From a85dd7b8df52e35d8ee3794c65cac5c39128fd80 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 23 Jan 2017 17:12:57 -0800 Subject: [PATCH] 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(-) 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; }