linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Josef Bacik <josef@toxicpanda.com>
To: linux-btrfs@vger.kernel.org, kernel-team@fb.com
Cc: Nikolay Borisov <nborisov@suse.com>
Subject: [PATCH v4 03/12] btrfs: track ordered bytes instead of just dio ordered bytes
Date: Tue, 26 Jan 2021 16:24:27 -0500	[thread overview]
Message-ID: <4447efff3c9450d1903758e1dde899623885241f.1611695838.git.josef@toxicpanda.com> (raw)
In-Reply-To: <cover.1611695838.git.josef@toxicpanda.com>

We track dio_bytes because the shrink delalloc code needs to know if we
have more DIO in flight than we have normal buffered IO.  The reason for
this is because we can't "flush" DIO, we have to just wait on the
ordered extents to finish.

However this is true of all ordered extents.  If we have more ordered
space outstanding than dirty pages we should be waiting on ordered
extents.  We already are ok on this front technically, because we always
do a FLUSH_DELALLOC_WAIT loop, but I want to use the ordered counter in
the preemptive flushing code as well, so change this to count all
ordered bytes instead of just DIO ordered bytes.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/btrfs/ctree.h        |  2 +-
 fs/btrfs/disk-io.c      |  8 ++++----
 fs/btrfs/ordered-data.c | 13 ++++++-------
 fs/btrfs/space-info.c   | 18 +++++++-----------
 4 files changed, 18 insertions(+), 23 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ed6bb46a2572..7d8660227520 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -797,7 +797,7 @@ struct btrfs_fs_info {
 	/* used to keep from writing metadata until there is a nice batch */
 	struct percpu_counter dirty_metadata_bytes;
 	struct percpu_counter delalloc_bytes;
-	struct percpu_counter dio_bytes;
+	struct percpu_counter ordered_bytes;
 	s32 dirty_metadata_batch;
 	s32 delalloc_batch;
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 5473bed6a7e8..e0d56b3d1223 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1469,7 +1469,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 {
 	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
 	percpu_counter_destroy(&fs_info->delalloc_bytes);
-	percpu_counter_destroy(&fs_info->dio_bytes);
+	percpu_counter_destroy(&fs_info->ordered_bytes);
 	percpu_counter_destroy(&fs_info->dev_replace.bio_counter);
 	btrfs_free_csum_hash(fs_info);
 	btrfs_free_stripe_hash_table(fs_info);
@@ -2802,7 +2802,7 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block
 	sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE;
 	sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE);
 
-	ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL);
+	ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL);
 	if (ret)
 		return ret;
 
@@ -4163,9 +4163,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 		       percpu_counter_sum(&fs_info->delalloc_bytes));
 	}
 
-	if (percpu_counter_sum(&fs_info->dio_bytes))
+	if (percpu_counter_sum(&fs_info->ordered_bytes))
 		btrfs_info(fs_info, "at unmount dio bytes count %lld",
-			   percpu_counter_sum(&fs_info->dio_bytes));
+			   percpu_counter_sum(&fs_info->ordered_bytes));
 
 	btrfs_sysfs_remove_mounted(fs_info);
 	btrfs_sysfs_remove_fsid(fs_info->fs_devices);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index b4e6500548a2..e8dee1578d4a 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -206,11 +206,11 @@ static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset
 	       type == BTRFS_ORDERED_COMPRESSED);
 	set_bit(type, &entry->flags);
 
-	if (dio) {
-		percpu_counter_add_batch(&fs_info->dio_bytes, num_bytes,
-					 fs_info->delalloc_batch);
+	percpu_counter_add_batch(&fs_info->ordered_bytes, num_bytes,
+				 fs_info->delalloc_batch);
+
+	if (dio)
 		set_bit(BTRFS_ORDERED_DIRECT, &entry->flags);
-	}
 
 	/* one ref for the tree */
 	refcount_set(&entry->refs, 1);
@@ -503,9 +503,8 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
 		btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes,
 						false);
 
