summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_trans.c
diff options
context:
space:
mode:
authorDavid Chinner <dgc@sgi.com>2007-05-24 15:26:31 +1000
committerTim Shimmin <tes@chook.melbourne.sgi.com>2007-07-14 15:28:50 +1000
commit92821e2ba4ae26887223326fb0b95cdab963b768 (patch)
treea40a2ef10e5b0791df3e522f3139193d39bf2454 /fs/xfs/xfs_trans.c
parent3260f78ad6d5b788e78ea709d377f58e569bee41 (diff)
downloadop-kernel-dev-92821e2ba4ae26887223326fb0b95cdab963b768.zip
op-kernel-dev-92821e2ba4ae26887223326fb0b95cdab963b768.tar.gz
[XFS] Lazy Superblock Counters
When we have a couple of hundred transactions on the fly at once, they all typically modify the on disk superblock in some way. create/unclink/mkdir/rmdir modify inode counts, allocation/freeing modify free block counts. When these counts are modified in a transaction, they must eventually lock the superblock buffer and apply the mods. The buffer then remains locked until the transaction is committed into the incore log buffer. The result of this is that with enough transactions on the fly the incore superblock buffer becomes a bottleneck. The result of contention on the incore superblock buffer is that transaction rates fall - the more pressure that is put on the superblock buffer, the slower things go. The key to removing the contention is to not require the superblock fields in question to be locked. We do that by not marking the superblock dirty in the transaction. IOWs, we modify the incore superblock but do not modify the cached superblock buffer. In short, we do not log superblock modifications to critical fields in the superblock on every transaction. In fact we only do it just before we write the superblock to disk every sync period or just before unmount. This creates an interesting problem - if we don't log or write out the fields in every transaction, then how do the values get recovered after a crash? the answer is simple - we keep enough duplicate, logged information in other structures that we can reconstruct the correct count after log recovery has been performed. It is the AGF and AGI structures that contain the duplicate information; after recovery, we walk every AGI and AGF and sum their individual counters to get the correct value, and we do a transaction into the log to correct them. An optimisation of this is that if we have a clean unmount record, we know the value in the superblock is correct, so we can avoid the summation walk under normal conditions and so mount/recovery times do not change under normal operation. One wrinkle that was discovered during development was that the blocks used in the freespace btrees are never accounted for in the AGF counters. This was once a valid optimisation to make; when the filesystem is full, the free space btrees are empty and consume no space. Hence when it matters, the "accounting" is correct. But that means the when we do the AGF summations, we would not have a correct count and xfs_check would complain. Hence a new counter was added to track the number of blocks used by the free space btrees. This is an *on-disk format change*. As a result of this, lazy superblock counters are a mkfs option and at the moment on linux there is no way to convert an old filesystem. This is possible - xfs_db can be used to twiddle the right bits and then xfs_repair will do the format conversion for you. Similarly, you can convert backwards as well. At some point we'll add functionality to xfs_admin to do the bit twiddling easily.... SGI-PV: 964999 SGI-Modid: xfs-linux-melb:xfs-kern:28652a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Tim Shimmin <tes@sgi.com>
Diffstat (limited to 'fs/xfs/xfs_trans.c')
-rw-r--r--fs/xfs/xfs_trans.c58
1 files changed, 46 insertions, 12 deletions
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index cc2d609..7133fd9 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -427,6 +427,14 @@ undo_blocks:
*
* Mark the transaction structure to indicate that the superblock
* needs to be updated before committing.
+ *
+ * Because we may not be keeping track of allocated/free inodes and
+ * used filesystem blocks in the superblock, we do not mark the
+ * superblock dirty in this transaction if we modify these fields.
+ * We still need to update the transaction deltas so that they get
+ * applied to the incore superblock, but we don't want them to
+ * cause the superblock to get locked and logged if these are the
+ * only fields in the superblock that the transaction modifies.
