ocfs2: improve recovery performance

Journal replay will be run when performing recovery for a dead node.  To
avoid the stale cache impact, all blocks of dead node's journal inode
were reloaded from disk.  This hurts the performance.  Check whether one
block is cached before reloading it can improve performance a lot.  In
my test env, the time doing recovery was improved from 120s to 1s.

[akpm@linux-foundation.org: clean up the for loop p_blkno handling]
Link: http://lkml.kernel.org/r/1466155682-24656-1-git-send-email-junxiao.bi@oracle.com
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: Joseph Qi <joseph.qi@huawei.com>
Cc: "Gang He" <ghe@suse.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index e607419cdfa46b445ff000f9cca6b2cc535093ab..a244f14c6b87737ca75c1d1c34dcf4e80ad0de40 100644 (file)
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1159,10 +1159,8 @@ static int ocfs2_force_read_journal(struct inode *inode)
        int status = 0;
        int i;
        u64 v_blkno, p_blkno, p_blocks, num_blocks;
-#define CONCURRENT_JOURNAL_FILL 32ULL
-       struct buffer_head *bhs[CONCURRENT_JOURNAL_FILL];
-
-       memset(bhs, 0, sizeof(struct buffer_head *) * CONCURRENT_JOURNAL_FILL);
+       struct buffer_head *bh = NULL;
+       struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
        num_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
        v_blkno = 0;
@@ -1174,29 +1172,32 @@ static int ocfs2_force_read_journal(struct inode *inode)
                        goto bail;
                }
 
-               if (p_blocks > CONCURRENT_JOURNAL_FILL)
-                       p_blocks = CONCURRENT_JOURNAL_FILL;
-
-               /* We are reading journal data which should not
-                * be put in the uptodate cache */
-               status = ocfs2_read_blocks_sync(OCFS2_SB(inode->i_sb),
-                                               p_blkno, p_blocks, bhs);
-               if (status < 0) {
-                       mlog_errno(status);
-                       goto bail;
-               }
+               for (i = 0; i < p_blocks; i++, p_blkno++) {
+                       bh = __find_get_block(osb->sb->s_bdev, p_blkno,
+                                       osb->sb->s_blocksize);
+                       /* block not cached. */
+                       if (!bh)
+                               continue;
+
+                       brelse(bh);
+                       bh = NULL;
+                       /* We are reading journal data which should not
+                        * be put in the uptodate cache.
+                        */
+                       status = ocfs2_read_blocks_sync(osb, p_blkno, 1, &bh);
+                       if (status < 0) {
+                               mlog_errno(status);
+                               goto bail;
+                       }
 
-               for(i = 0; i < p_blocks; i++) {
-                       brelse(bhs[i]);
-                       bhs[i] = NULL;
+                       brelse(bh);
+                       bh = NULL;
                }
 
                v_blkno += p_blocks;
        }
 
 bail:
-       for(i = 0; i < CONCURRENT_JOURNAL_FILL; i++)
-               brelse(bhs[i]);
        return status;
 }