ext4: Retry block reservation From: Aneesh Kumar K.V 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 Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 8 +++++++- fs/ext4/inode.c | 14 +++++++++++--- fs/ext4/mballoc.c | 7 ++++++- 3 files changed, 24 insertions(+), 5 deletions(-) Index: linux-2.6.27-rc3/fs/ext4/balloc.c =================================================================== --- linux-2.6.27-rc3.orig/fs/ext4/balloc.c 2008-08-27 09:45:05.000000000 -0700 +++ linux-2.6.27-rc3/fs/ext4/balloc.c 2008-08-27 13:54:26.000000000 -0700 @@ -1736,10 +1736,16 @@ /* * 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. Index: linux-2.6.27-rc3/fs/ext4/inode.c =================================================================== --- linux-2.6.27-rc3.orig/fs/ext4/inode.c 2008-08-27 09:45:05.000000000 -0700 +++ linux-2.6.27-rc3/fs/ext4/inode.c 2008-08-27 13:54:26.000000000 -0700 @@ -1521,6 +1521,7 @@ 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; @@ -1529,6 +1530,7 @@ * 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); @@ -1539,6 +1541,10 @@ 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; @@ -1825,20 +1831,18 @@ 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 @@ -1871,6 +1875,10 @@ 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); Index: linux-2.6.27-rc3/fs/ext4/mballoc.c =================================================================== --- linux-2.6.27-rc3.orig/fs/ext4/mballoc.c 2008-08-27 09:45:05.000000000 -0700 +++ linux-2.6.27-rc3/fs/ext4/mballoc.c 2008-08-27 13:54:26.000000000 -0700 @@ -4394,7 +4394,12 @@ /* * 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; }