*/
void
xfs_trans_mod_sb(
@@ -434,13 +442,19 @@ xfs_trans_mod_sb(
uint field,
int64_t delta)
{
+ uint32_t flags = (XFS_TRANS_DIRTY|XFS_TRANS_SB_DIRTY);
+ xfs_mount_t *mp = tp->t_mountp;
switch (field) {
case XFS_TRANS_SB_ICOUNT:
tp->t_icount_delta += delta;
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+ flags &= ~XFS_TRANS_SB_DIRTY;
break;
case XFS_TRANS_SB_IFREE:
tp->t_ifree_delta += delta;
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+ flags &= ~XFS_TRANS_SB_DIRTY;
break;
case XFS_TRANS_SB_FDBLOCKS:
/*
@@ -453,6 +467,8 @@ xfs_trans_mod_sb(
ASSERT(tp->t_blk_res_used <= tp->t_blk_res);
}
tp->t_fdblocks_delta += delta;
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+ flags &= ~XFS_TRANS_SB_DIRTY;
break;
case XFS_TRANS_SB_RES_FDBLOCKS:
/*
@@ -462,6 +478,8 @@ xfs_trans_mod_sb(
*/
ASSERT(delta < 0);
tp->t_res_fdblocks_delta += delta;
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+ flags &= ~XFS_TRANS_SB_DIRTY;
break;
case XFS_TRANS_SB_FREXTENTS:
/*
@@ -544,18 +562,23 @@ xfs_trans_apply_sb_deltas(
(tp->t_ag_freeblks_delta + tp->t_ag_flist_delta +
tp->t_ag_btree_delta));
- if (tp->t_icount_delta != 0) {
- INT_MOD(sbp->sb_icount, ARCH_CONVERT, tp->t_icount_delta);
- }
- if (tp->t_ifree_delta != 0) {
- INT_MOD(sbp->sb_ifree, ARCH_CONVERT, tp->t_ifree_delta);
- }
+ /*
+ * Only update the superblock counters if we are logging them
+ */
+ if (!xfs_sb_version_haslazysbcount(&(tp->t_mountp->m_sb))) {
+ if (tp->t_icount_delta != 0) {
+ INT_MOD(sbp->sb_icount, ARCH_CONVERT, tp->t_icount_delta);
+ }
+ if (tp->t_ifree_delta != 0) {
+ INT_MOD(sbp->sb_ifree, ARCH_CONVERT, tp->t_ifree_delta);
+ }
- if (tp->t_fdblocks_delta != 0) {
- INT_MOD(sbp->sb_fdblocks, ARCH_CONVERT, tp->t_fdblocks_delta);
- }
- if (tp->t_res_fdblocks_delta != 0) {
- INT_MOD(sbp->sb_fdblocks, ARCH_CONVERT, tp->t_res_fdblocks_delta);
+ if (tp->t_fdblocks_delta != 0) {
+ INT_MOD(sbp->sb_fdblocks, ARCH_CONVERT, tp->t_fdblocks_delta);
+ }
+ if (tp->t_res_fdblocks_delta != 0) {
+ INT_MOD(sbp->sb_fdblocks, ARCH_CONVERT, tp->t_res_fdblocks_delta);
+ }
}
if (tp->t_frextents_delta != 0) {
@@ -627,6 +650,7 @@ xfs_trans_unreserve_and_mod_sb(
{
xfs_mod_sb_t msb[14]; /* If you add cases, add entries */
xfs_mod_sb_t *msbp;
+ xfs_mount_t *mp = tp->t_mountp;
/* REFERENCED */
int error;
int rsvd;
@@ -659,8 +683,15 @@ xfs_trans_unreserve_and_mod_sb(
* The t_res_fdblocks_delta and t_res_frextents_delta fields are
* explicitly NOT applied to the in-core superblock.
* The idea is that that has already been done.
+ *
+ * If we are not logging superblock counters, then the inode
+ * allocated/free and used block counts are not updated in the
+ * on disk superblock. In this case, XFS_TRANS_SB_DIRTY will
+ * not be set when the transaction is updated but we still need
+ * to update the incore superblock with the changes.
*/
- if (tp->t_flags & XFS_TRANS_SB_DIRTY) {
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb) ||
+ (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
if (tp->t_icount_delta != 0) {
msbp->msb_field = XFS_SBS_ICOUNT;
msbp->msb_delta = tp->t_icount_delta;
@@ -676,6 +707,9 @@ xfs_trans_unreserve_and_mod_sb(
msbp->msb_delta = tp->t_fdblocks_delta;
msbp++;
}
+ }
+
+ if (tp->t_flags & XFS_TRANS_SB_DIRTY) {
if (tp->t_frextents_delta != 0) {
msbp->msb_field = XFS_SBS_FREXTENTS;
msbp->msb_delta = tp->t_frextents_delta;
OpenPOWER on IntegriCloud