From d46d29f072accb069cb42b5fbebcc77d9094a785 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 11 Jan 2017 13:38:52 -0800 Subject: md/raid5-cache: delete meaningless code sector_t is unsigned long, it's never < 0 Reported-by: Julia Lawall Signed-off-by: Shaohua Li --- drivers/md/raid5-cache.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/md/raid5-cache.c') diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 0e8ed2c327b0..e0d6dd1835d0 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1393,8 +1393,6 @@ static void r5l_do_reclaim(struct r5l_log *log) next_checkpoint = r5c_calculate_new_cp(conf); spin_unlock_irq(&log->io_list_lock); - BUG_ON(reclaimable < 0); - if (reclaimable == 0 || !write_super) return; -- cgit v1.2.3 From 86aa1397ddfde563b3692adadb8b8e32e97b4e5e Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 12 Jan 2017 17:22:41 -0800 Subject: md/r5cache: read data into orig_page for prexor of cached data 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 show whether orig_page has the latest data from raid disk. We introduce a helper function uptodate_for_rmw() to simplify the a couple conditions in handle_stripe_dirtying(). Signed-off-by: Song Liu Signed-off-by: Shaohua Li --- drivers/md/raid5-cache.c | 2 ++ drivers/md/raid5.c | 44 +++++++++++++++++++++++++++++++++++--------- drivers/md/raid5.h | 5 +++++ 3 files changed, 42 insertions(+), 9 deletions(-) (limited to 'drivers/md/raid5-cache.c') diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index e0d6dd1835d0..95dcaa022e1f 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -2349,6 +2349,8 @@ 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 36c13e4be9c9..7780ae44f355 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1015,7 +1015,17 @@ again: 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)) + /* + * issuing read for a page in journal, this + * must be preparing for prexor in rmw; read + * the data into 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; @@ -2380,6 +2390,13 @@ 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)) + /* + * end read for a page in journal, this + * must be preparing for prexor in rmw + */ + set_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags); + if (atomic_read(&rdev->read_errors)) atomic_set(&rdev->read_errors, 0); } else { @@ -3594,6 +3611,21 @@ unhash: 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, @@ -3625,9 +3657,7 @@ 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++; @@ -3639,7 +3669,6 @@ 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++; @@ -3693,9 +3722,7 @@ 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, @@ -3722,7 +3749,6 @@ 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 ed8e1362ab36..461df197d157 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. + */ }; /* -- cgit v1.2.3 From a85dd7b8df52e35d8ee3794c65cac5c39128fd80 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 23 Jan 2017 17:12:57 -0800 Subject: md/r5cache: flush data only stripes in r5l_recovery_log() For safer operation, all arrays start in write-through mode, which has been better tested and is more mature. And actually the write-through/write-mode isn't persistent after array restarted, so we always start array in write-through mode. However, if recovery found data-only stripes before the shutdown (from previous write-back mode), it is not safe to start the array in write-through mode, as write-through mode can not handle stripes with data in write-back cache. To solve this problem, we flush all data-only stripes in r5l_recovery_log(). When r5l_recovery_log() returns, the array starts with empty cache in write-through mode. This logic is implemented in r5c_recovery_flush_data_only_stripes(): 1. enable write back cache 2. flush all stripes 3. wake up conf->mddev->thread 4. wait for all stripes get flushed (reuse wait_for_quiescent) 5. disable write back cache The wait in 4 will be waked up in release_inactive_stripe_list() when conf->active_stripes reaches 0. It is safe to wake up mddev->thread here because all the resource required for the thread has been initialized. Signed-off-by: Song Liu Signed-off-by: Shaohua Li --- drivers/md/md.c | 5 +++++ drivers/md/raid5-cache.c | 56 ++++++++++++++++++++++++++++++++++-------------- 2 files changed, 45 insertions(+), 16 deletions(-) (limited to 'drivers/md/raid5-cache.