linux/fs/btrfs
Filipe Manana a724f313f8 btrfs: do unsigned integer division in the extent buffer binary search loop
In the search loop of the binary search function, we are doing a division
by 2 of the sum of the high and low slots. Because the slots are integers,
the generated assembly code for it is the following on x86_64:

   0x00000000000141f1 <+145>:	mov    %eax,%ebx
   0x00000000000141f3 <+147>:	shr    $0x1f,%ebx
   0x00000000000141f6 <+150>:	add    %eax,%ebx
   0x00000000000141f8 <+152>:	sar    %ebx

It's a few more instructions than a simple right shift, because signed
integer division needs to round towards zero. However we know that slots
can never be negative (btrfs_header_nritems() returns an u32), so we
can instead use unsigned types for the low and high slots and therefore
use unsigned integer division, which results in a single instruction on
x86_64:

   0x00000000000141f0 <+144>:	shr    %ebx

So use unsigned types for the slots and therefore unsigned division.

This is part of a small patchset comprised of the following two patches:

  btrfs: eliminate extra call when doing binary search on extent buffer
  btrfs: do unsigned integer division in the extent buffer binary search loop

The following fs_mark test was run on a non-debug kernel (Debian's default
kernel config) before and after applying the patchset:

  $ cat test.sh
  #!/bin/bash

  DEV=/dev/sdi
  MNT=/mnt/sdi
  MOUNT_OPTIONS="-o ssd"
  MKFS_OPTIONS="-O no-holes -R free-space-tree"
  FILES=100000
  THREADS=$(nproc --all)
  FILE_SIZE=0

  umount $DEV &> /dev/null
  mkfs.btrfs -f $MKFS_OPTIONS $DEV
  mount $MOUNT_OPTIONS $DEV $MNT

  OPTS="-S 0 -L 6 -n $FILES -s $FILE_SIZE -t $THREADS -k"
  for ((i = 1; i <= $THREADS; i++)); do
      OPTS="$OPTS -d $MNT/d$i"
  done

  fs_mark $OPTS

  umount $MNT

Results before applying patchset:

  FSUse%        Count         Size    Files/sec     App Overhead
       2      1200000            0     174472.0         11549868
       4      2400000            0     253503.0         11694618
       4      3600000            0     257833.1         11611508
       6      4800000            0     247089.5         11665983
       6      6000000            0     211296.1         12121244
      10      7200000            0     187330.6         12548565

Results after applying patchset:

  FSUse%        Count         Size    Files/sec     App Overhead
       2      1200000            0     207556.0         11393252
       4      2400000            0     266751.1         11347909
       4      3600000            0     274397.5         11270058
       6      4800000            0     259608.4         11442250
       6      6000000            0     238895.8         11635921
       8      7200000            0     211942.2         11873825

