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 10/19] btrfs: calculate discard delay based on number of extents
Date: Mon, 7 Oct 2019 16:17:41 -0400 [thread overview]
Message-ID: <37690bf17c3b3c9f20137fb186c7af4021bb664b.1570479299.git.dennis@kernel.org> (raw)
In-Reply-To: <cover.1570479299.git.dennis@kernel.org>
In-Reply-To: <cover.1570479299.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>
---
fs/btrfs/ctree.h | 2 ++
fs/btrfs/discard.c | 31 +++++++++++++++++++++++++++++--
fs/btrfs/discard.h | 3 +++
fs/btrfs/extent-tree.c | 4 +++-
fs/btrfs/sysfs.c | 30 ++++++++++++++++++++++++++++++
5 files changed, 67 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8479ab037812..b0823961d049 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -449,6 +449,8 @@ struct btrfs_discard_ctl {
struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
atomic_t discard_extents;
atomic64_t discardable_bytes;
+ atomic_t delay;
+ atomic_t iops_limit;
};
/* delayed seq elem */
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 75a2ff14b3c0..c7afb5f8240d 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -15,6 +15,11 @@
#define BTRFS_DISCARD_DELAY (300ULL * NSEC_PER_SEC)
+/* target discard delay in milliseconds */
+#define BTRFS_DISCARD_TARGET_MSEC (6 * 60 * 60ULL * 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_cache *cache)
@@ -170,10 +175,12 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
cache = find_next_cache(discard_ctl, now);
if (cache) {
- u64 delay = 0;
+ u64 delay = atomic_read(&discard_ctl->delay);
if (now < cache->discard_delay)
- delay = nsecs_to_jiffies(cache->discard_delay - now);
+ delay = max_t(u64, delay,
+ nsecs_to_jiffies(cache->discard_delay -
+ now));
mod_delayed_work(discard_ctl->discard_workers,
&discard_ctl->work,
@@ -232,6 +239,24 @@ static void btrfs_discard_workfn(struct work_struct *work)
btrfs_discard_schedule_work(discard_ctl, false);
}
+void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
+{
+ s32 discard_extents = atomic_read(&discard_ctl->discard_extents);
+ s32 iops_limit;
+ unsigned long delay;
+
+ if (!discard_extents)
+ return;
+
+ iops_limit = atomic_read(&discard_ctl->iops_limit);
+ if (iops_limit)
+ iops_limit = MSEC_PER_SEC / iops_limit;
+
+ delay = BTRFS_DISCARD_TARGET_MSEC / discard_extents;
+ delay = clamp_t(s32, delay, iops_limit, BTRFS_DISCARD_MAX_DELAY);
+ atomic_set(&discard_ctl->delay, msecs_to_jiffies(delay));
+}
+
void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info)
{
struct btrfs_block_group_cache *cache, *next;
@@ -301,6 +326,8 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
atomic_set(&discard_ctl->discard_extents, 0);
atomic64_set(&discard_ctl->discardable_bytes, 0);
+ atomic_set(&discard_ctl->delay, BTRFS_DISCARD_MAX_DELAY);
+ atomic_set(&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 d55a9a9f8ad8..acaf56f63b1c 100644
--- a/fs/btrfs/discard.h
+++ b/fs/btrfs/discard.h
@@ -7,6 +7,8 @@
#define BTRFS_DISCARD_H
#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
#include <linux/workqueue.h>
#include "ctree.h"
@@ -39,6 +41,7 @@ void btrfs_discard_cancel_work(struct btrfs_discard_ctl *discard_ctl,
struct btrfs_block_group_cache *cache);
void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
bool override);
+void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl);
void btrfs_discard_resume(struct btrfs_fs_info *fs_info);
void btrfs_discard_stop(struct btrfs_fs_info *fs_info);
void btrfs_discard_init(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ff42e4abb01d..ab0d46da3771 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2920,8 +2920,10 @@ 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 a2852706ec6c..b9a62e470316 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -493,9 +493,39 @@ static ssize_t btrfs_discardable_bytes_show(struct kobject *kobj,
}
BTRFS_ATTR(discard, discardable_bytes, btrfs_discardable_bytes_show);
+static ssize_t btrfs_discard_iops_limit_show(struct kobject *kobj,
+ struct kobj_attribute *a,
+ char *buf)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent);
+
+ return snprintf(buf, PAGE_SIZE, "%d\n",
+ atomic_read(&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 = to_fs_info(kobj->parent);
+ s32 iops_limit;
+ int ret;
+
+ ret = kstrtos32(buf, 10, &iops_limit);
