From: Chris Maosn <mason@xxxxxxxx>
Subject: 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@xxxxxxxx>
--- a/fs/reiserfs/journal.c Fri Apr 14 13:10:47 2006 -0400
+++ b/fs/reiserfs/journal.c Sun May 07 22:07:38 2006 -0400
@@ -1189,6 +1189,21 @@ 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,
@@ -1605,6 +1620,31 @@ static int flush_journal_list(struct sup
up(&journal->j_flush_sem);
put_fs_excl();
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,
@@ -3436,16 +3476,6 @@ 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);
- }
}
/*
@@ -3847,7 +3877,9 @@ 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;
--
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
