From 9924a92a8c217576bd2a2b1bbbb854462f1a00ae Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 8 Feb 2013 21:59:22 -0500 Subject: ext4: pass context information to jbd2__journal_start() So we can better understand what bits of ext4 are responsible for long-running jbd2 handles, use jbd2__journal_start() so we can pass context information for logging purposes. The recommended way for finding the longer-running handles is: T=/sys/kernel/debug/tracing EVENT=$T/events/jbd2/jbd2_handle_stats echo "interval > 5" > $EVENT/filter echo 1 > $EVENT/enable ./run-my-fs-benchmark cat $T/trace > /tmp/problem-handles This will list handles that were active for longer than 20ms. Having longer-running handles is bad, because a commit started at the wrong time could stall for those 20+ milliseconds, which could delay an fsync() or an O_SYNC operation. Here is an example line from the trace file describing a handle which lived on for 311 jiffies, or over 1.2 seconds: postmark-2917 [000] .... 196.435786: jbd2_handle_stats: dev 254,32 tid 570 type 2 line_no 2541 interval 311 sync 0 requested_blocks 1 dirtied_blocks 0 Signed-off-by: "Theodore Ts'o" --- fs/ext4/ialloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/ialloc.c') diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 3f32c8012447..10bd6fecc9ff 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1137,7 +1137,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) goto out; - handle = ext4_journal_start_sb(sb, 1); + handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; -- cgit v1.2.3 From 1139575a927010390c6b38e4215a6d741b056074 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 9 Feb 2013 16:27:09 -0500 Subject: ext4: start handle at the last possible moment when creating inodes In ext4_{create,mknod,mkdir,symlink}(), don't start the journal handle until the inode has been succesfully allocated. In order to do this, we need to start the handle in the ext4_new_inode(). So create a new variant of this function, ext4_new_inode_start_handle(), so the handle can be created at the last possible minute, before we need to modify the inode allocation bitmap block. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ialloc.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'fs/ext4/ialloc.c') diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 10bd6fecc9ff..91d8fe3aced3 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -634,8 +634,10 @@ static int find_group_other(struct super_block *sb, struct inode *parent, * For other inodes, search forward from the parent directory's block * group to find a free inode. */ -struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode, - const struct qstr *qstr, __u32 goal, uid_t *owner) +struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, + umode_t mode, const struct qstr *qstr, + __u32 goal, uid_t *owner, int handle_type, + unsigned int line_no, int nblocks) { struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; @@ -725,6 +727,15 @@ repeat_in_this_group: "inode=%lu", ino + 1); continue; } + if (!handle) { + BUG_ON(nblocks <= 0); + handle = __ext4_journal_start_sb(dir->i_sb, line_no, + handle_type, nblocks); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto fail; + } + } BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode_bitmap_bh); if (err) -- cgit v1.2.3 From 8de5c325b4ee7d5b23b95edd28b81c9a2a9f427f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 14 Feb 2013 15:11:41 -0500 Subject: ext4: use KERN_WARNING for warning messages Some messages printed related to a WARN_ON(1) were printed using KERN_NOTICE. Use KERN_WARNING or ext4_warning() instead so that context related to the WARN_ON() is printed at the same printk warning level (and log files, etc.) Signed-off-by: "Theodore Ts'o" --- fs/ext4/ialloc.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'fs/ext4/ialloc.c') diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 91d8fe3aced3..32fd2b9075dd 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1028,17 +1028,17 @@ iget_failed: inode = NULL; bad_orphan: ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino); - printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n", + printk(KERN_WARNING "ext4_test_bit(bit=%d, block=%llu) = %d\n", bit, (unsigned long long)bitmap_bh->b_blocknr, ext4_test_bit(bit, bitmap_bh->b_data)); - printk(KERN_NOTICE "inode=%p\n", inode); + printk(KERN_WARNING "inode=%p\n", inode); if (inode) { - printk(KERN_NOTICE "is_bad_inode(inode)=%d\n", + printk(KERN_WARNING "is_bad_inode(inode)=%d\n", is_bad_inode(inode)); - printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n", + printk(KERN_WARNING "NEXT_ORPHAN(inode)=%u\n", NEXT_ORPHAN(inode)); - printk(KERN_NOTICE "max_ino=%lu\n", max_ino); - printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink); + printk(KERN_WARNING "max_ino=%lu\n", max_ino); + printk(KERN_WARNING "i_nlink=%u\n", inode->i_nlink); /* Avoid freeing blocks if we got a bad deleted inode */ if (inode->i_nlink == 0) inode->i_blocks = 0; -- cgit v1.2.3