From: "Jayson R. King" <dev@jaysonking.com>
To: LKML <linux-kernel@vger.kernel.org>,
Stable team <stable@kernel.org>,
Greg Kroah-Hartman <gregkh@suse.de>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>,
Mingming Cao <cmm@us.ibm.com>, "Theodore Ts'o" <tytso@mit.edu>,
linux-ext4@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Jayson King <dev@jaysonking.com>
Subject: [04/11] ext4: Add percpu dirty block accounting.
Date: Sat, 27 Feb 2010 00:32:34 -0600 [thread overview]
Message-ID: <4B88BC82.2000101@jaysonking.com> (raw)
In-Reply-To: <4B88BA1B.4050500@jaysonking.com>
From: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Date: Fri Oct 10 09:39:00 2008 -0400
Subject: ext4: Add percpu dirty block accounting.
commit 6bc6e63fcd7dac9e633ea29f1fddd9580ab28f3f upstream.
This patch adds dirty block accounting using percpu_counters. Delayed
allocation block reservation is now done by updating dirty block
counter. In a later patch we switch to non delalloc mode if the
filesystem free blocks is greater than 150% of total filesystem dirty
blocks
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Mingming Cao<cmm@us.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Jayson R. King <dev@jaysonking.com>
---
fs/ext4/balloc.c | 62 ++++++++++++++++++++++++++++----------------
fs/ext4/ext4_sb.h | 1
fs/ext4/inode.c | 22 +++++++--------
fs/ext4/mballoc.c | 31 +++++++++-------------
fs/ext4/super.c | 8 ++++-
5 files changed, 73 insertions(+), 51 deletions(-)
diff -urNp linux-2.6.27.orig/fs/ext4/balloc.c linux-2.6.27/fs/ext4/balloc.c
--- linux-2.6.27.orig/fs/ext4/balloc.c 2010-02-26 14:21:03.148252808 -0600
+++ linux-2.6.27/fs/ext4/balloc.c 2010-02-26 14:21:14.292252864 -0600
@@ -1757,26 +1757,38 @@ out:
int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
ext4_fsblk_t nblocks)
{
- s64 free_blocks;
+ s64 free_blocks, dirty_blocks;
ext4_fsblk_t root_blocks = 0;
struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+ struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
- free_blocks = percpu_counter_read(fbc);
+ free_blocks = percpu_counter_read_positive(fbc);
+ dirty_blocks = percpu_counter_read_positive(dbc);
if (!capable(CAP_SYS_RESOURCE) &&
sbi->s_resuid != current->fsuid &&
(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
root_blocks = ext4_r_blocks_count(sbi->s_es);
- if (free_blocks - (nblocks + root_blocks) < EXT4_FREEBLOCKS_WATERMARK)
- free_blocks = percpu_counter_sum(&sbi->s_freeblocks_counter);
-
- if (free_blocks < (root_blocks + nblocks))
+ if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+ EXT4_FREEBLOCKS_WATERMARK) {
+ free_blocks = percpu_counter_sum(fbc);
+ dirty_blocks = percpu_counter_sum(dbc);
+ if (dirty_blocks < 0) {
+ printk(KERN_CRIT "Dirty block accounting "
+ "went wrong %lld\n",
+ dirty_blocks);
+ }
+ }
+ /* Check whether we have space after
+ * accounting for current dirty blocks
+ */
+ if (free_blocks < ((s64)(root_blocks + nblocks) + dirty_blocks))
/* we don't have free space */
return -ENOSPC;
- /* reduce fs free blocks counter */
- percpu_counter_sub(fbc, nblocks);
+ /* Add the blocks to nblocks */
+ percpu_counter_add(dbc, nblocks);
return 0;
}
@@ -1792,23 +1804,28 @@ int ext4_claim_free_blocks(struct ext4_s
ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
ext4_fsblk_t nblocks)
{
- ext4_fsblk_t free_blocks;
+ ext4_fsblk_t free_blocks, dirty_blocks;
ext4_fsblk_t root_blocks = 0;
+ struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+ struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
- free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+ free_blocks = percpu_counter_read_positive(fbc);
+ dirty_blocks = percpu_counter_read_positive(dbc);
if (!capable(CAP_SYS_RESOURCE) &&
sbi->s_resuid != current->fsuid &&
(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
root_blocks = ext4_r_blocks_count(sbi->s_es);
- if (free_blocks - (nblocks + root_blocks) < EXT4_FREEBLOCKS_WATERMARK)
- free_blocks = percpu_counter_sum_positive(&sbi->s_freeblocks_counter);
-
- if (free_blocks <= root_blocks)
+ if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+ EXT4_FREEBLOCKS_WATERMARK) {
+ free_blocks = percpu_counter_sum_positive(fbc);
+ dirty_blocks = percpu_counter_sum_positive(dbc);
+ }
+ if (free_blocks <= (root_blocks + dirty_blocks))
/* we don't have free space */
return 0;
- if (free_blocks - root_blocks < nblocks)
+ if (free_blocks - (root_blocks + dirty_blocks) < nblocks)
return free_blocks - root_blocks;
return nblocks;
}
@@ -2089,13 +2106,14 @@ allocated:
le16_add_cpu(&gdp->bg_free_blocks_count, -num);
gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp);
spin_unlock(sb_bgl_lock(sbi, group_no));
- if (!EXT4_I(inode)->i_delalloc_reserved_flag && (*count != num)) {
- /*
- * we allocated less blocks than we
- * claimed. Add the difference back.
