ocfs2: improve recovery performance

Orabug: 24308229

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

Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>

diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index afa750cfb7fda34abd48eeb637ad5a84f7f530bc..1602f0609fda491947899e4ae73801722f33cad7 100644 (file)
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1132,10 +1132,8 @@ 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;
@@ -1147,29 +1145,35 @@ static int ocfs2_force_read_journal(struct inode *inode)
                        goto bail;
                }
 
-               if (p_blocks > CONCURRENT_JOURNAL_FILL)
-                       p_blocks = CONCURRENT_JOURNAL_FILL;
+               for (i = 0; i < p_blocks; i++) {
+                       bh = __find_get_block(osb->sb->s_bdev, p_blkno,
+                                       osb->sb->s_blocksize);
+                       /* block not cached. */
+                       if (!bh) {
+                               p_blkno++;
+                               continue;
+                       }
 
-               /* 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;
-               }
+                       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;
+                       p_blkno++;
                }
 
                v_blkno += p_blocks;
        }
 
 bail:
-       for(i = 0; i < CONCURRENT_JOURNAL_FILL; i++)
-               brelse(bhs[i]);
        return status;
 }