summaryrefslogtreecommitdiffstats
path: root/fs/jfs/super.c
diff options
context:
space:
mode:
authorDave Kleikamp <shaggy@austin.ibm.com>2005-07-27 09:17:57 -0500
committerDave Kleikamp <shaggy@austin.ibm.com>2005-07-27 09:17:57 -0500
commitcbc3d65ebcb0c494183d45cf202a53352cbf3871 (patch)
tree4f05bef55fd76ddd7668187e84e7fbc16a4849f6 /fs/jfs/super.c
parentde8fd087b280797977b012a4275ee53ff2999f3f (diff)
downloadop-kernel-dev-cbc3d65ebcb0c494183d45cf202a53352cbf3871.zip
op-kernel-dev-cbc3d65ebcb0c494183d45cf202a53352cbf3871.tar.gz
JFS: Improve sync barrier processing
Under heavy load, hot metadata pages are often locked by non-committed transactions, making them difficult to flush to disk. This prevents the sync point from advancing past a transaction that had modified the page. There is a point during the sync barrier processing where all outstanding transactions have been committed to disk, but no new transaction have been allowed to proceed. This is the best time to write the metadata. Signed-off-by: Dave Kleikamp <shaggy@austin.ibm.com>
Diffstat (limited to 'fs/jfs/super.c')
-rw-r--r--fs/jfs/super.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index ee32211..c2abdae 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -531,7 +531,7 @@ static int jfs_sync_fs(struct super_block *sb, int wait)
/* log == NULL indicates read-only mount */
if (log) {
jfs_flush_journal(log, wait);
- jfs_syncpt(log);
+ jfs_syncpt(log, 0);
}
return 0;
OpenPOWER on IntegriCloud