- */
- percpu_counter_add(&sbi->s_freeblocks_counter, *count - num);
- }
+ percpu_counter_sub(&sbi->s_freeblocks_counter, num);
+ /*
+ * Now reduce the dirty block count also. Should not go negative
+ */
+ if (!EXT4_I(inode)->i_delalloc_reserved_flag)
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, *count);
+ else
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, num);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, group_no);
spin_lock(sb_bgl_lock(sbi, flex_group));
diff -urNp linux-2.6.27.orig/fs/ext4/ext4_sb.h linux-2.6.27/fs/ext4/ext4_sb.h
--- linux-2.6.27.orig/fs/ext4/ext4_sb.h 2010-02-26 14:10:41.167252303 -0600
+++ linux-2.6.27/fs/ext4/ext4_sb.h 2010-02-26 14:21:14.292252864 -0600
@@ -60,6 +60,7 @@ struct ext4_sb_info {
struct percpu_counter s_freeblocks_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
+ struct percpu_counter s_dirtyblocks_counter;
struct blockgroup_lock s_blockgroup_lock;
/* root of the per fs reservation window tree */
diff -urNp linux-2.6.27.orig/fs/ext4/inode.c linux-2.6.27/fs/ext4/inode.c
--- linux-2.6.27.orig/fs/ext4/inode.c 2010-02-26 14:21:03.149252723 -0600
+++ linux-2.6.27/fs/ext4/inode.c 2010-02-26 14:21:14.293252633 -0600
@@ -1032,19 +1032,20 @@ static void ext4_da_update_reserve_space
BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
- /* Account for allocated meta_blocks */
- mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
-
- /* update fs free blocks counter for truncate case */
- percpu_counter_add(&sbi->s_freeblocks_counter, mdb_free);
+ if (mdb_free) {
+ /* Account for allocated meta_blocks */
+ mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+
+ /* update fs dirty blocks counter */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
+ EXT4_I(inode)->i_allocated_meta_blocks = 0;
+ EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+ }
/* update per-inode reservations */
BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks);
EXT4_I(inode)->i_reserved_data_blocks -= used;
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- EXT4_I(inode)->i_reserved_meta_blocks = mdb;
- EXT4_I(inode)->i_allocated_meta_blocks = 0;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/*
@@ -1609,8 +1610,8 @@ static void ext4_da_release_space(struct
release = to_free + mdb_free;
- /* update fs free blocks counter for truncate case */
- percpu_counter_add(&sbi->s_freeblocks_counter, release);
+ /* update fs dirty blocks counter for truncate case */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
/* update per-inode reservations */
BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
@@ -2546,7 +2547,6 @@ static int ext4_da_write_begin(struct fi
index = pos >> PAGE_CACHE_SHIFT;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
-
retry:
/*
* With delayed allocation, we don't log the i_disksize update
diff -urNp linux-2.6.27.orig/fs/ext4/mballoc.c linux-2.6.27/fs/ext4/mballoc.c
--- linux-2.6.27.orig/fs/ext4/mballoc.c 2010-02-26 14:21:03.150252678 -0600
+++ linux-2.6.27/fs/ext4/mballoc.c 2010-02-26 14:21:14.294252546 -0600
@@ -3100,7 +3100,7 @@ void exit_ext4_mballoc(void)
*/
static noinline_for_stack int
ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
- handle_t *handle)
+ handle_t *handle, unsigned long reserv_blks)
{
struct buffer_head *bitmap_bh = NULL;
struct ext4_super_block *es;
@@ -3188,21 +3188,16 @@ ext4_mb_mark_diskspace_used(struct ext4_
le16_add_cpu(&gdp->bg_free_blocks_count, -ac->ac_b_ex.fe_len);
gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
-
+ percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
/*
- * free blocks account has already be reduced/reserved
- * at write_begin() time for delayed allocation
- * do not double accounting
+ * Now reduce the dirty block count also. Should not go negative
*/
- if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED) &&
- ac->ac_o_ex.fe_len != ac->ac_b_ex.fe_len) {
- /*
- * we allocated less blocks than we calimed
- * Add the difference back
- */
