From: Dennis Zhou <dennis@kernel.org> To: David Sterba <dsterba@suse.com>, Chris Mason <clm@fb.com>, Josef Bacik <josef@toxicpanda.com>, Omar Sandoval <osandov@osandov.com> Cc: kernel-team@fb.com, linux-btrfs@vger.kernel.org, Dennis Zhou <dennis@kernel.org> Subject: [PATCH 13/22] btrfs: calculate discard delay based on number of extents Date: Mon, 25 Nov 2019 14:46:53 -0500 Message-ID: <9171398d2ba16bc6b2b41a3d4982acf9ae27417d.1574709825.git.dennis@kernel.org> (raw) In-Reply-To: <cover.1574709825.git.dennis@kernel.org> In-Reply-To: <cover.1574709825.git.dennis@kernel.org> Use the number of discardable extents to help guide our discard delay interval. This value is reevaluated every transaction commit. Signed-off-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: Josef Bacik <josef@toxicpanda.com> --- fs/btrfs/ctree.h | 2 ++ fs/btrfs/discard.c | 53 ++++++++++++++++++++++++++++++++++++++---- fs/btrfs/discard.h | 1 + fs/btrfs/extent-tree.c | 4 +++- fs/btrfs/sysfs.c | 31 ++++++++++++++++++++++++ 5 files changed, 86 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 5b13bda52ab7..78b970cfd108 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -469,6 +469,8 @@ struct btrfs_discard_ctl { struct list_head discard_list[BTRFS_NR_DISCARD_LISTS]; atomic_t discardable_extents; atomic64_t discardable_bytes; + u32 delay; + u32 iops_limit; }; /* delayed seq elem */ diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 074341c8242a..ddd5cc303b1e 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -14,6 +14,11 @@ /* This is an initial delay to give some chance for lba reuse. */ #define BTRFS_DISCARD_DELAY (120ULL * NSEC_PER_SEC) +/* Target completion latency of discarding all discardable extents. */ +#define BTRFS_DISCARD_TARGET_MSEC (6 * 60 * 60UL * MSEC_PER_SEC) +#define BTRFS_DISCARD_MAX_DELAY (10000UL) +#define BTRFS_DISCARD_MAX_IOPS (10UL) + static struct list_head *btrfs_get_discard_list( struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) @@ -231,11 +236,18 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, block_group = find_next_block_group(discard_ctl, now); if (block_group) { - u64 delay = 0; + u32 delay = discard_ctl->delay; + + /* + * This timeout is to hopefully prevent immediate discarding + * in a recently allocated block group. + */ + if (now < block_group->discard_eligible_time) { + u64 bg_timeout = (block_group->discard_eligible_time - + now); - if (now < block_group->discard_eligible_time) - delay = nsecs_to_jiffies( - block_group->discard_eligible_time - now); + delay = max_t(u64, delay, nsecs_to_jiffies(bg_timeout)); + } mod_delayed_work(discard_ctl->discard_workers, &discard_ctl->work, @@ -341,6 +353,37 @@ bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl) test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags)); } +/** + * btrfs_discard_calc_delay - recalculate the base delay + * @discard_ctl: discard control + * + * Recalculate the base delay which is based off the total number of + * discardable_extents. Clamp this with the iops_limit and + * BTRFS_DISCARD_MAX_DELAY. + */ +void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) +{ + s32 discardable_extents = + atomic_read(&discard_ctl->discardable_extents); + s32 iops_limit; + unsigned long delay; + + if (!discardable_extents) + return; + + spin_lock(&discard_ctl->lock); + + iops_limit = READ_ONCE(discard_ctl->iops_limit); + if (iops_limit) + iops_limit = MSEC_PER_SEC / iops_limit; + + delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents; + delay = clamp_t(s32, delay, iops_limit, BTRFS_DISCARD_MAX_DELAY); + discard_ctl->delay = msecs_to_jiffies(delay); + + spin_unlock(&discard_ctl->lock); +} + /** * btrfs_discard_update_discardable - propagate discard counters * @block_group: block_group of interest @@ -470,6 +513,8 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info) atomic_set(&discard_ctl->discardable_extents, 0); atomic64_set(&discard_ctl->discardable_bytes, 0); + discard_ctl->delay = BTRFS_DISCARD_MAX_DELAY; + discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS; } void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h index 75f00a84d540..88f1363aa4e4 100644 --- a/fs/btrfs/discard.h +++ b/fs/btrfs/discard.h @@ -23,6 +23,7 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl); /* Update operations. */ +void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl); void btrfs_discard_update_discardable(struct btrfs_block_group *block_group, struct btrfs_free_space_ctl *ctl); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 857642dc8589..27ca833c11c8 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2941,8 +2941,10 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) cond_resched(); } - if (btrfs_test_opt(fs_info, DISCARD_ASYNC)) + if (btrfs_test_opt(fs_info, DISCARD_ASYNC)) { + btrfs_discard_calc_delay(&fs_info->discard_ctl); btrfs_discard_schedule_work(&fs_info->discard_ctl, true); + } /* * Transaction is finished. We don't need the lock anymore. We diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 07098f6d62bd..043430ae3818 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -344,6 +344,36 @@ static const struct attribute_group btrfs_static_feature_attr_group = { */ #define