From: Josef Bacik <josef@toxicpanda.com>
To: linux-btrfs@vger.kernel.org, kernel-team@fb.com
Subject: [PATCH 3/3] btrfs: replace cleaner_delayed_iput_mutex with a waitqueue
Date: Fri, 11 Jan 2019 10:21:03 -0500 [thread overview]
Message-ID: <20190111152103.17001-4-josef@toxicpanda.com> (raw)
In-Reply-To: <20190111152103.17001-1-josef@toxicpanda.com>
The throttle path doesn't take cleaner_delayed_iput_mutex, which means
we could think we're done flushing iputs in the data space reservation
path when we could have a throttler doing an iput. There's no real
reason to serialize the delayed iput flushing, so instead of taking the
cleaner_delayed_iput_mutex whenever we flush the delayed iputs just
replace it with an atomic counter and a waitqueue. This removes the
short (or long depending on how big the inode is) window where we think
there are no more pending iputs when there really are some.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
fs/btrfs/ctree.h | 4 +++-
fs/btrfs/disk-io.c | 5 ++---
fs/btrfs/extent-tree.c | 13 ++++++++-----
fs/btrfs/inode.c | 21 +++++++++++++++++++++
4 files changed, 34 insertions(+), 9 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index dc56a4d940c3..20af5d6d81f1 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -915,7 +915,8 @@ struct btrfs_fs_info {
spinlock_t delayed_iput_lock;
struct list_head delayed_iputs;
- struct mutex cleaner_delayed_iput_mutex;
+ atomic_t nr_delayed_iputs;
+ wait_queue_head_t delayed_iputs_wait;
/* this protects tree_mod_seq_list */
spinlock_t tree_mod_seq_lock;
@@ -3240,6 +3241,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root);
int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
void btrfs_add_delayed_iput(struct inode *inode);
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
+int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info);
int btrfs_prealloc_file_range(struct inode *inode, int mode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f40f6fdc1019..238e0113f2d3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1694,9 +1694,7 @@ static int cleaner_kthread(void *arg)
goto sleep;
}
- mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
btrfs_run_delayed_iputs(fs_info);
- mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
again = btrfs_clean_one_deleted_snapshot(root);
mutex_unlock(&fs_info->cleaner_mutex);
@@ -2654,7 +2652,6 @@ int open_ctree(struct super_block *sb,
mutex_init(&fs_info->delete_unused_bgs_mutex);
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
- mutex_init(&fs_info->cleaner_delayed_iput_mutex);
seqlock_init(&fs_info->profiles_lock);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
@@ -2676,6 +2673,7 @@ int open_ctree(struct super_block *sb,
atomic_set(&fs_info->defrag_running, 0);
atomic_set(&fs_info->qgroup_op_seq, 0);
atomic_set(&fs_info->reada_works_cnt, 0);
+ atomic_set(&fs_info->nr_delayed_iputs, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
fs_info->sb = sb;
fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
@@ -2753,6 +2751,7 @@ int open_ctree(struct super_block *sb,
init_waitqueue_head(&fs_info->transaction_wait);
init_waitqueue_head(&fs_info->transaction_blocked_wait);
init_waitqueue_head(&fs_info->async_submit_wait);
+ init_waitqueue_head(&fs_info->delayed_iputs_wait);
INIT_LIST_HEAD(&fs_info->pinned_chunks);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0127d272cd2a..5b6c9fc227ff 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4280,10 +4280,14 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
/*
* The cleaner kthread might still be doing iput
* operations. Wait for it to finish so that
- * more space is released.
+ * more space is released. We don't need to
+ * explicitly run the delayed iputs here because
+ * the commit_transaction would have woken up
+ * the cleaner.
*/
- mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
- mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
+ ret = btrfs_wait_on_delayed_iputs(fs_info);
+ if (ret)
+ return ret;
goto again;
} else {
btrfs_end_transaction(trans);
@@ -4958,9 +4962,8 @@ static void flush_space(struct btrfs_fs_info *fs_info,
* bunch of pinned space, so make sure we run the iputs before
* we do our pinned bytes check below.
*/
- mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
btrfs_run_delayed_iputs(fs_info);
- mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
+ btrfs_wait_on_delayed_iputs(fs_info);
ret = may_commit_transaction(fs_info, space_info);
break;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0b9f3e482cea..958e30c7c744 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3260,6 +3260,7 @@ void btrfs_add_delayed_iput(struct inode *inode)
if (atomic_add_unless(&inode->i_count, -1, 1))
return;
+ atomic_inc(&fs_info->nr_delayed_iputs);
spin_lock(&fs_info->delayed_iput_lock);
ASSERT(list_empty(&binode->delayed_iput));
list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs);
@@ -3280,11 +3281,31 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
list_del_init(&inode->delayed_iput);
spin_unlock(&fs_info->delayed_iput_lock);
iput(&inode->vfs_inode);
+ if (atomic_dec_and_test(&fs_info->nr_delayed_iputs))
+ wake_up(&fs_info->delayed_iputs_wait);
spin_lock(&fs_info->delayed_iput_lock);
}
spin_unlock(&fs_info->delayed_iput_lock);
}
+/**
+ * btrfs_wait_on_delayed_iputs - wait on the delayed iputs to be done running
+ * @fs_info - the fs_info for this fs
+ * @return - EINTR if we were killed, 0 if nothing's pending
+ *
+ * This will wait on any delayed iputs that are currently running with KILLABLE
+ * set. Once they are all done running we will return, unless we are killed in
+ * which case we return EINTR.
+ */
+int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info)
+{
+ int ret = wait_event_killable(fs_info->delayed_iputs_wait,
+ atomic_read(&fs_info->nr_delayed_iputs) == 0);
+ if (ret)
+ return -EINTR;
+ return 0;
+}
+
/*
* This creates an orphan entry for the given inode in case something goes wrong
* in the middle of an unlink.
--
2.14.3
next prev parent reply other threads:[~2019-01-11 15:21 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-11 15:21 [PATCH 0/3][V3] Delayed iput fixes Josef Bacik
2019-01-11 15:21 ` [PATCH 1/3] btrfs: run delayed iputs before committing Josef Bacik
2019-01-11 15:21 ` [PATCH 2/3] btrfs: wakeup cleaner thread when adding delayed iput Josef Bacik
2019-01-11 15:21 ` Josef Bacik [this message]
2019-01-16 19:12 ` [PATCH 3/3] btrfs: replace cleaner_delayed_iput_mutex with a waitqueue David Sterba
2019-02-05 18:23 ` David Sterba
-- strict thread matches above, loose matches on Subject: below --
2018-12-03 16:06 [PATCH 0/3][V2] Delayed iput fixes Josef Bacik
2018-12-03 16:06 ` [PATCH 3/3] btrfs: replace cleaner_delayed_iput_mutex with a waitqueue Josef Bacik
2018-12-04 11:46 ` Nikolay Borisov
2018-12-04 18:21 ` Josef Bacik
2018-11-21 19:09 [PATCH 0/3] Delayed iput fixes Josef Bacik
2018-11-21 19:09 ` [PATCH 3/3] btrfs: replace cleaner_delayed_iput_mutex with a waitqueue Josef Bacik
2018-11-27 8:29 ` Nikolay Borisov
2018-11-27 20:01 ` Josef Bacik
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=20190111152103.17001-4-josef@toxicpanda.com \
--to=josef@toxicpanda.com \
--cc=kernel-team@fb.com \
--cc=linux-btrfs@vger.kernel.org \
/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).