This is a note to let you know that we have just queued up the patch titled
Subject: ext4: Retry block reservation
to the 2.6.27-stable tree. Its filename is
ext4-retry-block-reservation.patch
A git repo of this tree can be found at
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
>From tytso@xxxxxxx Mon Apr 19 10:21:18 2010
From: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Date: Mon, 15 Mar 2010 20:25:59 -0400
Subject: ext4: Retry block reservation
To: stable@xxxxxxxxxx
Cc: "Theodore Ts'o" <tytso@xxxxxxx>, Ext4 Developers List <linux-ext4@xxxxxxxxxxxxxxx>, Mingming Cao <cmm@xxxxxxxxxx>, "Jayson R. King" <dev@xxxxxxxxxxxxxx>, "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Message-ID: <1268699165-17461-6-git-send-email-tytso@xxxxxxx>
From: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
commit 030ba6bc67b4f2bc5cd174f57785a1745c929abe upstream.
During block reservation if we don't have enough blocks left, retry
block reservation with smaller block counts. This makes sure we try
fallocate and DIO with smaller request size and don't fail early. The
delayed allocation reservation cannot try with smaller block count. So
retry block reservation to handle temporary disk full conditions. Also
print free blocks details if we fail block allocation during writepages.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Mingming Cao <cmm@xxxxxxxxxx>
Signed-off-by: "Theodore Ts'o" <tytso@xxxxxxx>
Signed-off-by: Jayson R. King <dev@xxxxxxxxxxxxxx>
Signed-off-by: Theodore Ts'o <tytso@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>
---
fs/ext4/balloc.c | 8 +++++++-
fs/ext4/inode.c | 14 +++++++++++---
fs/ext4/mballoc.c | 7 ++++++-
3 files changed, 24 insertions(+), 5 deletions(-)
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -1907,10 +1907,16 @@ ext4_fsblk_t ext4_old_new_blocks(handle_
/*
* With delalloc we already reserved the blocks
*/
- if (ext4_claim_free_blocks(sbi, *count)) {
+ while (*count && ext4_claim_free_blocks(sbi, *count)) {
+ /* let others to free the space */
+ yield();
+ *count = *count >> 1;
+ }
+ if (!*count) {
*errp = -ENOSPC;
return 0; /*return with ENOSPC error */
}
+ num = *count;
}
/*
* Check quota for allocation of this block.
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1549,6 +1549,7 @@ static int ext4_journalled_write_end(str
static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
{
+ int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned long md_needed, mdblocks, total = 0;
@@ -1557,6 +1558,7 @@ static int ext4_da_reserve_space(struct
* in order to allocate nrblocks
* worse case is one extent per block
*/
+repeat:
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
mdblocks = ext4_calc_metadata_amount(inode, total);
@@ -1567,6 +1569,10 @@ static int ext4_da_reserve_space(struct
if (ext4_claim_free_blocks(sbi, total)) {
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+ yield();
+ goto repeat;
+ }
return -ENOSPC;
}
EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
@@ -1864,20 +1870,18 @@ static void ext4_da_block_invalidatepage
static int mpage_da_map_blocks(struct mpage_da_data *mpd)
{
int err = 0;
+ struct buffer_head new;
struct buffer_head *lbh = &mpd->lbh;
sector_t next = lbh->b_blocknr;
- struct buffer_head new;
/*
* We consider only non-mapped and non-allocated blocks
*/
if (buffer_mapped(lbh) && !buffer_delay(lbh))
return 0;
-
new.b_state = lbh->b_state;
new.b_blocknr = 0;
new.b_size = lbh->b_size;
-
/*
* If we didn't accumulate anything
* to write simply return
@@ -1910,6 +1914,10 @@ static int mpage_da_map_blocks(struct m
lbh->b_size >> mpd->inode->i_blkbits, err);
printk(KERN_EMERG "This should not happen.!! "
"Data will be lost\n");
+ if (err == -ENOSPC) {
+ printk(KERN_CRIT "Total free blocks count %lld\n",
+ ext4_count_free_blocks(mpd->inode->i_sb));
+ }
/* invlaidate all the pages */
ext4_da_block_invalidatepages(mpd, next,
lbh->b_size >> mpd->inode->i_blkbits);
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4651,7 +4651,12 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t
/*
* With delalloc we already reserved the blocks
*/
- if (ext4_claim_free_blocks(sbi, ar->len)) {
+ while (ar->len && ext4_claim_free_blocks(sbi, ar->len)) {
+ /* let others to free the space */
+ yield();
+ ar->len = ar->len >> 1;
+ }
+ if (!ar->len) {
*errp = -ENOSPC;
return 0;
}
Patches currently in stable-queue which might be from aneesh.kumar@xxxxxxxxxxxxxxxxxx are
queue-2.6.27/ext4-fix-file-fragmentation-during-large-file-write.patch
queue-2.6.27/ext4-retry-block-allocation-if-we-have-free-blocks-left.patch
queue-2.6.27/vfs-add-no_nrwrite_index_update-writeback-control-flag.patch
queue-2.6.27/ext4-retry-block-reservation.patch
queue-2.6.27/ext4-invalidate-pages-if-delalloc-block-allocation-fails.patch
queue-2.6.27/ext4-use-tag-dirty-lookup-during-mpage_da_submit_io.patch
queue-2.6.27/vfs-remove-the-range_cont-writeback-mode.patch
queue-2.6.27/ext4-make-sure-all-the-block-allocation-paths-reserve-blocks.patch
queue-2.6.27/ext4-implement-range_cyclic-in-ext4_da_writepages-instead-of-write_cache_pages.patch
queue-2.6.27/ext4-add-percpu-dirty-block-accounting.patch
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
