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" <tytso@mit.edu>
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 07d9def..5042c87 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -234,7 +234,8 @@
* protection against it
*/
sb_start_intwrite(inode->i_sb);
- handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
+ ext4_blocks_for_truncate(inode)+3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
@@ -656,7 +657,8 @@
if (map.m_len > DIO_MAX_BLOCKS)
map.m_len = DIO_MAX_BLOCKS;
dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
- handle = ext4_journal_start(inode, dio_credits);
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+ dio_credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
return ret;
@@ -881,7 +883,7 @@
}
retry:
- handle = ext4_journal_start(inode, needed_blocks);
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
@@ -1881,7 +1883,8 @@
* references to buffers so we are safe */
unlock_page(page);
- handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+ ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
@@ -2312,7 +2315,8 @@
needed_blocks = ext4_da_writepages_trans_blocks(inode);
/* start a new transaction*/
- handle = ext4_journal_start(inode, needed_blocks);
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+ needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
@@ -2468,7 +2472,7 @@
* to journalling the i_disksize update if writes to the end
* of file which has an already mapped buffer.
*/
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
@@ -4215,8 +4219,9 @@
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
- handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
- EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3);
+ handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
+ (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) +
+ EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)) + 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
@@ -4251,7 +4256,7 @@
(attr->ia_size < inode->i_size)) {
handle_t *handle;
- handle = ext4_journal_start(inode, 3);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
@@ -4271,7 +4276,8 @@
attr->ia_size);
if (error) {
/* Do as much error cleanup as possible */
- handle = ext4_journal_start(inode, 3);
+ handle = ext4_journal_start(inode,
+ EXT4_HT_INODE, 3);
if (IS_ERR(handle)) {
ext4_orphan_del(NULL, inode);
goto err_out;
@@ -4612,7 +4618,7 @@
{
handle_t *handle;
- handle = ext4_journal_start(inode, 2);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle))
goto out;
@@ -4713,7 +4719,7 @@
/* Finally we can mark the inode as dirty. */
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -4791,7 +4797,8 @@
else
get_block = ext4_get_block;
retry_alloc:
- handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+ ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = VM_FAULT_SIGBUS;
goto out;