* [PATCH 1/2] md/r5cache: flush data only stripes in r5l_recovery_log()
@ 2016-12-07 19:36 Song Liu
2016-12-07 19:36 ` [PATCH 2/2] md/r5cache: read data into orig_page for prexor of cached data Song Liu
0 siblings, 1 reply; 2+ messages in thread
From: Song Liu @ 2016-12-07 19:36 UTC (permalink / raw
To: linux-raid
Cc: neilb, shli, kernel-team, dan.j.williams, hch, liuzhengyuan,
liuyun01, Song Liu
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@fb.com>
---
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
^ permalink raw reply related [flat|nested] 2+ messages in thread
* [PATCH 2/2] md/r5cache: read data into orig_page for prexor of cached data
2016-12-07 19:36 [PATCH 1/2] md/r5cache: flush data only stripes in r5l_recovery_log() Song Liu
@ 2016-12-07 19:36 ` Song Liu
0 siblings, 0 replies; 2+ messages in thread
From: Song Liu @ 2016-12-07 19:36 UTC (permalink / raw
To: linux-raid
Cc: neilb, shli, kernel-team, dan.j.williams, hch, liuzhengyuan,
liuyun01, Song Liu
With write back cache, we use orig_page to do prexor. This patch
makes sure we read data into orig_page for it.
Flag R5_OrigPageUPTDODATE is added to make show when orig_page
has the latest data from raid disk.
Signed-off-by: Song Liu <songliubraving@fb.com>
---
drivers/md/raid5-cache.c | 2 ++
drivers/md/raid5.c | 37 ++++++++++++++++++++++++++++---------
drivers/md/raid5.h | 5 +++++
3 files changed, 35 insertions(+), 9 deletions(-)
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 830bb7f..03cef8b 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -2373,6 +2373,8 @@ void r5c_release_extra_page(struct stripe_head *sh)
struct page *p = sh->dev[i].orig_page;
sh->dev[i].orig_page = sh->dev[i].page;
+ clear_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
if (!using_disk_info_extra_page)
put_page(p);
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 524b041..eb7425a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1019,7 +1019,13 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
- sh->dev[i].vec.bv_page = sh->dev[i].page;
+
+ if (!op_is_write(op) &&
+ test_bit(R5_InJournal, &sh->dev[i].flags) &&
+ sh->dev[i].page != sh->dev[i].orig_page)
+ sh->dev[i].vec.bv_page = sh->dev[i].orig_page;
+ else
+ sh->dev[i].vec.bv_page = sh->dev[i].page;
bi->bi_vcnt = 1;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
@@ -2389,6 +2395,10 @@ static void raid5_end_read_request(struct bio * bi)
} else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
+ if (test_bit(R5_InJournal, &sh->dev[i].flags) &&
+ sh->dev[i].page != sh->dev[i].orig_page)
+ set_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
if (atomic_read(&rdev->read_errors))
atomic_set(&rdev->read_errors, 0);
} else {
@@ -3603,6 +3613,21 @@ static void handle_stripe_clean_event(struct r5conf *conf,
break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
}
+/*
+ * For RMW in write back cache, we need extra page in prexor to store the
+ * old data. This page is stored in dev->orig_page.
+ *
+ * This function checks whether we have data for prexor. The exact logic
+ * is:
+ * R5_UPTODATE && (!R5_InJournal || R5_OrigPageUPTDODATE)
+ */
+static inline bool uptodate_for_rmw(struct r5dev *dev)
+{
+ return (test_bit(R5_UPTODATE, &dev->flags)) &&
+ (!test_bit(R5_InJournal, &dev->flags) ||
+ test_bit(R5_OrigPageUPTDODATE, &dev->flags));
+}
+
static int handle_stripe_dirtying(struct r5conf *conf,
struct stripe_head *sh,
struct stripe_head_state *s,
@@ -3634,9 +3659,7 @@ static int handle_stripe_dirtying(struct r5conf *conf,
if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx ||
test_bit(R5_InJournal, &dev->flags)) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !((test_bit(R5_UPTODATE, &dev->flags) &&
- (!test_bit(R5_InJournal, &dev->flags) ||
- dev->page != dev->orig_page)) ||
+ !(uptodate_for_rmw(dev) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rmw++;
@@ -3648,7 +3671,6 @@ static int handle_stripe_dirtying(struct r5conf *conf,
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_InJournal, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rcw++;
@@ -3702,9 +3724,7 @@ static int handle_stripe_dirtying(struct r5conf *conf,
i == sh->pd_idx || i == sh->qd_idx ||
test_bit(R5_InJournal, &dev->flags)) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !((test_bit(R5_UPTODATE, &dev->flags) &&
- (!test_bit(R5_InJournal, &dev->flags) ||
- dev->page != dev->orig_page)) ||
+ !(uptodate_for_rmw(dev) ||
test_bit(R5_Wantcompute, &dev->flags)) &&
test_bit(R5_Insync, &dev->flags)) {
if (test_bit(STRIPE_PREREAD_ACTIVE,
@@ -3731,7 +3751,6 @@ static int handle_stripe_dirtying(struct r5conf *conf,
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_InJournal, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
rcw++;
if (test_bit(R5_Insync, &dev->flags) &&
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index b39fe46..6cc8d4c 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -322,6 +322,11 @@ enum r5dev_flags {
* data and parity being written are in the journal
* device
*/
+ R5_OrigPageUPTDODATE, /* with write back cache, we read old data into
+ * dev->orig_page for prexor. When this flag is
+ * set, orig_page contains latest data in the
+ * raid disk.
+ */
};
/*
--
2.9.3
^ permalink raw reply related [flat|nested] 2+ messages in thread
end of thread, other threads:[~2016-12-07 19:36 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-12-07 19:36 [PATCH 1/2] md/r5cache: flush data only stripes in r5l_recovery_log() Song Liu
2016-12-07 19:36 ` [PATCH 2/2] md/r5cache: read data into orig_page for prexor of cached data Song Liu
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.