lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

JFS: Improve sync barrier processing

Browse Source 
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>
This commit is contained in:
Dave Kleikamp
2005-07-27 09:17:57 -05:00
parent de8fd087b2
commit cbc3d65ebc
4 changed files with 26 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fs/jfs/jfs_logmgr.h
View File

@@ -510,6 +510,6 @@ extern int lmLogFormat(struct jfs_log *log, s64 logAddress, int logSize);
extern int lmGroupCommit(struct jfs_log *, struct tblock *);
extern int jfsIOWait(void *);
extern void jfs_flush_journal(struct jfs_log * log, int wait);
extern void jfs_syncpt(struct jfs_log *log);
extern void jfs_syncpt(struct jfs_log *log, int hard_sync);
#endif /* _H_JFS_LOGMGR */