From 6d3117b41295150d4ac70622055dd8f5529d86b2 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Sat, 21 May 2011 14:05:58 +0100 Subject: [PATCH 1/2] GFS2: Wipe directory hash table metadata when deallocating a directory The deallocation code for directories in GFS2 is largely divided into two parts. The first part deallocates any directory leaf blocks and marks the directory as being a regular file when that is complete. The second stage was identical to deallocating regular files. Regular files have their data blocks in a different address space to directories, and thus what would have been normal data blocks in a regular file (the hash table in a GFS2 directory) were deallocated correctly. However, a reference to these blocks was left in the journal (assuming of course that some previous activity had resulted in those blocks being in the journal or ail list). This patch uses the i_depth as a test of whether the inode is an exhash directory (we cannot test the inode type as that has already been changed to a regular file at this stage in deallocation) The original issue was reported by Chris Hertel as an issue he encountered running bonnie++ Reported-by: Christopher R. Hertel Cc: Abhijith Das Signed-off-by: Steven Whitehouse --- fs/gfs2/bmap.c | 2 ++ fs/gfs2/rgrp.c | 4 ++++ 2 files changed, 6 insertions(+) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 74add2ddcc3f..e65493a8ac00 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -780,6 +780,8 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, metadata = (height != ip->i_height - 1); if (metadata) revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs; + else if (ip->i_depth) + revokes = sdp->sd_inptrs; if (ip != GFS2_I(sdp->sd_rindex)) error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 7273ad3c85ba..9b780df3fd54 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1629,6 +1629,10 @@ void __gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen) gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data); gfs2_trans_add_rg(rgd); + + /* Directories keep their data in the metadata address space */ + if (ip->i_depth) + gfs2_meta_wipe(ip, bstart, blen); } /** From 26b06a6958df0f12f1a654db8598433eb89cc024 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Sat, 21 May 2011 19:21:07 +0100 Subject: [PATCH 2/2] GFS2: Wait properly when flushing the ail list The ail flush code has always relied upon log flushing to prevent it from spinning needlessly. This fixes it to wait on the last I/O request submitted (we don't need to wait for all of it) instead of either spinning with io_schedule or sleeping. As a result cpu usage of gfs2_logd is much reduced with certain workloads. Reported-by: Abhijith Das Tested-by: Abhijith Das Signed-off-by: Steven Whitehouse --- fs/gfs2/log.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index cec26c00b50d..903115f2bb34 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -228,6 +228,27 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp) return ret; } +static void gfs2_ail1_wait(struct gfs2_sbd *sdp) +{ + struct gfs2_ail *ai; + struct gfs2_bufdata *bd; + struct buffer_head *bh; + + spin_lock(&sdp->sd_ail_lock); + list_for_each_entry_reverse(ai, &sdp->sd_ail1_list, ai_list) { + list_for_each_entry(bd, &ai->ai_ail1_list, bd_ail_st_list) { + bh = bd->bd_bh; + if (!buffer_locked(bh)) + continue; + get_bh(bh); + spin_unlock(&sdp->sd_ail_lock); + wait_on_buffer(bh); + brelse(bh); + return; + } + } + spin_unlock(&sdp->sd_ail_lock); +} /** * gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced @@ -878,9 +899,9 @@ void gfs2_meta_syncfs(struct gfs2_sbd *sdp) gfs2_log_flush(sdp, NULL); for (;;) { gfs2_ail1_start(sdp); + gfs2_ail1_wait(sdp); if (gfs2_ail1_empty(sdp)) break; - msleep(10); } } @@ -920,12 +941,14 @@ int gfs2_logd(void *data) if (gfs2_ail_flush_reqd(sdp)) { gfs2_ail1_start(sdp); - io_schedule(); + gfs2_ail1_wait(sdp); gfs2_ail1_empty(sdp); gfs2_log_flush(sdp, NULL); } - wake_up(&sdp->sd_log_waitq); + if (!gfs2_ail_flush_reqd(sdp)) + wake_up(&sdp->sd_log_waitq); + t = gfs2_tune_get(sdp, gt_logd_secs) * HZ; if (freezing(current)) refrigerator();