+ if (ret || iops_limit < 0)
+ return -EINVAL;
+
+ atomic_set(&fs_info->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 const struct attribute *discard_attrs[] = {
BTRFS_ATTR_PTR(discard, discard_extents),
BTRFS_ATTR_PTR(discard, discardable_bytes),
+ BTRFS_ATTR_PTR(discard, iops_limit),
NULL,
};
--
2.17.1
next prev parent reply other threads:[~2019-10-07 20:18 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-07 20:17 [RFC PATCH 00/19] btrfs: async discard support Dennis Zhou
2019-10-07 20:17 ` [PATCH 01/19] bitmap: genericize percpu bitmap region iterators Dennis Zhou
2019-10-07 20:26 ` Josef Bacik
2019-10-07 22:24 ` Dennis Zhou
2019-10-15 12:11 ` David Sterba
2019-10-15 18:35 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 02/19] btrfs: rename DISCARD opt to DISCARD_SYNC Dennis Zhou
2019-10-07 20:27 ` Josef Bacik
2019-10-08 11:12 ` Johannes Thumshirn
2019-10-11 9:19 ` Nikolay Borisov
2019-10-07 20:17 ` [PATCH 03/19] btrfs: keep track of which extents have been discarded Dennis Zhou
2019-10-07 20:37 ` Josef Bacik
2019-10-07 22:38 ` Dennis Zhou
2019-10-10 13:40 ` Josef Bacik
2019-10-11 16:15 ` Dennis Zhou
2019-10-08 12:46 ` Nikolay Borisov
2019-10-11 16:08 ` Dennis Zhou
2019-10-15 12:17 ` David Sterba
2019-10-15 19:58 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 04/19] btrfs: keep track of cleanliness of the bitmap Dennis Zhou
2019-10-10 14:16 ` Josef Bacik
2019-10-11 16:17 ` Dennis Zhou
2019-10-15 12:23 ` David Sterba
2019-10-07 20:17 ` [PATCH 05/19] btrfs: add the beginning of async discard, discard workqueue Dennis Zhou
2019-10-10 14:38 ` Josef Bacik
2019-10-15 12:49 ` David Sterba
2019-10-15 19:57 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 06/19] btrfs: handle empty block_group removal Dennis Zhou
2019-10-10 15:00 ` Josef Bacik
2019-10-11 16:52 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 07/19] btrfs: discard one region at a time in async discard Dennis Zhou
2019-10-10 15:22 ` Josef Bacik
2019-10-14 19:42 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 08/19] btrfs: track discardable extents for asnyc discard Dennis Zhou
2019-10-10 15:36 ` Josef Bacik
2019-10-14 19:50 ` Dennis Zhou
2019-10-15 13:12 ` David Sterba
2019-10-15 18:41 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 09/19] btrfs: keep track of discardable_bytes Dennis Zhou
2019-10-10 15:38 ` Josef Bacik
2019-10-07 20:17 ` Dennis Zhou [this message]
2019-10-10 15:41 ` [PATCH 10/19] btrfs: calculate discard delay based on number of extents Josef Bacik
2019-10-11 18:07 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 11/19] btrfs: add bps discard rate limit Dennis Zhou
2019-10-10 15:47 ` Josef Bacik
2019-10-14 19:56 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 12/19] btrfs: limit max discard size for async discard Dennis Zhou
2019-10-10 16:16 ` Josef Bacik
2019-10-14 19:57 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 13/19] btrfs: have multiple discard lists Dennis Zhou
2019-10-10 16:51 ` Josef Bacik
2019-10-14 20:04 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 14/19] btrfs: only keep track of data extents for async discard Dennis Zhou
2019-10-10 16:53 ` Josef Bacik
2019-10-07 20:17 ` [PATCH 15/19] btrfs: load block_groups into discard_list on mount Dennis Zhou
2019-10-10 17:11 ` Josef Bacik
2019-10-14 20:17 ` Dennis Zhou
2019-10-14 23:38 ` David Sterba
2019-10-15 15:42 ` Dennis Zhou
2019-10-07 20:17 ` [PATCH 16/19] btrfs: keep track of discard reuse stats Dennis Zhou
2019-10-10 17:13 ` Josef Bacik
2019-10-07 20:17 ` [PATCH 17/19] btrfs: add async discard header Dennis Zhou
2019-10-10 17:13 ` Josef Bacik
2019-10-07 20:17 ` [PATCH 18/19] btrfs: increase the metadata allowance for the free_space_cache Dennis Zhou
2019-10-10 17:16 ` Josef Bacik
2019-10-07 20:17 ` [PATCH 19/19] btrfs: make smaller extents more likely to go into bitmaps Dennis Zhou
2019-10-10 17:17 ` Josef Bacik
2019-10-11 7:49 ` [RFC PATCH 00/19] btrfs: async discard support Nikolay Borisov
2019-10-14 21:05 ` Dennis Zhou
2019-10-15 12:08 ` David Sterba
2019-10-15 15:41 ` 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=37690bf17c3b3c9f20137fb186c7af4021bb664b.1570479299.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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).