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-02-15 19:38:55 +01:00
..
tests btrfs: drop private_data parameter from extent_io_tree_init 2022-12-05 18:00:54 +01:00
accessors.c btrfs: add eb to btrfs_node_key_ptr_offset 2022-12-05 18:00:58 +01:00
accessors.h btrfs: add stack helpers for a few btrfs items 2022-12-05 18:00:58 +01:00
acl.c for-6.2-tag 2022-12-12 20:47:51 -08:00
acl.h for-6.2-tag 2022-12-12 20:47:51 -08:00
async-thread.c btrfs: simplify WQ_HIGHPRI handling in struct btrfs_workqueue 2022-05-16 17:03:15 +02:00
async-thread.h btrfs: remove unused typedefs get_extent_t and btrfs_work_func_t 2022-07-25 17:45:36 +02:00
backref.c btrfs: skip backref walking during fiemap if we know the leaf is shared 2023-02-15 19:38:50 +01:00
backref.h btrfs: send: skip resolution of our own backref when finding clone source 2022-12-05 18:00:50 +01:00
bio.c btrfs: split zone append bios in btrfs_submit_bio 2023-02-15 19:38:53 +01:00
bio.h btrfs: remove the fs_info argument to btrfs_submit_bio 2023-02-15 19:38:53 +01:00
block-group.c btrfs: don't use size classes for zoned file systems 2023-02-13 17:50:34 +01:00
block-group.h btrfs: don't use size classes for zoned file systems 2023-02-13 17:50:34 +01:00
block-rsv.c btrfs: simplify percent calculation helpers, rename div_factor 2022-12-05 18:00:48 +01:00
block-rsv.h btrfs: simplify percent calculation helpers, rename div_factor 2022-12-05 18:00:48 +01:00
btrfs_inode.h btrfs: remove now spurious bio submission helpers 2023-02-15 19:38:53 +01:00
check-integrity.c btrfs: use btrfs_dev_name() helper to handle missing devices better 2022-12-05 18:00:57 +01:00
check-integrity.h btrfs: check-integrity: split submit_bio from btrfsic checking 2022-05-16 17:03:12 +02:00
compression.c btrfs: split zone append bios in btrfs_submit_bio 2023-02-15 19:38:53 +01:00
compression.h btrfs: split zone append bios in btrfs_submit_bio 2023-02-15 19:38:53 +01:00
ctree.c btrfs: do unsigned integer division in the extent buffer binary search loop 2023-02-15 19:38:55 +01:00
ctree.h btrfs: do unsigned integer division in the extent buffer binary search loop 2023-02-15 19:38:55 +01:00
defrag.c btrfs: remove the wait argument to btrfs_start_ordered_extent 2023-02-13 17:50:34 +01:00
defrag.h btrfs: move defrag related prototypes to their own header 2022-12-05 18:00:46 +01:00
delalloc-space.c btrfs: update function comments 2022-12-05 18:00:45 +01:00
delalloc-space.h btrfs: move delalloc space related prototypes to delalloc-space.h 2022-12-05 18:00:44 +01:00
delayed-inode.c btrfs: pass btrfs_inode to btrfs_inode_unlock 2022-12-05 18:00:53 +01:00
delayed-inode.h btrfs: extend btrfs_dir_item type to store encryption status 2022-12-05 18:00:43 +01:00
delayed-ref.c btrfs: directly pass in fs_info to btrfs_merge_delayed_refs 2023-02-13 17:50:33 +01:00
delayed-ref.h btrfs: directly pass in fs_info to btrfs_merge_delayed_refs 2023-02-13 17:50:33 +01:00
dev-replace.c btrfs: use btrfs_dev_name() helper to handle missing devices better 2022-12-05 18:00:57 +01:00
dev-replace.h btrfs: move dev-replace prototypes into dev-replace.h 2022-12-05 18:00:47 +01:00
dir-item.c btrfs: move dir-item prototypes into dir-item.h 2022-12-05 18:00:46 +01:00
dir-item.h btrfs: move dir-item prototypes into dir-item.h 2022-12-05 18:00:46 +01:00
discard.c btrfs: hold block group refcount during async discard 2023-02-15 19:38:50 +01:00
discard.h
disk-io.c btrfs: combine btrfs_clear_buffer_dirty and clear_extent_buffer_dirty 2023-02-15 19:38:54 +01:00
disk-io.h btrfs: rename btrfs_clean_tree_block to btrfs_clear_buffer_dirty 2023-02-15 19:38:53 +01:00
export.c btrfs: move super_block specific helpers into super.h 2022-12-05 18:00:47 +01:00
export.h btrfs: simplify generation check in btrfs_get_dentry 2022-12-05 18:00:41 +01:00
