xfs: reduce debug overhead of dir leaf/node checks

Source kernel commit: 1fea323ff00526dcc04fbb4ee6e7d04e4e2ab0e1

On debug kernels, we call xfs_dir3_leaf_check_int() multiple times
on every directory modification. The robust hash ordering checks it
does on every entry in the leaf on every call results in a massive
CPU overhead which slows down debug kernels by a large amount.

We use xfs_dir3_leaf_check_int() for the verifiers as well, so we
can't just gut the function to reduce overhead. What we can do,
however, is reduce the work it does when it is called from the
debug interfaces, just leaving the high level checks in place and
leaving the robust validation to the verifiers. This means the debug
checks will catch gross errors, but subtle bugs might not be caught
until a verifier is run.

It is easy enough to restore the existing debug behaviour if the
developer needs it (just change a call parameter in the debug code),
but overwise the overhead makes testing large directory block sizes
on debug kernels very slow.

Profile at an unlink rate of ~80k file/s on a 64k block size
filesystem before the patch:

40.30%  [kernel]  [k] xfs_dir3_leaf_check_int
10.98%  [kernel]  [k] __xfs_dir3_data_check
8.10%  [kernel]  [k] xfs_verify_dir_ino
4.42%  [kernel]  [k] memcpy
2.22%  [kernel]  [k] xfs_dir2_data_get_ftype
1.52%  [kernel]  [k] do_raw_spin_lock

Profile after, at an unlink rate of ~125k files/s (+50% improvement)
has largely dropped the leaf verification debug overhead out of the
profile.

16.53%  [kernel]  [k] __xfs_dir3_data_check
12.53%  [kernel]  [k] xfs_verify_dir_ino
7.97%  [kernel]  [k] memcpy
3.36%  [kernel]  [k] xfs_dir2_data_get_ftype
2.86%  [kernel]  [k] __pv_queued_spin_lock_slowpath

Create shows a similar change in profile and a +25% improvement in
performance.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Eric Sandeen <sandeen@sandeen.net>

diff --git a/libxfs/xfs_dir2_leaf.c b/libxfs/xfs_dir2_leaf.c
index 0cecd698f18bc8bc0f4a753b3387c7665f3c3902..2eddb9b900a2c533e7ecafb6ea12b3f8c535a5f3 100644 (file)
--- a/libxfs/xfs_dir2_leaf.c
+++ b/libxfs/xfs_dir2_leaf.c
@@ -111,7 +111,7 @@ xfs_dir3_leaf1_check(
        } else if (leafhdr.magic != XFS_DIR2_LEAF1_MAGIC)
                return __this_address;
 
-       return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf);
+       return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf, false);
 }
 
 static inline void
@@ -137,7 +137,8 @@ xfs_failaddr_t
 xfs_dir3_leaf_check_int(
        struct xfs_mount                *mp,
        struct xfs_dir3_icleaf_hdr      *hdr,
-       struct xfs_dir2_leaf            *leaf)
+       struct xfs_dir2_leaf            *leaf,
+       bool                            expensive_checking)
 {
        struct xfs_da_geometry          *geo = mp->m_dir_geo;
        xfs_dir2_leaf_tail_t            *ltp;
@@ -160,6 +161,9 @@ xfs_dir3_leaf_check_int(
            (char *)&hdr->ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp))
                return __this_address;
 
+       if (!expensive_checking)
+               return NULL;
+
        /* Check hash value order, count stale entries.  */
        for (i = stale = 0; i < hdr->count; i++) {
                if (i + 1 < hdr->count) {
@@ -193,7 +197,7 @@ xfs_dir3_leaf_verify(
                return fa;
 
        xfs_dir2_leaf_hdr_from_disk(mp, &leafhdr, bp->b_addr);
-       return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr);
+       return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr, true);
 }
 
 static void

diff --git a/libxfs/xfs_dir2_node.c b/libxfs/xfs_dir2_node.c
index ab156a8e9990e277cd9a8d575ca1a9de0c3f7f36..4dc983c3744e1c2fcd48f7e00f22a314f5f3b64b 100644 (file)
--- a/libxfs/xfs_dir2_node.c
+++ b/libxfs/xfs_dir2_node.c
@@ -70,7 +70,7 @@ xfs_dir3_leafn_check(
        } else if (leafhdr.magic != XFS_DIR2_LEAFN_MAGIC)
                return __this_address;
 
-       return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf);
+       return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf, false);
 }
 
 static inline void

diff --git a/libxfs/xfs_dir2_priv.h b/libxfs/xfs_dir2_priv.h
index 44c6a77cba05dc352c5e1c0767862f8ebef4e560..94943ce49cab0198c42ab26c68f2e771fa125b27 100644 (file)
--- a/libxfs/xfs_dir2_priv.h
+++ b/libxfs/xfs_dir2_priv.h
@@ -127,7 +127,8 @@ xfs_dir3_leaf_find_entry(struct xfs_dir3_icleaf_hdr *leafhdr,
 extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state);
 
 extern xfs_failaddr_t xfs_dir3_leaf_check_int(struct xfs_mount *mp,
-               struct xfs_dir3_icleaf_hdr *hdr, struct xfs_dir2_leaf *leaf);
+               struct xfs_dir3_icleaf_hdr *hdr, struct xfs_dir2_leaf *leaf,
+               bool expensive_checks);
 
 /* xfs_dir2_node.c */
 void xfs_dir2_free_hdr_from_disk(struct xfs_mount *mp,