discard_to_fs_info(_kobj) to_fs_info((_kobj)->parent->parent) +static ssize_t btrfs_discard_iops_limit_show(struct kobject *kobj, + struct kobj_attribute *a, + char *buf) +{ + struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); + + return snprintf(buf, PAGE_SIZE, "%u\n", + READ_ONCE(fs_info->discard_ctl.iops_limit)); +} + +static ssize_t btrfs_discard_iops_limit_store(struct kobject *kobj, + struct kobj_attribute *a, + const char *buf, size_t len) +{ + struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj); + struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl; + u32 iops_limit; + int ret; + + ret = kstrtou32(buf, 10, &iops_limit); + if (ret) + return -EINVAL; + + WRITE_ONCE(discard_ctl->iops_limit, iops_limit); + + return len; +} +BTRFS_ATTR_RW(discard, iops_limit, btrfs_discard_iops_limit_show, + btrfs_discard_iops_limit_store); + static ssize_t btrfs_discardable_extents_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) @@ -367,6 +397,7 @@ static ssize_t btrfs_discardable_bytes_show(struct kobject *kobj, BTRFS_ATTR(discard, discardable_bytes, btrfs_discardable_bytes_show); static const struct attribute *discard_debug_attrs[] = { + BTRFS_ATTR_PTR(discard, iops_limit), BTRFS_ATTR_PTR(discard, discardable_extents), BTRFS_ATTR_PTR(discard, discardable_bytes), NULL, -- 2.17.1
next prev parent reply index Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-11-25 19:46 [PATCH v4 00/22] btrfs: async discard support Dennis Zhou 2019-11-25 19:46 ` [PATCH 01/22] bitmap: genericize percpu bitmap region iterators Dennis Zhou 2019-11-25 19:46 ` [PATCH 02/22] btrfs: rename DISCARD opt to DISCARD_SYNC Dennis Zhou 2019-11-25 19:46 ` [PATCH 03/22] btrfs: keep track of which extents have been discarded Dennis Zhou 2019-11-25 19:46 ` [PATCH 04/22] btrfs: keep track of cleanliness of the bitmap Dennis Zhou 2019-11-25 19:46 ` [PATCH 05/22] btrfs: add the beginning of async discard, discard workqueue Dennis Zhou 2019-11-25 19:46 ` [PATCH 06/22] btrfs: handle empty block_group removal Dennis Zhou 2019-11-25 19:46 ` [PATCH 07/22] btrfs: discard one region at a time in async discard Dennis Zhou 2019-11-25 19:46 ` [PATCH 08/22] btrfs: add removal calls for sysfs debug/ Dennis Zhou 2019-11-25 19:46 ` [PATCH 09/22] btrfs: make UUID/debug have its own kobject Dennis Zhou 2019-11-25 19:46 ` [PATCH 10/22] btrfs: add discard sysfs directory Dennis Zhou 2019-11-25 19:46 ` [PATCH 11/22] btrfs: track discardable extents for async discard Dennis Zhou 2019-11-25 19:46 ` [PATCH 12/22] btrfs: keep track of discardable_bytes Dennis Zhou 2019-11-25 19:46 ` Dennis Zhou [this message] 2019-11-25 19:46 ` [PATCH 14/22] btrfs: add bps discard rate limit Dennis Zhou 2019-11-25 19:46 ` [PATCH 15/22] btrfs: limit max discard size for async discard Dennis Zhou 2019-11-25 19:46 ` [PATCH 16/22] btrfs: make max async discard size tunable Dennis Zhou 2019-11-25 19:46 ` [PATCH 17/22] btrfs: have multiple discard lists Dennis Zhou 2019-11-25 19:46 ` [PATCH 18/22] btrfs: only keep track of data extents for async discard Dennis Zhou 2019-11-25 19:46 ` [PATCH 19/22] btrfs: keep track of discard reuse stats Dennis Zhou 2019-11-25 19:47 ` [PATCH 20/22] btrfs: add async discard header Dennis Zhou 2019-11-25 19:47 ` [PATCH 21/22] btrfs: increase the metadata allowance for the free_space_cache Dennis Zhou 2019-11-25 19:47 ` [PATCH 22/22] btrfs: make smaller extents more likely to go into bitmaps Dennis Zhou 2019-11-26 21:52 ` [PATCH v4 00/22] btrfs: async discard support David Sterba 2019-11-27 18:26 ` Dennis Zhou -- strict thread matches above, loose matches on Subject: below -- 2019-12-14 0:22 [PATCH v6 " Dennis Zhou 2019-12-14 0:22 ` [PATCH 13/22] btrfs: calculate discard delay based on number of extents Dennis Zhou 2019-12-30 16:50 ` David Sterba 2020-01-02 16:45 ` Dennis Zhou 2019-12-09 19:45 [PATCH v5 00/22] btrfs: async discard support Dennis Zhou 2019-12-09 19:45 ` [PATCH 13/22] btrfs: calculate discard delay based on number of extents Dennis Zhou 2019-11-20 21:50 [PATCH v3 00/22] btrfs: async discard support Dennis Zhou 2019-11-20 21:51 ` [PATCH 13/22] btrfs: calculate discard delay based on number of extents Dennis Zhou 2019-10-23 22:52 [PATCH v2 00/22] btrfs: async discard support Dennis Zhou 2019-10-23 22:53 ` [PATCH 13/22] btrfs: calculate discard delay based on number of extents Dennis Zhou
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=9171398d2ba16bc6b2b41a3d4982acf9ae27417d.1574709825.git.dennis@kernel.org \ --to=dennis@kernel.org \ --cc=clm@fb.com \ --cc=dsterba@suse.com \ --cc=josef@toxicpanda.com \ --cc=kernel-team@fb.com \ --cc=linux-btrfs@vger.kernel.org \ --cc=osandov@osandov.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
Linux-BTRFS Archive on lore.kernel.org Archives are clonable: git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/git/0.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 linux-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \ linux-btrfs@vger.kernel.org public-inbox-index linux-btrfs Example config snippet for mirrors Newsgroup available over NNTP: nntp://nntp.lore.kernel.org/org.kernel.vger.linux-btrfs AGPL code for this site: git clone https://public-inbox.org/public-inbox.git