The patch titled
Fix reiserfs latencies caused by data=ordered
has been added to the -mm tree. Its filename is
fix-reiserfs-latencies-caused-by-data=ordered.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: Fix reiserfs latencies caused by data=ordered
From: Chris Mason <mason@xxxxxxxx>
ReiserFS does periodic cleanup of old transactions in order to limit the
length of time a journal replay may take after a crash. Sometimes, writing
metadata from an old (already committed) transaction may require committing
a newer transaction, which also requires writing all data=ordered buffers.
This can cause very long stalls on journal_begin.
This patch makes sure new transactions will not need to be committed before
trying a periodic reclaim of an old transaction. It is low risk because if
a bad decision is made, it just means a slightly longer journal replay
after a crash.
Signed-off-by: Chris Mason <mason@xxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
diff -puN fs/reiserfs/journal.c~fix-reiserfs-latencies-caused-by-data=ordered fs/reiserfs/journal.c
--- a/fs/reiserfs/journal.c~fix-reiserfs-latencies-caused-by-data=ordered
+++ a/fs/reiserfs/journal.c
@@ -1186,6 +1186,21 @@ static struct reiserfs_journal_list *fin
return NULL;
}
+static int newer_jl_done(struct reiserfs_journal_cnode *cn)
+{
+ struct super_block *sb = cn->sb;
+ b_blocknr_t blocknr = cn->blocknr;
+
+ cn = cn->hprev;
+ while (cn) {
+ if (cn->sb == sb && cn->blocknr == blocknr && cn->jlist &&
+ atomic_read(&cn->jlist->j_commit_left) != 0)
+ return 0;
+ cn = cn->hprev;
+ }
+ return 1;
+}
+
static void remove_journal_hash(struct super_block *,
struct reiserfs_journal_cnode **,
struct reiserfs_journal_list *, unsigned long,
@@ -1604,6 +1619,31 @@ static int flush_journal_list(struct sup
return err;
}
+static int test_transaction(struct super_block *s,
+ struct reiserfs_journal_list *jl)
+{
+ struct reiserfs_journal_cnode *cn;
+
+ if (jl->j_len == 0 || atomic_read(&jl->j_nonzerolen) == 0)
+ return 1;
+
+ cn = jl->j_realblock;
+ while (cn) {
+ /* if the blocknr == 0, this has been cleared from the hash,
+ ** skip it
+ */
+ if (cn->blocknr == 0) {
+ goto next;
+ }
+ if (cn->bh && !newer_jl_done(cn))
+ return 0;
+ next:
+ cn = cn->next;
+ cond_resched();
+ }
+ return 0;
+}
+
static int write_one_transaction(struct super_block *s,
struct reiserfs_journal_list *jl,
struct buffer_chunk *chunk)
@@ -3433,16 +3473,6 @@ static void flush_async_commits(void *p)
flush_commit_list(p_s_sb, jl, 1);
}
unlock_kernel();
- /*
- * this is a little racey, but there's no harm in missing
- * the filemap_fdata_write
- */
- if (!atomic_read(&journal->j_async_throttle)
- && !reiserfs_is_journal_aborted(journal)) {
- atomic_inc(&journal->j_async_throttle);
- filemap_fdatawrite(p_s_sb->s_bdev->bd_inode->i_mapping);
- atomic_dec(&journal->j_async_throttle);
- }
}
/*
@@ -3844,7 +3874,9 @@ static void flush_old_journal_lists(stru
entry = journal->j_journal_list.next;
jl = JOURNAL_LIST_ENTRY(entry);
/* this check should always be run, to send old lists to disk */
- if (jl->j_timestamp < (now - (JOURNAL_MAX_TRANS_AGE * 4))) {
+ if (jl->j_timestamp < (now - (JOURNAL_MAX_TRANS_AGE * 4)) &&
+ atomic_read(&jl->j_commit_left) == 0 &&
+ test_transaction(s, jl)) {
flush_used_journal_lists(s, jl);
} else {
break;
_
Patches currently in -mm which might be from mason@xxxxxxxx are
fix-reiserfs-lock-inversion-of-bkl-vs-inode-semaphore.patch
reiserfs_write_full_page-should-not-get_block-past-eof.patch
reiserfs-warn-about-the-useless-nolargeio-option.patch
make-reiserfs-default-to-barrier=flush.patch
make-ext3-mount-default-to-barrier=1.patch
reiserfs_fsync-should-only-use-barriers-when-they-are-enabled.patch
fix-reiserfs-latencies-caused-by-data=ordered.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
