From: "Aneesh Kumar K.V" Subject: [PATCH -V3 04/11] ext4: Add percpu dirty block accounting. Date: Wed, 27 Aug 2008 20:58:29 +0530 Message-ID: <1219850916-8986-4-git-send-email-aneesh.kumar@linux.vnet.ibm.com> References: <1219850916-8986-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com> <1219850916-8986-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com> <1219850916-8986-3-git-send-email-aneesh.kumar@linux.vnet.ibm.com> Cc: linux-ext4@vger.kernel.org, "Aneesh Kumar K.V" To: cmm@us.ibm.com, tytso@mit.edu, sandeen@redhat.com Return-path: Received: from e28smtp04.in.ibm.com ([59.145.155.4]:53740 "EHLO e28esmtp04.in.ibm.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1756155AbYH0P26 (ORCPT ); Wed, 27 Aug 2008 11:28:58 -0400 Received: from d28relay04.in.ibm.com (d28relay04.in.ibm.com [9.184.220.61]) by e28esmtp04.in.ibm.com (8.13.1/8.13.1) with ESMTP id m7RFSt2i003910 for ; Wed, 27 Aug 2008 20:58:55 +0530 Received: from d28av05.in.ibm.com (d28av05.in.ibm.com [9.184.220.67]) by d28relay04.in.ibm.com (8.13.8/8.13.8/NCO v9.0) with ESMTP id m7RFStgu1454168 for ; Wed, 27 Aug 2008 20:58:55 +0530 Received: from d28av05.in.ibm.com (loopback [127.0.0.1]) by d28av05.in.ibm.com (8.13.1/8.13.3) with ESMTP id m7RFStnB021643 for ; Wed, 27 Aug 2008 20:58:55 +0530 In-Reply-To: <1219850916-8986-3-git-send-email-aneesh.kumar@linux.vnet.ibm.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: This patch add dirty block accounting using percpu_counters. Delayed allocation block reservation is now done by updating dirty block counter. In the later patch we switch to non delalloc mode if the filesystem free blocks is < that 150 % of total filesystem dirty blocks Signed-off-by: Aneesh Kumar K.V --- fs/ext4/balloc.c | 59 +++++++++++++++++++++++++++++++++------------------- fs/ext4/ext4_sb.h | 1 + fs/ext4/inode.c | 22 +++++++++--------- fs/ext4/mballoc.c | 17 ++------------ fs/ext4/super.c | 8 ++++++- 5 files changed, 59 insertions(+), 48 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 5767332..b19346a 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -1605,26 +1605,38 @@ ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, 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; } @@ -1640,23 +1652,28 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi, 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; } @@ -1943,13 +1960,11 @@ ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode, 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 + */ + 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 --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h index 6300226..0fa3762 100644 --- a/fs/ext4/ext4_sb.h +++ b/fs/ext4/ext4_sb.h @@ -59,6 +59,7 @@ 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 --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 98a998b..14ec7d1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1030,19 +1030,20 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) 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); } @@ -1588,8 +1589,8 @@ static void ext4_da_release_space(struct inode *inode, int to_free) 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); @@ -2471,7 +2472,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, 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 --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 419009f..4da4b9a 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2971,22 +2971,11 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, 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); - } - + 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, ac->ac_b_ex.fe_group); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ed77786..7b9db51 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -520,6 +520,7 @@ static void ext4_put_super(struct super_block *sb) 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++) @@ -2259,6 +2260,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) 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; @@ -2491,6 +2495,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) 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]); @@ -3164,7 +3169,8 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) 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)) -- 1.6.0.1.90.g27a6e