extent-io-tree.c btrfs: fix spelling mistakes found using codespell 2023-02-15 19:38:50 +01:00
extent-io-tree.h btrfs: remove the io_failure_record infrastructure 2023-02-15 19:38:51 +01:00
extent-tree.c btrfs: rename btrfs_clean_tree_block to btrfs_clear_buffer_dirty 2023-02-15 19:38:53 +01:00
extent-tree.h btrfs: introduce size class to block group allocator 2023-02-13 17:50:34 +01:00
extent_io.c btrfs: combine btrfs_clear_buffer_dirty and clear_extent_buffer_dirty 2023-02-15 19:38:54 +01:00
extent_io.h btrfs: combine btrfs_clear_buffer_dirty and clear_extent_buffer_dirty 2023-02-15 19:38:54 +01:00
extent_map.c btrfs: remove no longer used btrfs_next_extent_map() 2022-12-05 18:00:56 +01:00
extent_map.h btrfs: remove no longer used btrfs_next_extent_map() 2022-12-05 18:00:56 +01:00
file-item.c btrfs: simplify the btrfs_csum_one_bio calling convention 2023-02-15 19:38:52 +01:00
file-item.h btrfs: simplify the btrfs_csum_one_bio calling convention 2023-02-15 19:38:52 +01:00
file.c btrfs: remove the wait argument to btrfs_start_ordered_extent 2023-02-13 17:50:34 +01:00
file.h btrfs: use cached state when looking for delalloc ranges with fiemap 2022-12-05 18:00:56 +01:00
free-space-cache.c btrfs: pass btrfs_inode to btrfs_add_delayed_iput 2022-12-05 18:00:55 +01:00
free-space-cache.h btrfs: convert discard stat defs to enum 2022-12-05 18:00:45 +01:00
free-space-tree.c btrfs: rename btrfs_clean_tree_block to btrfs_clear_buffer_dirty 2023-02-15 19:38:53 +01:00
free-space-tree.h
fs.c btrfs: sysfs: update fs features directory asynchronously 2023-02-13 17:50:35 +01:00
fs.h btrfs: calculate file system wide queue limit for zoned mode 2023-02-15 19:38:53 +01:00
inode-item.c btrfs: move file-item prototypes into their own header 2022-12-05 18:00:46 +01:00
inode-item.h btrfs: use struct fscrypt_str instead of struct qstr 2022-12-05 18:00:43 +01:00
inode.c btrfs: split zone append bios in btrfs_submit_bio 2023-02-15 19:38:53 +01:00
ioctl.c btrfs: rename btrfs_clean_tree_block to btrfs_clear_buffer_dirty 2023-02-15 19:38:53 +01:00
ioctl.h btrfs: move ioctl prototypes into ioctl.h 2022-12-05 18:00:46 +01:00
Kconfig btrfs: use generic Kconfig option for 256kB page size limit 2022-01-20 08:52:55 +02:00
locking.c btrfs: move accessor helpers into accessors.h 2022-12-05 18:00:42 +01:00
locking.h btrfs: move the lockdep helpers into locking.h 2022-12-05 18:00:44 +01:00
lru_cache.c btrfs: send: cache utimes operations for directories if possible 2023-02-15 19:38:50 +01:00
lru_cache.h btrfs: send: cache utimes operations for directories if possible 2023-02-15 19:38:50 +01:00
lzo.c btrfs: use PAGE_{ALIGN, ALIGNED, ALIGN_DOWN} macro 2023-02-13 17:50:34 +01:00
Makefile btrfs: send: genericize the backref cache to allow it to be reused 2023-02-13 17:50:35 +01:00
messages.c btrfs: move btrfs_abort_transaction to transaction.c 2023-02-13 17:50:33 +01:00
messages.h btrfs: move btrfs_abort_transaction to transaction.c 2023-02-13 17:50:33 +01:00
misc.h btrfs: simplify percent calculation helpers, rename div_factor 2022-12-05 18:00:48 +01:00
ordered-data.c btrfs: remove the wait argument to btrfs_start_ordered_extent 2023-02-13 17:50:34 +01:00
ordered-data.h btrfs: remove the wait argument to btrfs_start_ordered_extent 2023-02-13 17:50:34 +01:00
orphan.c btrfs: move orphan prototypes into orphan.h 2022-12-05 18:00:47 +01:00
orphan.h btrfs: move orphan prototypes into orphan.h 2022-12-05 18:00:47 +01:00
print-tree.c btrfs: move struct btrfs_tree_parent_check out of disk-io.h 2022-12-05 18:00:57 +01:00
print-tree.h
props.c btrfs: move super_block specific helpers into super.h 2022-12-05 18:00:47 +01:00
props.h btrfs: make module init/exit match their sequence 2022-12-05 18:00:40 +01:00
qgroup.c btrfs: rename btrfs_clean_tree_block to btrfs_clear_buffer_dirty 2023-02-15 19:38:53 +01:00