-	if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
-		percpu_counter_add_batch(&fs_info->dio_bytes, -entry->num_bytes,
-					 fs_info->delalloc_batch);
+	percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,
+				 fs_info->delalloc_batch);
 
 	tree = &btrfs_inode->ordered_tree;
 	spin_lock_irq(&tree->lock);
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index af6ab30e36e7..ff138cef7d0b 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -489,7 +489,7 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_trans_handle *trans;
 	u64 delalloc_bytes;
-	u64 dio_bytes;
+	u64 ordered_bytes;
 	u64 items;
 	long time_left;
 	int loops;
@@ -513,25 +513,20 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
 
 	delalloc_bytes = percpu_counter_sum_positive(
 						&fs_info->delalloc_bytes);
-	dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
-	if (delalloc_bytes == 0 && dio_bytes == 0) {
-		if (trans)
-			return;
-		if (wait_ordered)
-			btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
+	ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes);
+	if (delalloc_bytes == 0 && ordered_bytes == 0)
 		return;
-	}
 
 	/*
 	 * If we are doing more ordered than delalloc we need to just wait on
 	 * ordered extents, otherwise we'll waste time trying to flush delalloc
 	 * that likely won't give us the space back we need.
 	 */
-	if (dio_bytes > delalloc_bytes)
+	if (ordered_bytes > delalloc_bytes)
 		wait_ordered = true;
 
 	loops = 0;
-	while ((delalloc_bytes || dio_bytes) && loops < 3) {
+	while ((delalloc_bytes || ordered_bytes) && loops < 3) {
 		u64 temp = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
 		long nr_pages = min_t(u64, temp, LONG_MAX);
 
@@ -556,7 +551,8 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
 
 		delalloc_bytes = percpu_counter_sum_positive(
 						&fs_info->delalloc_bytes);
-		dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
+		ordered_bytes = percpu_counter_sum_positive(
+						&fs_info->ordered_bytes);
 	}
 }
 
-- 
2.26.2


  parent reply	other threads:[~2021-01-26 23:07 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-26 21:24 [PATCH v4 00/12] Improve preemptive ENOSPC flushing Josef Bacik
2021-01-26 21:24 ` [PATCH v4 01/12] btrfs: make flush_space take a enum btrfs_flush_state instead of int Josef Bacik
2021-01-26 21:24 ` [PATCH v4 02/12] btrfs: add a trace point for reserve tickets Josef Bacik
2021-01-26 21:24 ` Josef Bacik [this message]
2021-01-26 21:24 ` [PATCH v4 04/12] btrfs: introduce a FORCE_COMMIT_TRANS flush operation Josef Bacik
2021-01-26 21:24 ` [PATCH v4 05/12] btrfs: improve preemptive background space flushing Josef Bacik
2021-01-26 21:24 ` [PATCH v4 06/12] btrfs: rename need_do_async_reclaim Josef Bacik
2021-01-26 21:24 ` [PATCH v4 07/12] btrfs: check reclaim_size in need_preemptive_reclaim Josef Bacik
2021-01-26 21:24 ` [PATCH v4 08/12] btrfs: rework btrfs_calc_reclaim_metadata_size Josef Bacik
2021-01-26 21:24 ` [PATCH v4 09/12] btrfs: simplify the logic in need_preemptive_flushing Josef Bacik
2021-01-26 21:24 ` [PATCH v4 10/12] btrfs: implement space clamping for preemptive flushing Josef Bacik
2021-01-26 21:24 ` [PATCH v4 11/12] btrfs: adjust the flush trace point to include the source Josef Bacik
2021-01-26 21:24 ` [PATCH v4 12/12] btrfs: add a trace class for dumping the current ENOSPC state Josef Bacik
2021-01-27 15:03 ` [PATCH v4 00/12] Improve preemptive ENOSPC flushing David Sterba

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=4447efff3c9450d1903758e1dde899623885241f.1611695838.git.josef@toxicpanda.com \
    --to=josef@toxicpanda.com \
    --cc=kernel-team@fb.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=nborisov@suse.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).