summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2021-03-22 09:52:05 -0700
committerDarrick J. Wong <djwong@kernel.org>2021-03-25 16:47:51 -0700
commitec08c14ba28ce073b3f63c8edbee0f3c38e1b6a1 (patch)
treed561191b8fcff1f25ebe1ed301af065775c624ad
parent929f8b0deb8365122826135b36ddae55b12b4852 (diff)
downloadlinux-ec08c14ba28ce073b3f63c8edbee0f3c38e1b6a1.tar.bz2
xfs: type verification is expensive
From a concurrent rm -rf workload: 41.04% [kernel] [k] xfs_dir3_leaf_check_int 9.85% [kernel] [k] __xfs_dir3_data_check 5.60% [kernel] [k] xfs_verify_ino 5.32% [kernel] [k] xfs_agino_range 4.21% [kernel] [k] memcpy 3.06% [kernel] [k] xfs_errortag_test 2.57% [kernel] [k] xfs_dir_ino_validate 1.66% [kernel] [k] xfs_dir2_data_get_ftype 1.17% [kernel] [k] do_raw_spin_lock 1.11% [kernel] [k] xfs_verify_dir_ino 0.84% [kernel] [k] __raw_callee_save___pv_queued_spin_unlock 0.83% [kernel] [k] xfs_buf_find 0.64% [kernel] [k] xfs_log_commit_cil THere's an awful lot of overhead in just range checking inode numbers in that, but each inode number check is not a lot of code. The total is a bit over 14.5% of the CPU time is spent validating inode numbers. The problem is that they deeply nested global scope functions so the overhead here is all in function call marshalling. text data bss dec hex filename 2077 0 0 2077 81d fs/xfs/libxfs/xfs_types.o.orig 2197 0 0 2197 895 fs/xfs/libxfs/xfs_types.o There's a small increase in binary size by inlining all the local nested calls in the verifier functions, but the same workload now profiles as: 40.69% [kernel] [k] xfs_dir3_leaf_check_int 10.52% [kernel] [k] __xfs_dir3_data_check 6.68% [kernel] [k] xfs_verify_dir_ino 4.22% [kernel] [k] xfs_errortag_test 4.15% [kernel] [k] memcpy 3.53% [kernel] [k] xfs_dir_ino_validate 1.87% [kernel] [k] xfs_dir2_data_get_ftype 1.37% [kernel] [k] do_raw_spin_lock 0.98% [kernel] [k] xfs_buf_find 0.94% [kernel] [k] __raw_callee_save___pv_queued_spin_unlock 0.73% [kernel] [k] xfs_log_commit_cil Now we only spend just over 10% of the time validing inode numbers for the same workload. Hence a few "inline" keyworks is good enough to reduce the validation overhead by 30%... Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
-rw-r--r--fs/xfs/libxfs/xfs_types.c18
1 files changed, 9 insertions, 9 deletions
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index b254fbeaaa50..04801362e1a7 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -13,7 +13,7 @@
#include "xfs_mount.h"
/* Find the size of the AG, in blocks. */
-xfs_agblock_t
+inline xfs_agblock_t
xfs_ag_block_count(
struct xfs_mount *mp,
xfs_agnumber_t agno)
@@ -29,7 +29,7 @@ xfs_ag_block_count(
* Verify that an AG block number pointer neither points outside the AG
* nor points at static metadata.
*/
-bool
+inline bool
xfs_verify_agbno(
struct xfs_mount *mp,
xfs_agnumber_t agno,
@@ -49,7 +49,7 @@ xfs_verify_agbno(
* Verify that an FS block number pointer neither points outside the
* filesystem nor points at static AG metadata.
*/
-bool
+inline bool
xfs_verify_fsbno(
struct xfs_mount *mp,
xfs_fsblock_t fsbno)
@@ -85,7 +85,7 @@ xfs_verify_fsbext(
}
/* Calculate the first and last possible inode number in an AG. */
-void
+inline void
xfs_agino_range(
struct xfs_mount *mp,
xfs_agnumber_t agno,
@@ -116,7 +116,7 @@ xfs_agino_range(
* Verify that an AG inode number pointer neither points outside the AG
* nor points at static metadata.
*/
-bool
+inline bool
xfs_verify_agino(
struct xfs_mount *mp,
xfs_agnumber_t agno,
@@ -146,7 +146,7 @@ xfs_verify_agino_or_null(
* Verify that an FS inode number pointer neither points outside the
* filesystem nor points at static AG metadata.
*/
-bool
+inline bool
xfs_verify_ino(
struct xfs_mount *mp,
xfs_ino_t ino)
@@ -162,7 +162,7 @@ xfs_verify_ino(
}
/* Is this an internal inode number? */
-bool
+inline bool
xfs_internal_inum(
struct xfs_mount *mp,
xfs_ino_t ino)
@@ -190,7 +190,7 @@ xfs_verify_dir_ino(
* Verify that an realtime block number pointer doesn't point off the
* end of the realtime device.
*/
-bool
+inline bool
xfs_verify_rtbno(
struct xfs_mount *mp,
xfs_rtblock_t rtbno)
@@ -215,7 +215,7 @@ xfs_verify_rtext(
}
/* Calculate the range of valid icount values. */
-void
+inline void
xfs_icount_range(
struct xfs_mount *mp,
unsigned long long *min,