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 82821ee0d57f..01175dac0db6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5291,6 +5291,11 @@ int md_run(struct mddev *mddev) if (start_readonly && mddev->ro == 0) mddev->ro = 2; /* read-only, but switch on first write */ + /* + * NOTE: some pers->run(), for example r5l_recovery_log(), wakes + * up mddev->thread. It is important to initialize critical + * resources for mddev->thread BEFORE calling pers->run(). + */ err = pers->run(mddev); if (err) pr_warn("md: pers->run() failed ...\n"); diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 95dcaa022e1f..3d7dda85494c 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -2060,7 +2060,7 @@ 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; sector_t next_checkpoint = MaxSector; @@ -2074,7 +2074,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, WARN_ON(list_empty(&ctx->cached_list)); - 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; @@ -2124,14 +2124,39 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log, ctx->pos = write_pos; ctx->seq += 1; next_checkpoint = sh->log_start; - list_del_init(&sh->lru); - raid5_release_stripe(sh); } log->next_checkpoint = next_checkpoint; __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; + + list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) { + r5c_make_stripe_write_out(sh); + set_bit(STRIPE_HANDLE, &sh->state); + list_del_init(&sh->lru); + raid5_release_stripe(sh); + } + + md_wakeup_thread(conf->mddev->thread); + /* reuse conf->wait_for_quiescent in recovery */ + wait_event(conf->wait_for_quiescent, + atomic_read(&conf->active_stripes) == 0); + + log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; +} + static int r5l_recovery_log(struct r5l_log *log) { struct mddev *mddev = log->rdev->mddev; @@ -2158,32 +2183,31 @@ static int r5l_recovery_log(struct r5l_log *log) pos = ctx.pos; ctx.seq += 10000; - 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", mdname(mddev)); - else { + else pr_debug("md/raid:%s: recovering %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; } -- cgit v1.2.3 From 2e38a37f23c98d7fad87ff022670060b8a0e2bf5 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 24 Jan 2017 10:45:30 -0800 Subject: md/r5cache: disable write back for degraded array write-back cache in degraded mode introduces corner cases to the array. Although we try to cover all these corner cases, it is safer to just disable write-back cache when the array is in degraded mode. In this patch, we disable writeback cache for degraded mode: 1. On device failure, if the array enters degraded mode, raid5_error() will submit async job r5c_disable_writeback_async to disable writeback; 2. In r5c_journal_mode_store(), it is invalid to enable writeback in degraded mode; 3. In r5c_try_caching_write(), stripes with s->failed>0 will be handled in write-through mode. Signed-off-by: Song Liu Signed-off-by: Shaohua Li --- drivers/md/raid5-cache.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/md/raid5.c | 15 ++++++++------- drivers/md/raid5.h | 2 ++ 3 files changed, 56 insertions(+), 7 deletions(-) (limited to 'drivers/md/raid5-cache.c') diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 3d7dda85494c..302dea3296ba 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -162,6 +162,8 @@ struct r5l_log { /* to submit async io_units, to fulfill ordering of flush */ struct work_struct deferred_io_work; + /* to disable write back during in degraded mode */ + struct work_struct disable_writeback_work; }; /* @@ -611,6 +613,21 @@ static void r5l_submit_io_async(struct work_struct *work) r5l_do_submit_io(log, io); } +static void r5c_disable_writeback_async(struct work_struct *work) +{ + struct r5l_log *log = container_of(work, struct r5l_log, + disable_writeback_work); + struct mddev *mddev = log->rdev->mddev; + + if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH) + return; + pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n", + mdname(mddev)); + mddev_suspend(mddev); + log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; + mddev_resume(mddev); +} + static void r5l_submit_current_io(struct r5l_log *log) { struct r5l_io_unit *io = log->current_io; @@ -2269,6 +2286,10 @@ static ssize_t r5c_journal_mode_store(struct mddev *mddev, val > R5C_JOURNAL_MODE_WRITE_BACK) return -EINVAL; + if (raid5_calc_degraded(conf) > 0 && + val == R5C_JOURNAL_MODE_WRITE_BACK) + return -EINVAL; + mddev_suspend(mddev); conf->log->r5c_journal_mode = val; mddev_resume(mddev); @@ -2323,6 +2344,16 @@ int r5c_try_caching_write(struct r5conf *conf, set_bit(STRIPE_R5C_CACHING, &sh->state); } + /* + * 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. + */ + if (s->failed) { + r5c_make_stripe_write_out(sh); + return -EAGAIN; + } + for (i = disks; i--; ) { dev = &sh->dev[i]; /* if non-overwrite, use writing-out phase */ @@ -2579,6 +2610,19 @@ ioerr: return ret; } +void r5c_update_on_rdev_error(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + struct r5l_log *log = conf->log; + + if (!log) + return; + + if (raid5_calc_degraded(conf) > 0 && + conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK) + schedule_work(&log->disable_writeback_work); +} + int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) { struct request_queue *q = bdev_get_queue(rdev->bdev); @@ -2651,6 +2695,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) spin_lock_init(&log->no_space_stripes_lock); INIT_WORK(&log->deferred_io_work, r5l_submit_io_async); + INIT_WORK(&log->disable_writeback_work, r5c_disable_writeback_async); log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; INIT_LIST_HEAD(&log->stripe_in_journal_list); @@ -2683,6 +2728,7 @@ io_kc: void r5l_exit_log(struct r5l_log *log) { + flush_work(&log->disable_writeback_work); md_unregister_thread(&log->reclaim_thread); mempool_destroy(log->meta_pool); bioset_free(log->bs); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index dc83da69ca7c..3c7e106c12a2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -556,7 +556,7 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, * of the two sections, and some non-in_sync devices may * be insync in the section most affected by failed devices. */ -static int calc_degraded(struct r5conf *conf) +int raid5_calc_degraded(struct r5conf *conf) { int degraded, degraded2; int i; @@ -619,7 +619,7 @@ static int has_failed(struct r5conf *conf) if (conf->mddev->reshape_position == MaxSector) return conf->mddev->degraded > conf->max_degraded; - degraded = calc_degraded(conf); + degraded = raid5_calc_degraded(conf); if (degraded > conf->max_degraded) return 1; return 0; @@ -2555,7 +2555,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) spin_lock_irqsave(&conf->device_lock, flags); clear_bit(In_sync, &rdev->flags); - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); set_bit(MD_RECOVERY_INTR, &mddev->recovery); @@ -2569,6 +2569,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) bdevname(rdev->bdev, b), mdname(mddev), conf->raid_disks - mddev->degraded); + r5c_update_on_rdev_error(mddev); } /* @@ -7091,7 +7092,7 @@ static int raid5_run(struct mddev *mddev) /* * 0 for a fully functional array, 1 or 2 for a degraded array. */ - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); if (has_failed(conf)) { pr_crit("md/raid:%s: not enough operational devices (%d/%d failed)\n", @@ -7338,7 +7339,7 @@ static int raid5_spare_active(struct mddev *mddev) } } spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); print_raid5_conf(conf); return count; @@ -7698,7 +7699,7 @@ static int raid5_start_reshape(struct mddev *mddev) * pre and post number of devices. */ spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); } mddev->raid_disks = conf->raid_disks; @@ -7786,7 +7787,7 @@ static void raid5_finish_reshape(struct mddev *mddev) } else { int d; spin_lock_irq(&conf->device_lock); - mddev->degraded = calc_degraded(conf); + mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irq(&conf->device_lock); for (d = conf->raid_disks ; d < conf->raid_disks - mddev->delta_disks; diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 461df197d157..1440fa26e296 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -758,6 +758,7 @@ extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, extern struct stripe_head * raid5_get_active_stripe(struct r5conf *conf, sector_t sector, int previous, int noblock, int noquiesce); +extern int raid5_calc_degraded(struct r5conf *conf); extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev); extern void r5l_exit_log(struct r5l_log *log); extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh); @@ -786,4 +787,5 @@ 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); extern struct md_sysfs_entry r5c_journal_mode; +extern void r5c_update_on_rdev_error(struct mddev *mddev); #endif -- cgit v1.2.3