From: Dmitry Monakhov <dmonakhov@gmail.com>
To: linux-ext4@vger.kernel.org
Cc: tytso@mit.edu, Dmitry Monakhov <dmonakhov@gmail.com>
Subject: [PATCH] ext4: fix extent_status fragmentation for plain files
Date: Wed, 6 Nov 2019 12:25:02 +0000 [thread overview]
Message-ID: <20191106122502.19986-1-dmonakhov@gmail.com> (raw)
It is appeared that extent are not cached for inodes with depth == 0
which result in suboptimal extent status populating inside ext4_map_blocks()
by map's result where size requested is usually smaller than extent size so
cache becomes fragmented
# Example: I have plain file:
File size of /mnt/test is 33554432 (8192 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 8191: 40960.. 49151: 8192: last,eof
$ perf record -e 'ext4:ext4_es_*' /root/bin/fio --name=t --direct=0 --rw=randread --bs=4k --filesize=32M --size=32M --filename=/mnt/test
$ perf script | grep ext4_es_insert_extent | head -n 10
fio 131 [000] 13.975421: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [494/1) mapped 41454 status W
fio 131 [000] 13.975939: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [6064/1) mapped 47024 status W
fio 131 [000] 13.976467: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [6907/1) mapped 47867 status W
fio 131 [000] 13.976937: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [3850/1) mapped 44810 status W
fio 131 [000] 13.977440: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [3292/1) mapped 44252 status W
fio 131 [000] 13.977931: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [6882/1) mapped 47842 status W
fio 131 [000] 13.978376: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [3117/1) mapped 44077 status W
fio 131 [000] 13.978957: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [2896/1) mapped 43856 status W
fio 131 [000] 13.979474: ext4:ext4_es_insert_extent: dev 253,0 ino 12 es [7479/1) mapped 48439 status W
This is wrong, we should cache extents inside ext4_find_extent() as we already do for inodes with depth > 0
Signed-off-by: Dmitry Monakhov <dmonakhov@gmail.com>
---
fs/ext4/extents.c | 47 +++++++++++++++++++++++++++--------------------
1 file changed, 27 insertions(+), 20 deletions(-)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index fb0f99d..24d6bfd 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -498,6 +498,30 @@ int ext4_ext_check_inode(struct inode *inode)
return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0);
}
+static void ext4_es_cache_extents(struct inode *inode,
+ struct ext4_extent_header *eh)
+{
+ struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
+ ext4_lblk_t prev = 0;
+ int i;
+
+ for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
+ unsigned int status = EXTENT_STATUS_WRITTEN;
+ ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
+ int len = ext4_ext_get_actual_len(ex);
+
+ if (prev && (prev != lblk))
+ ext4_es_cache_extent(inode, prev, lblk - prev, ~0,
+ EXTENT_STATUS_HOLE);
+
+ if (ext4_ext_is_unwritten(ex))
+ status = EXTENT_STATUS_UNWRITTEN;
+ ext4_es_cache_extent(inode, lblk, len,
+ ext4_ext_pblock(ex), status);
+ prev = lblk + len;
+ }
+}
+
static struct buffer_head *
__read_extent_tree_block(const char *function, unsigned int line,
struct inode *inode, ext4_fsblk_t pblk, int depth,
@@ -532,26 +556,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
*/
if (!(flags & EXT4_EX_NOCACHE) && depth == 0) {
struct ext4_extent_header *eh = ext_block_hdr(bh);
- struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
- ext4_lblk_t prev = 0;
- int i;
-
- for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
- unsigned int status = EXTENT_STATUS_WRITTEN;
- ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
- int len = ext4_ext_get_actual_len(ex);
-
- if (prev && (prev != lblk))
- ext4_es_cache_extent(inode, prev,
- lblk - prev, ~0,
- EXTENT_STATUS_HOLE);
-
- if (ext4_ext_is_unwritten(ex))
- status = EXTENT_STATUS_UNWRITTEN;
- ext4_es_cache_extent(inode, lblk, len,
- ext4_ext_pblock(ex), status);
- prev = lblk + len;
- }
+ ext4_es_cache_extents(inode, eh);
}
return bh;
errout:
@@ -899,6 +904,8 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
path[0].p_bh = NULL;
i = depth;
+ if (!(flags & EXT4_EX_NOCACHE) && depth == 0)
+ ext4_es_cache_extents(inode, eh);
/* walk through the tree */
while (i) {
ext_debug("depth %d: num %d, max %d\n",
--
2.7.4
next reply other threads:[~2019-11-06 12:25 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-06 12:25 Dmitry Monakhov [this message]
2019-11-07 15:38 ` [PATCH] ext4: fix extent_status fragmentation for plain files Theodore Y. Ts'o
2019-11-08 15:21 ` Dmitry Monakhov
2020-01-25 2:22 ` Theodore Y. Ts'o
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=20191106122502.19986-1-dmonakhov@gmail.com \
--to=dmonakhov@gmail.com \
--cc=linux-ext4@vger.kernel.org \
--cc=tytso@mit.edu \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.