summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorChris Mason <mason@suse.com>2006-09-29 01:59:56 -0700
committerLinus Torvalds <torvalds@g5.osdl.org>2006-09-29 09:18:11 -0700
commita3172027148120b8f8797cbecc7d0a0b215736a1 (patch)
tree9da7b5eafe136c8c5b9e76e9a9cccd70899df252
parent25736b1c692d436508585d1d710912e6f76be2d8 (diff)
[PATCH] Fix reiserfs latencies caused by data=ordered
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@suse.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--fs/reiserfs/journal.c54
1 files changed, 43 insertions, 11 deletions
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 9b3672d6936..e6b5ccf23f1 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -1186,6 +1186,21 @@ static struct reiserfs_journal_list *find_newer_jl_for_cn(struct
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 super_block *s,
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(struct super_block *s)
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;