qgroup.h btrfs: sink gfp_t parameter to btrfs_qgroup_trace_extent 2022-12-05 18:00:43 +01:00
raid56.c btrfs: raid56: handle endio in scrub_rbio 2023-02-15 19:38:55 +01:00
raid56.h btrfs: fix spelling mistakes found using codespell 2023-02-15 19:38:50 +01:00
rcu-string.h btrfs: replace strncpy() with strscpy() 2022-12-05 18:00:59 +01:00
ref-verify.c btrfs: move accessor helpers into accessors.h 2022-12-05 18:00:42 +01:00
ref-verify.h
reflink.c btrfs: pass btrfs_inode to btrfs_inode_unlock 2022-12-05 18:00:53 +01:00
reflink.h
relocation.c btrfs: use PAGE_{ALIGN, ALIGNED, ALIGN_DOWN} macro 2023-02-13 17:50:34 +01:00
relocation.h btrfs: move relocation prototypes into relocation.h 2022-12-05 18:00:47 +01:00
root-tree.c btrfs: move orphan prototypes into orphan.h 2022-12-05 18:00:47 +01:00
root-tree.h btrfs: move root tree prototypes to their own header 2022-12-05 18:00:44 +01:00
scrub.c btrfs: fix spelling mistakes found using codespell 2023-02-15 19:38:50 +01:00
scrub.h btrfs: move scrub prototypes into scrub.h 2022-12-05 18:00:47 +01:00
send.c btrfs: send: cache utimes operations for directories if possible 2023-02-15 19:38:50 +01:00
send.h btrfs: send add define for v2 buffer size 2022-12-05 18:00:41 +01:00
space-info.c btrfs: zoned: enable metadata over-commit for non-ZNS setup 2023-01-11 20:04:25 +01:00
space-info.h btrfs: move btrfs_account_ro_block_groups_free_space into space-info.c 2022-12-05 18:00:44 +01:00
subpage.c btrfs: move the printk helpers out of ctree.h 2022-12-05 18:00:41 +01:00
subpage.h btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine 2022-05-16 17:03:11 +02:00
super.c btrfs: fix spelling mistakes found using codespell 2023-02-15 19:38:50 +01:00
super.h btrfs: move super_block specific helpers into super.h 2022-12-05 18:00:47 +01:00
sysfs.c btrfs: sysfs: update fs features directory asynchronously 2023-02-13 17:50:35 +01:00
sysfs.h btrfs: sysfs: update fs features directory asynchronously 2023-02-13 17:50:35 +01:00
transaction.c btrfs: sysfs: update fs features directory asynchronously 2023-02-13 17:50:35 +01:00
transaction.h btrfs: move btrfs_abort_transaction to transaction.c 2023-02-13 17:50:33 +01:00
tree-checker.c btrfs: pass the extent buffer for the btrfs_item_nr helpers 2022-12-05 18:00:58 +01:00
tree-checker.h btrfs: move struct btrfs_tree_parent_check out of disk-io.h 2022-12-05 18:00:57 +01:00
tree-log.c btrfs: replace btrfs_wait_tree_block_writeback by wait_on_extent_buffer_writeback 2023-02-15 19:38:54 +01:00
tree-log.h btrfs: use a negative value for BTRFS_LOG_FORCE_COMMIT 2023-02-13 17:50:34 +01:00
tree-mod-log.c btrfs: add eb to btrfs_node_key_ptr_offset 2022-12-05 18:00:58 +01:00
tree-mod-log.h btrfs: fix SPDX comment in tree-mod-log.h 2022-12-05 18:00:48 +01:00
ulist.c btrfs: constify ulist parameter of ulist_next() 2022-12-05 18:00:50 +01:00
ulist.h btrfs: constify ulist parameter of ulist_next() 2022-12-05 18:00:50 +01:00
uuid-tree.c btrfs: move uuid tree prototypes to uuid-tree.h 2022-12-05 18:00:46 +01:00
uuid-tree.h btrfs: move uuid tree prototypes to uuid-tree.h 2022-12-05 18:00:46 +01:00
verity.c btrfs: move orphan prototypes into orphan.h 2022-12-05 18:00:47 +01:00
verity.h btrfs: move verity prototypes into verity.h 2022-12-05 18:00:47 +01:00
volumes.c btrfs: remove struct btrfs_io_geometry 2023-02-15 19:38:52 +01:00
volumes.h btrfs: remove struct btrfs_io_geometry 2023-02-15 19:38:52 +01:00
xattr.c btrfs: move dir-item prototypes into dir-item.h 2022-12-05 18:00:46 +01:00
xattr.h
zlib.c btrfs: zlib: zero-initialize zlib workspace 2023-01-25 20:11:08 +01:00
zoned.c btrfs: split zone append bios in btrfs_submit_bio 2023-02-15 19:38:53 +01:00
zoned.h btrfs: split zone append bios in btrfs_submit_bio 2023-02-15 19:38:53 +01:00
zstd.c btrfs: constify input buffer parameter in compression code 2022-12-05 18:00:55 +01:00