ext4: Retry block reservation

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@linux.vnet.ibm.com>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1707850301d6b77a4ee5da629d51b6fc37299dc6..57909882c0846e6dad354566e59d9d905fd698a0 100644 (file)
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -1738,10 +1738,16 @@ ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode,
                /*
                 * 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.

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b778d5a33ea7c32f1fdebfce5c0be300f5e5b1de..eb9d449817d06d7d9302f426873ef730641e75dc 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1521,6 +1521,7 @@ static int ext4_journalled_write_end(struct file *file,
 
 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 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
         * 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 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 
        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 void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
 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 @@ static int  mpage_da_map_blocks(struct mpage_da_data *mpd)
                                  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);

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 2c10b5058a8da7d4604173310155cfb0427bc639..e4f30de11a9dcd14e53e18d17718ffcf0fa8e170 100644 (file)
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4395,7 +4395,12 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
                /*
                 * 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;
                }