When there is data only stripes in the journal, we flush them out in
r5l_recovery_log(). Ths logic is implemented in a new function:
r5c_recovery_flush_data_only_stripes();
We need conf->log in r5l_load_log(), so we need to set it before calling
r5l_load_log(). If r5l_load_log() fails, we set conf->log back to NULL.
Signed-off-by: Song Liu <songliubraving@xxxxxx>
---
drivers/md/raid5-cache.c | 60 +++++++++++++++++++++++++++++++++++-------------
drivers/md/raid5.c | 9 +++++++-
drivers/md/raid5.h | 4 ++++
3 files changed, 56 insertions(+), 17 deletions(-)
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index ae2684a..830bb7f 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -2061,7 +2061,7 @@ static int
r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
struct r5l_recovery_ctx *ctx)
{
- struct stripe_head *sh, *next;
+ struct stripe_head *sh;
struct mddev *mddev = log->rdev->mddev;
struct page *page;
@@ -2072,7 +2072,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
return -ENOMEM;
}
- list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+ list_for_each_entry(sh, &ctx->cached_list, lru) {
struct r5l_meta_block *mb;
int i;
int offset;
@@ -2123,13 +2123,39 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
ctx->pos = write_pos;
ctx->seq += 1;
log->next_checkpoint = sh->log_start;
- list_del_init(&sh->lru);
- raid5_release_stripe(sh);
}
__free_page(page);
return 0;
}
+static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
+ struct r5l_recovery_ctx *ctx)
+{
+ struct mddev *mddev = log->rdev->mddev;
+ struct r5conf *conf = mddev->private;
+ struct stripe_head *sh, *next;
+
+ if (ctx->data_only_stripes == 0)
+ return;
+
+ log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_BACK;
+ set_bit(R5C_PRE_INIT_FLUSH, &conf->cache_state);
+
+ list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+ list_del_init(&sh->lru);
+ raid5_release_stripe(sh);
+ }
+
+ md_wakeup_thread(conf->mddev->thread);
+ wait_event(conf->wait_for_r5c_pre_init_flush,
+ atomic_read(&conf->active_stripes) == 0 &&
+ atomic_read(&conf->r5c_cached_full_stripes) == 0 &&
+ atomic_read(&conf->r5c_cached_partial_stripes) == 0);
+
+ clear_bit(R5C_PRE_INIT_FLUSH, &conf->cache_state);
+ log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
+}
+
static int r5l_recovery_log(struct r5l_log *log)
{
struct mddev *mddev = log->rdev->mddev;
@@ -2156,11 +2182,6 @@ static int r5l_recovery_log(struct r5l_log *log)
pos = ctx.pos;
ctx.seq += 1000;
- if (ctx.data_only_stripes == 0) {
- log->next_checkpoint = ctx.pos;
- r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
- ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
- }
if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0))
pr_debug("md/raid:%s: starting from clean shutdown\n",
@@ -2169,19 +2190,24 @@ static int r5l_recovery_log(struct r5l_log *log)
pr_debug("md/raid:%s: recoverying %d data-only stripes and %d data-parity stripes\n",
mdname(mddev), ctx.data_only_stripes,
ctx.data_parity_stripes);
+ }
- if (ctx.data_only_stripes > 0)
- if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
- pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
- mdname(mddev));
- return -EIO;
- }
+ if (ctx.data_only_stripes == 0) {
+ log->next_checkpoint = ctx.pos;
+ r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
+ ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
+ } else if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
+ pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
+ mdname(mddev));
+ return -EIO;
}
log->log_start = ctx.pos;
log->seq = ctx.seq;
log->last_checkpoint = pos;
r5l_write_super(log, pos);
+
+ r5c_recovery_flush_data_only_stripes(log, &ctx);
return 0;
}
@@ -2626,14 +2652,16 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
spin_lock_init(&log->stripe_in_journal_lock);
atomic_set(&log->stripe_in_journal_count, 0);
+ rcu_assign_pointer(conf->log, log);
+
if (r5l_load_log(log))
goto error;
- rcu_assign_pointer(conf->log, log);
set_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
return 0;
error:
+ rcu_assign_pointer(conf->log, NULL);
md_unregister_thread(&log->reclaim_thread);
reclaim_thread:
mempool_destroy(log->meta_pool);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 6bf3c26..524b041 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -232,7 +232,9 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
* When quiesce in r5c write back, set STRIPE_HANDLE for stripes with
* data in journal, so they are not released to cached lists
*/
- if (conf->quiesce && r5c_is_writeback(conf->log) &&
+ if ((conf->quiesce ||
+ test_bit(R5C_PRE_INIT_FLUSH, &conf->cache_state)) &&
+ r5c_is_writeback(conf->log) &&
!test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0) {
if (test_bit(STRIPE_R5C_CACHING, &sh->state))
r5c_make_stripe_write_out(sh);
@@ -264,6 +266,10 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
< IO_THRESHOLD)
md_wakeup_thread(conf->mddev->thread);
atomic_dec(&conf->active_stripes);
+ if (test_bit(R5C_PRE_INIT_FLUSH, &conf->cache_state) &&
+ atomic_read(&conf->active_stripes) == 0)
+ wake_up(&sh->raid_conf->wait_for_r5c_pre_init_flush);
+
if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
if (!r5c_is_writeback(conf->log))
list_add_tail(&sh->lru, temp_inactive_list);
@@ -6638,6 +6644,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
init_waitqueue_head(&conf->wait_for_quiescent);
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
+ init_waitqueue_head(&conf->wait_for_r5c_pre_init_flush);
INIT_LIST_HEAD(&conf->handle_list);
INIT_LIST_HEAD(&conf->hold_list);
INIT_LIST_HEAD(&conf->delayed_list);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index ed8e136..b39fe46 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -564,6 +564,9 @@ enum r5_cache_state {
R5C_EXTRA_PAGE_IN_USE, /* a stripe is using disk_info.extra_page
* for prexor
*/
+ R5C_PRE_INIT_FLUSH, /* flushing data only stripes recovered from
+ * the journal
+ */
};
struct r5conf {
@@ -679,6 +682,7 @@ struct r5conf {
int group_cnt;
int worker_cnt_per_group;
struct r5l_log *log;
+ wait_queue_head_t wait_for_r5c_pre_init_flush;
};
--
2.9.3
--
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