- percpu_counter_add(&sbi->s_freeblocks_counter,
- ac->ac_o_ex.fe_len - ac->ac_b_ex.fe_len);
- }
+ if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
+ /* release all the reserved blocks if non delalloc */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
+ else
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ ac->ac_b_ex.fe_len);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
@@ -4636,12 +4631,13 @@ static int ext4_mb_discard_preallocation
ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
struct ext4_allocation_request *ar, int *errp)
{
+ int freed;
struct ext4_allocation_context *ac = NULL;
struct ext4_sb_info *sbi;
struct super_block *sb;
ext4_fsblk_t block = 0;
- int freed;
- int inquota;
+ unsigned long inquota;
+ unsigned long reserv_blks = 0;
sb = ar->inode->i_sb;
sbi = EXT4_SB(sb);
@@ -4659,6 +4655,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t
*errp = -ENOSPC;
return 0;
}
+ reserv_blks = ar->len;
}
while (ar->len && DQUOT_ALLOC_BLOCK(ar->inode, ar->len)) {
ar->flags |= EXT4_MB_HINT_NOPREALLOC;
@@ -4704,7 +4701,7 @@ repeat:
ext4_mb_new_preallocation(ac);
}
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
- *errp = ext4_mb_mark_diskspace_used(ac, handle);
+ *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
if (*errp == -EAGAIN) {
/*
* drop the reference that we took
diff -urNp linux-2.6.27.orig/fs/ext4/super.c linux-2.6.27/fs/ext4/super.c
--- linux-2.6.27.orig/fs/ext4/super.c 2010-02-26 14:10:41.170252357 -0600
+++ linux-2.6.27/fs/ext4/super.c 2010-02-26 14:21:14.295252319 -0600
@@ -520,6 +520,7 @@ static void ext4_put_super(struct super_
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
@@ -2279,6 +2280,9 @@ static int ext4_fill_super(struct super_
err = percpu_counter_init(&sbi->s_dirs_counter,
ext4_count_dirs(sb));
}
+ if (!err) {
+ err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ }
if (err) {
printk(KERN_ERR "EXT4-fs: insufficient memory\n");
goto failed_mount3;
@@ -2516,6 +2520,7 @@ failed_mount3:
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
@@ -3207,7 +3212,8 @@ static int ext4_statfs(struct dentry *de
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
- buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter);
+ buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
+ percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
ext4_free_blocks_count_set(es, buf->f_bfree);
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
next prev parent reply other threads:[~2010-02-27 7:22 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-02-27 6:22 [00/11] fix ext4 deadlock on 2.6.27.y Jayson R. King
2010-02-27 6:32 ` [01/11] ext4: invalidate pages if delalloc block allocation fails Jayson R. King
2010-02-27 6:32 ` [02/11] percpu counter: clean up percpu_counter_sum_and_set() Jayson R. King
2010-02-27 6:32 ` [03/11] ext4: Make sure all the block allocation paths reserve blocks Jayson R. King
2010-02-27 6:32 ` Jayson R. King [this message]
2010-02-27 6:32 ` [05/11] ext4: Retry block reservation Jayson R. King
2010-02-27 6:32 ` [06/11] ext4: Retry block allocation if we have free blocks left Jayson R. King
2010-02-27 6:33 ` [07/11] ext4: Use tag dirty lookup during mpage_da_submit_io Jayson R. King
2010-02-27 6:33 ` [08/11] vfs: Remove the range_cont writeback mode Jayson R. King
2010-02-27 6:33 ` [09/11] vfs: Add no_nrwrite_index_update writeback control flag Jayson R. King
2010-02-27 6:33 ` [10/11] ext4: Fix file fragmentation during large file write Jayson R. King
2010-02-27 6:33 ` [11/11] ext4: Implement range_cyclic in ext4_da_writepages instead of write_cache_pages Jayson R. King
2010-02-28 3:16 ` [00/11] fix ext4 deadlock on 2.6.27.y Greg KH
2010-03-15 20:09 ` [stable] " Greg KH
2010-03-15 23:17 ` tytso
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=4B88BC82.2000101@jaysonking.com \
--to=dev@jaysonking.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=cmm@us.ibm.com \
--cc=gregkh@suse.de \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox