diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-12-14 10:03:36 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-12-14 10:03:36 -0800 |
commit | 37222e1c9ee3ce587f5b41fed868bd8a592a992f (patch) | |
tree | b65f22a1e20286185463ca1a2889e593d963a393 /drivers/md/raid5.c | |
parent | 76b8f82cde2d9c13ef0c9a9aa2581b9b30b68e8c (diff) | |
parent | 06e3c817b750c131a20e82eed57a17841ea88ed2 (diff) |
Merge branch 'for-linus' of git://neil.brown.name/md
* 'for-linus' of git://neil.brown.name/md: (27 commits)
md: add 'recovery_start' per-device sysfs attribute
md: rcu_read_lock() walk of mddev->disks in md_do_sync()
md: integrate spares into array at earliest opportunity.
md: move compat_ioctl handling into md.c
md: revise Kconfig help for MD_MULTIPATH
md: add MODULE_DESCRIPTION for all md related modules.
raid: improve MD/raid10 handling of correctable read errors.
md/raid10: print more useful messages on device failure.
md/bitmap: update dirty flag when bitmap bits are explicitly set.
md: Support write-intent bitmaps with externally managed metadata.
md/bitmap: move setting of daemon_lastrun out of bitmap_read_sb
md: support updating bitmap parameters via sysfs.
md: factor out parsing of fixed-point numbers
md: support bitmap offset appropriate for external-metadata arrays.
md: remove needless setting of thread->timeout in raid10_quiesce
md: change daemon_sleep to be in 'jiffies' rather than 'seconds'.
md: move offset, daemon_sleep and chunksize out of bitmap structure
md: collect bitmap-specific fields into one structure.
md/raid1: add takeover support for raid5->raid1
md: add honouring of suspend_{lo,hi} to raid1.
...
Diffstat (limited to 'drivers/md/raid5.c')
-rw-r--r-- | drivers/md/raid5.c | 63 |
1 files changed, 48 insertions, 15 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index d29215d966d..e84204eb12d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2947,6 +2947,7 @@ static void handle_stripe5(struct stripe_head *sh) struct r5dev *dev; mdk_rdev_t *blocked_rdev = NULL; int prexor; + int dec_preread_active = 0; memset(&s, 0, sizeof(s)); pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d " @@ -3096,12 +3097,8 @@ static void handle_stripe5(struct stripe_head *sh) set_bit(STRIPE_INSYNC, &sh->state); } } - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < - IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + dec_preread_active = 1; } /* Now to consider new write requests and what else, if anything @@ -3208,6 +3205,16 @@ static void handle_stripe5(struct stripe_head *sh) ops_run_io(sh, &s); + if (dec_preread_active) { + /* We delay this until after ops_run_io so that if make_request + * is waiting on a barrier, it won't continue until the writes + * have actually been submitted. + */ + atomic_dec(&conf->preread_active_stripes); + if (atomic_read(&conf->preread_active_stripes) < + IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } return_io(return_bi); } @@ -3221,6 +3228,7 @@ static void handle_stripe6(struct stripe_head *sh) struct r6_state r6s; struct r5dev *dev, *pdev, *qdev; mdk_rdev_t *blocked_rdev = NULL; + int dec_preread_active = 0; pr_debug("handling stripe %llu, state=%#lx cnt=%d, " "pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n", @@ -3358,7 +3366,6 @@ static void handle_stripe6(struct stripe_head *sh) * completed */ if (sh->reconstruct_state == reconstruct_state_drain_result) { - int qd_idx = sh->qd_idx; sh->reconstruct_state = reconstruct_state_idle; /* All the 'written' buffers and the parity blocks are ready to @@ -3380,12 +3387,8 @@ static void handle_stripe6(struct stripe_head *sh) set_bit(STRIPE_INSYNC, &sh->state); } } - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < - IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + dec_preread_active = 1; } /* Now to consider new write requests and what else, if anything @@ -3494,6 +3497,18 @@ static void handle_stripe6(struct stripe_head *sh) ops_run_io(sh, &s); + + if (dec_preread_active) { + /* We delay this until after ops_run_io so that if make_request + * is waiting on a barrier, it won't continue until the writes + * have actually been submitted. + */ + atomic_dec(&conf->preread_active_stripes); + if (atomic_read(&conf->preread_active_stripes) < + IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } + return_io(return_bi); } @@ -3741,7 +3756,7 @@ static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio) { mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev->private; - unsigned int dd_idx; + int dd_idx; struct bio* align_bi; mdk_rdev_t *rdev; @@ -3866,7 +3881,13 @@ static int make_request(struct request_queue *q, struct bio * bi) int cpu, remaining; if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) { - bio_endio(bi, -EOPNOTSUPP); + /* Drain all pending writes. We only really need + * to ensure they have been submitted, but this is + * easier. + */ + mddev->pers->quiesce(mddev, 1); + mddev->pers->quiesce(mddev, 0); + md_barrier_request(mddev, bi); return 0; } @@ -3990,6 +4011,9 @@ static int make_request(struct request_queue *q, struct bio * bi) finish_wait(&conf->wait_for_overlap, &w); set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); + if (mddev->barrier && + !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + atomic_inc(&conf->preread_active_stripes); release_stripe(sh); } else { /* cannot get stripe for read-ahead, just give-up */ @@ -4009,6 +4033,14 @@ static int make_request(struct request_queue *q, struct bio * bi) bio_endio(bi, 0); } + + if (mddev->barrier) { + /* We need to wait for the stripes to all be handled. + * So: wait for preread_active_stripes to drop to 0. + */ + wait_event(mddev->thread->wqueue, + atomic_read(&conf->preread_active_stripes) == 0); + } return 0; } @@ -5860,6 +5892,7 @@ static void raid5_exit(void) module_init(raid5_init); module_exit(raid5_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("RAID4/5/6 (striping with parity) personality for MD"); MODULE_ALIAS("md-personality-4"); /* RAID5 */ MODULE_ALIAS("md-raid5"); MODULE_ALIAS("md-raid4"); |