From: Junxiao Bi <junxiao.bi@xxxxxxxxxx> Subject: 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@xxxxxxxxxxxxxxxxxxxx: clean up the for loop p_blkno handling] Link: http://lkml.kernel.org/r/1466155682-24656-1-git-send-email-junxiao.bi@xxxxxxxxxx Signed-off-by: Junxiao Bi <junxiao.bi@xxxxxxxxxx> Reviewed-by: Joseph Qi <joseph.qi@xxxxxxxxxx> Cc: "Gang He" <ghe@xxxxxxxx> Cc: Mark Fasheh <mfasheh@xxxxxxx> Cc: Joel Becker <jlbec@xxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/ocfs2/journal.c | 41 +++++++++++++++++++++-------------------- 1 file changed, 21 insertions(+), 20 deletions(-) diff -puN fs/ocfs2/journal.c~ocfs2-improve-recovery-performance fs/ocfs2/journal.c --- a/fs/ocfs2/journal.c~ocfs2-improve-recovery-performance +++ a/fs/ocfs2/journal.c @@ -1159,10 +1159,8 @@ static int ocfs2_force_read_journal(stru 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(stru 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; } _ -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
