All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Sterba <dsterba@suse.com>
To: linux-btrfs@vger.kernel.org
Cc: David Sterba <dsterba@suse.com>
Subject: [PATCH 11/19] btrfs: speed up and simplify generic_bin_search
Date: Thu,  7 May 2020 22:19:53 +0200	[thread overview]
Message-ID: <32ed422c5c1fa2830c58a472222d3d09c49b7f60.1588853772.git.dsterba@suse.com> (raw)
In-Reply-To: <cover.1588853772.git.dsterba@suse.com>

The bin search jumps over the extent buffer item keys, comparing
directly the bytes if the key is in one page, or storing it in a
temporary buffer in case it spans two pages.

The mapping start and length are obtained from map_private_extent_buffer,
which is heavy weight compared to what we need. We know the key size and
can find out the eb page in a simple way.  For keys spanning two pages
the fallback read_extent_buffer is used.

The temporary variables are reduced and moved to the scope of use.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.c | 43 +++++++++++++++----------------------------
 1 file changed, 15 insertions(+), 28 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 6dbeb23c59ec..746dec22f250 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1668,15 +1668,8 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
 {
 	int low = 0;
 	int high = max;
-	int mid;
 	int ret;
-	struct btrfs_disk_key *tmp = NULL;
-	struct btrfs_disk_key unaligned;
-	unsigned long offset;
-	char *kaddr = NULL;
-	unsigned long map_start = 0;
-	unsigned long map_len = 0;
-	int err;
+	const int key_size = sizeof(struct btrfs_disk_key);
 
 	if (low > high) {
 		btrfs_err(eb->fs_info,
@@ -1687,32 +1680,26 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
 	}
 
 	while (low < high) {
+		unsigned long oip;
+		unsigned long offset;
+		struct btrfs_disk_key *tmp;
+		struct btrfs_disk_key unaligned;
+		int mid;
+
 		mid = (low + high) / 2;
 		offset = p + mid * item_size;
+		oip = offset_in_page(offset);
 
-		if (!kaddr || offset < map_start ||
-		    (offset + sizeof(struct btrfs_disk_key)) >
-		    map_start + map_len) {
-
-			err = map_private_extent_buffer(eb, offset,
-						sizeof(struct btrfs_disk_key),
-						&kaddr, &map_start, &map_len);
-
-			if (!err) {
-				tmp = (struct btrfs_disk_key *)(kaddr + offset -
-							map_start);
-			} else if (err == 1) {
-				read_extent_buffer(eb, &unaligned,
-						   offset, sizeof(unaligned));
-				tmp = &unaligned;
-			} else {
-				return err;
-			}
+		if (oip + key_size <= PAGE_SIZE) {
+			const unsigned long idx = offset >> PAGE_SHIFT;
+			char *kaddr = page_address(eb->pages[idx]);
 
+			tmp = (struct btrfs_disk_key *)(kaddr + oip);
 		} else {
-			tmp = (struct btrfs_disk_key *)(kaddr + offset -
-							map_start);
+			read_extent_buffer(eb, &unaligned, offset, key_size);
+			tmp = &unaligned;
 		}
+
 		ret = comp_keys(tmp, key);
 
 		if (ret < 0)
-- 
2.25.0


  parent reply	other threads:[~2020-05-07 20:20 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-07 20:19 [PATCH 00/19] Set/get helpers speedups and cleanups David Sterba
2020-05-07 20:19 ` [PATCH 01/19] btrfs: use the token::eb for all set/get helpers David Sterba
2020-05-08 12:05   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 02/19] btrfs: drop eb parameter from set/get token helpers David Sterba
2020-05-08 12:09   ` Johannes Thumshirn
2020-05-11 13:02     ` David Sterba
2020-05-11 14:41       ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 03/19] btrfs: don't use set/get token for single assignment in overwrite_item David Sterba
2020-05-08 13:25   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 04/19] btrfs: don't use set/get token in leaf_space_used David Sterba
2020-05-08 13:27   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 05/19] btrfs: preset set/get token with first page and drop condition David Sterba
2020-05-08 13:37   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 06/19] btrfs: add separate bounds checker for set/get helpers David Sterba
2020-05-08 13:39   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 07/19] btrfs: speed up btrfs_get_##bits helpers David Sterba
2020-05-08 13:42   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 08/19] btrfs: speed up btrfs_get_token_##bits helpers David Sterba
2020-05-08 13:46   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 09/19] btrfs: speed up btrfs_set_##bits helpers David Sterba
2020-05-08 13:48   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 10/19] btrfs: speed up btrfs_set_token_##bits helpers David Sterba
2020-05-08 13:50   ` Johannes Thumshirn
2020-05-11 13:17     ` David Sterba
2020-05-07 20:19 ` David Sterba [this message]
2020-05-08 14:04   ` [PATCH 11/19] btrfs: speed up and simplify generic_bin_search Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 12/19] btrfs: remove unused map_private_extent_buffer David Sterba
2020-05-08 14:05   ` Johannes Thumshirn
2020-05-07 20:19 ` [PATCH 13/19] btrfs: constify extent_buffer in the API functions David Sterba
2020-05-08 14:07   ` Johannes Thumshirn
2020-05-07 20:20 ` [PATCH 14/19] btrfs: drop unnecessary offset_in_page in extent buffer helpers David Sterba
2020-05-08 14:13   ` Johannes Thumshirn
2020-05-07 20:20 ` [PATCH 15/19] btrfs: optimize split page read in btrfs_get_##bits David Sterba
2020-05-08 14:17   ` Johannes Thumshirn
2020-05-07 20:20 ` [PATCH 16/19] btrfs: optimize split page read in btrfs_get_token_##bits David Sterba
2020-05-08 14:18   ` Johannes Thumshirn
2020-05-07 20:20 ` [PATCH 17/19] btrfs: optimize split page write in btrfs_set_##bits David Sterba
2020-05-08 14:20   ` Johannes Thumshirn
2020-05-07 20:20 ` [PATCH 18/19] btrfs: optimize split page write in btrfs_set_token_##bits David Sterba
2020-05-08 14:21   ` Johannes Thumshirn
2020-05-07 20:20 ` [PATCH 19/19] btrfs: update documentation of set/get helpers David Sterba
2020-05-07 21:33   ` Nikolay Borisov
2020-05-11 13:10     ` David Sterba
2020-05-11 14:16       ` Nikolay Borisov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=32ed422c5c1fa2830c58a472222d3d09c49b7f60.1588853772.git.dsterba@suse.com \
    --to=dsterba@suse.com \
    --cc=linux-btrfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.