. Periodically (every R5C_RECLAIM_WAKEUP_INTERVAL, 30 seconds) reclaim if there is no reclaim in the past 5 seconds. 2. when there are R5C_FULL_STRIPE_FLUSH_BATCH (256) cached full stripes, or cached stripes is enough for a full stripe (chunk size / 4k) (r5c_check_cached_full_stripe) 3. when there is pressure on stripe cache (r5c_check_stripe_cache_usage) 4. when there is pressure on journal space (r5l_write_stripe, r5c_cache_data) r5c_do_reclaim() contains new logic of reclaim. For stripe cache: When stripe cache pressure is high (more than 3/4 stripes are cached, or there is empty inactive lists), flush all full stripe. If fewer than R5C_RECLAIM_STRIPE_GROUP (NR_STRIPE_HASH_LOCKS * 2) full stripes are flushed, flush some paritial stripes. When stripe cache pressure is moderate (1/2 to 3/4 of stripes are cached), flush all full stripes. For log space: To avoid deadlock due to log space, we need to reserve enough space to flush cached data. The size of required log space depends on total number of cached stripes (stripe_in_journal_count). In current implementation, the writing-out phase automatically include pending data writes with parity writes (similar to write through case). Therefore, we need up to (conf->raid_disks + 1) pages for each cached stripe (1 page for meta data, raid_disks pages for all data and parity). r5c_log_required_to_flush_cache() calculates log space required to flush cache. In the following, we refer to the space calculated by r5c_log_required_to_flush_cache() as reclaim_required_space. Two flags are added to r5conf->cache_state: R5C_LOG_TIGHT and R5C_LOG_CRITICAL. R5C_LOG_TIGHT is set when free space on the log device is less than 3x of reclaim_required_space. R5C_LOG_CRITICAL is set when free space on the log device is less than 2x of reclaim_required_space. r5c_cache keeps all data in cache (not fully committed to RAID) in a list (stripe_in_journal_list). These stripes are in the order of their first appearance on the journal. So the log tail (last_checkpoint) should point to the journal_start of the first item in the list. When R5C_LOG_TIGHT is set, r5l_reclaim_thread starts flushing out stripes at the head of stripe_in_journal. When R5C_LOG_CRITICAL is set, the state machine only writes data that are already in the log device (in stripe_in_journal_list). This patch includes a fix to improve performance by Shaohua Li <shli@fb.com>. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Shaohua Li <shli@fb.com>
Diffstat (limited to 'drivers/md/raid5.h')
-rw-r--r--drivers/md/raid5.h39
1 files changed, 28 insertions, 11 deletions
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 73c183398e38..35b4c0f0a850 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -226,6 +226,8 @@ struct stripe_head {
struct r5l_io_unit *log_io;
struct list_head log_list;
+ sector_t log_start; /* first meta block on the journal */
+ struct list_head r5c; /* for r5c_cache->stripe_in_journal */
/**
* struct stripe_operations
* @target - STRIPE_OP_COMPUTE_BLK target
@@ -537,6 +539,27 @@ struct r5worker_group {
int stripes_cnt;
};
+enum r5_cache_state {
+ R5_INACTIVE_BLOCKED, /* release of inactive stripes blocked,
+ * waiting for 25% to be free
+ */
+ R5_ALLOC_MORE, /* It might help to allocate another
+ * stripe.
+ */
+ R5_DID_ALLOC, /* A stripe was allocated, don't allocate
+ * more until at least one has been
+ * released. This avoids flooding
+ * the cache.
+ */
+ R5C_LOG_TIGHT, /* log device space tight, need to
+ * prioritize stripes at last_checkpoint
+ */
+ R5C_LOG_CRITICAL, /* log device is running out of space,
+ * only process stripes that are already
+ * occupying the log
+ */
+};
+
struct r5conf {
struct hlist_head *stripe_hashtbl;
/* only protect corresponding hash list and inactive_list */
@@ -636,17 +659,6 @@ struct r5conf {
wait_queue_head_t wait_for_stripe;
wait_queue_head_t wait_for_overlap;
unsigned long cache_state;
-#define R5_INACTIVE_BLOCKED 1 /* release of inactive stripes blocked,
- * waiting for 25% to be free
- */
-#define R5_ALLOC_MORE 2 /* It might help to allocate another
- * stripe.
- */
-#define R5_DID_ALLOC 4 /* A stripe was allocated, don't allocate
- * more until at least one has been
- * released. This avoids flooding
- * the cache.
- */
struct shrinker shrinker;
int pool_size; /* number of disks in stripeheads in pool */
spinlock_t device_lock;
@@ -752,8 +764,13 @@ extern void
r5c_finish_stripe_write_out(struct r5conf *conf, struct stripe_head *sh,
struct stripe_head_state *s);
extern void r5c_release_extra_page(struct stripe_head *sh);
+extern void r5l_wake_reclaim(struct r5l_log *log, sector_t space);
extern void r5c_handle_cached_data_endio(struct r5conf *conf,
struct stripe_head *sh, int disks, struct bio_list *return_bi);
extern int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh,
struct stripe_head_state *s);
+extern void r5c_make_stripe_write_out(struct stripe_head *sh);
+extern void r5c_flush_cache(struct r5conf *conf, int num);
+extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
+extern void r5c_check_cached_full_stripe(struct r5conf *conf);
#endif