md/r5cache: handle sync with data in write back cache

Currently, sync of raid456 array cannot make progress when hitting
data in writeback r5cache.

This patch fixes this issue by flushing cached data of the stripe
before processing the sync request. This is achived by:

1. In handle_stripe(), do not set STRIPE_SYNCING if the stripe is
   in write back cache;
2. In r5c_try_caching_write(), handle the stripe in sync with write
   through;
3. In do_release_stripe(), make stripe in sync write out and send
   it to the state machine.

Shaohua: explictly set STRIPE_HANDLE after write out completed

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>

diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index cc3f8442f11ff4cf143348d1b773f832b4b3628f..4c00bc248287e4ab89b492225e0d054973725549 100644 (file)
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -2637,8 +2637,11 @@ int r5c_try_caching_write(struct r5conf *conf,
         * When run in degraded mode, array is set to write-through mode.
         * This check helps drain pending write safely in the transition to
         * write-through mode.
+        *
+        * When a stripe is syncing, the write is also handled in write
+        * through mode.
         */
-       if (s->failed) {
+       if (s->failed || test_bit(STRIPE_SYNCING, &sh->state)) {
                r5c_make_stripe_write_out(sh);
                return -EAGAIN;
        }
@@ -2841,6 +2844,9 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
        }
 
        r5l_append_flush_payload(log, sh->sector);
+       /* stripe is flused to raid disks, we can do resync now */
+       if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
+               set_bit(STRIPE_HANDLE, &sh->state);
 }
 
 int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0ac57a9256063054725a3549153d5512551f2c3e..9c4f7659f8b1337c99cfd0ab5070012e3f658849 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -233,11 +233,15 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
                        if (test_bit(R5_InJournal, &sh->dev[i].flags))
                                injournal++;
        /*
-        * When quiesce in r5c write back, set STRIPE_HANDLE for stripes with
-        * data in journal, so they are not released to cached lists
+        * In the following cases, the stripe cannot be released to cached
+        * lists. Therefore, we make the stripe write out and set
+        * STRIPE_HANDLE:
+        *   1. when quiesce in r5c write back;
+        *   2. when resync is requested fot the stripe.
         */
-       if (conf->quiesce && r5c_is_writeback(conf->log) &&
-           !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0) {
+       if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) ||
+           (conf->quiesce && 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);
                set_bit(STRIPE_HANDLE, &sh->state);
@@ -4656,8 +4660,13 @@ static void handle_stripe(struct stripe_head *sh)
 
        if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
                spin_lock(&sh->stripe_lock);
-               /* Cannot process 'sync' concurrently with 'discard' */
-               if (!test_bit(STRIPE_DISCARD, &sh->state) &&
+               /*
+                * Cannot process 'sync' concurrently with 'discard'.
+                * Flush data in r5cache before 'sync'.
+                */
+               if (!test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state) &&
+                   !test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) &&
+                   !test_bit(STRIPE_DISCARD, &sh->state) &&
                    test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
                        set_bit(STRIPE_SYNCING, &sh->state);
                        clear_bit(STRIPE_INSYNC, &sh->state);