From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 11 Oct 2022 12:16:56 +0000 (+0100)
Subject: btrfs: skip unnecessary delalloc search during fiemap and lseek
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=a2853ffc2eb9bfb6e6d48486df7f3969a58ae3b4;p=linux.git

btrfs: skip unnecessary delalloc search during fiemap and lseek

During fiemap and lseek (hole and data seeking), there's no point in
iterating the inode's io tree to count delalloc bits if the inode's
delalloc bytes counter has a value of zero, as that counter is updated
whenever we set a range for delalloc or clear a range from delalloc.

So skip the counting and io tree iteration if the inode's delalloc bytes
counter has a value of zero. This helps save time when processing a file
range corresponding to a hole or prealloc (unwritten) extent.

This patch is part of a series comprised of the following patches:

  btrfs: get the next extent map during fiemap/lseek more efficiently
  btrfs: skip unnecessary extent map searches during fiemap and lseek
  btrfs: skip unnecessary delalloc search during fiemap and lseek

The following test was performed on a release kernel (Debian's default
kernel config) before and after applying those 3 patches.

   # Wrapper to call fiemap in extent count only mode.
   # (struct fiemap::fm_extent_count set to 0)
   $ cat fiemap.c
   #include <stdio.h>
   #include <unistd.h>
   #include <stdlib.h>
   #include <fcntl.h>
   #include <errno.h>
   #include <string.h>
   #include <sys/ioctl.h>
   #include <linux/fs.h>
   #include <linux/fiemap.h>

   int main(int argc, char **argv)
   {
            struct fiemap fiemap = { 0 };
            int fd;

            if (argc != 2) {
                    printf("usage: %s <path>\n", argv[0]);
                    return 1;
            }
            fd = open(argv[1], O_RDONLY);
            if (fd < 0) {
                    fprintf(stderr, "error opening file: %s\n",
                            strerror(errno));
                    return 1;
            }

            /* fiemap.fm_extent_count set to 0, to count extents only. */
            fiemap.fm_length = FIEMAP_MAX_OFFSET;
            if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
                    fprintf(stderr, "fiemap error: %s\n",
                            strerror(errno));
                    return 1;
            }
            close(fd);
            printf("fm_mapped_extents = %d\n", fiemap.fm_mapped_extents);

            return 0;
   }

   $ gcc -o fiemap fiemap.c

And the wrapper shell script that creates a file with many holes and runs
fiemap against it:

   $ cat test.sh
   #!/bin/bash

   DEV=/dev/sdi
   MNT=/mnt/sdi

   mkfs.btrfs -f $DEV
   mount $DEV $MNT

   FILE_SIZE=$((1 * 1024 * 1024 * 1024))
   echo -n > $MNT/foobar
   for ((off = 0; off < $FILE_SIZE; off += 8192)); do
           xfs_io -c "pwrite -S 0xab $off 4K" $MNT/foobar > /dev/null
   done

   # flush all delalloc
   sync

   start=$(date +%s%N)
   ./fiemap $MNT/foobar
   end=$(date +%s%N)
   dur=$(( (end - start) / 1000000 ))
   echo "fiemap took $dur milliseconds"

   umount $MNT

Result before applying patchset:

   fm_mapped_extents = 131072
   fiemap took 63 milliseconds

Result after applying patchset:

   fm_mapped_extents = 131072
   fiemap took 39 milliseconds   (-38.1%)

Running the same test for a 512M file instead of a 1G file, gave the
following results.

Result before applying patchset:

   fm_mapped_extents = 65536
   fiemap took 29 milliseconds

Result after applying patchset:

   fm_mapped_extents = 65536
   fiemap took 20 milliseconds    (-31.0%)

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 1cf97280760ec..19b41b5fe6c0c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3537,15 +3537,27 @@ static bool find_delalloc_subrange(struct btrfs_inode *inode, u64 start, u64 end
 	struct extent_map *em;
 	u64 em_end;
 	u64 delalloc_len;
+	unsigned int outstanding_extents;
 
 	/*
 	 * Search the io tree first for EXTENT_DELALLOC. If we find any, it
 	 * means we have delalloc (dirty pages) for which writeback has not
 	 * started yet.
 	 */
-	*delalloc_start_ret = start;
-	delalloc_len = count_range_bits(&inode->io_tree, delalloc_start_ret, end,
-					len, EXTENT_DELALLOC, 1);
+	spin_lock(&inode->lock);
+	outstanding_extents = inode->outstanding_extents;
+
+	if (inode->delalloc_bytes > 0) {
+		spin_unlock(&inode->lock);
+		*delalloc_start_ret = start;
+		delalloc_len = count_range_bits(&inode->io_tree,
+						delalloc_start_ret, end,
+						len, EXTENT_DELALLOC, 1);
+	} else {
+		spin_unlock(&inode->lock);
+		delalloc_len = 0;
+	}
+
 	/*
 	 * If delalloc was found then *delalloc_start_ret has a sector size
 	 * aligned value (rounded down).
@@ -3553,17 +3565,12 @@ static bool find_delalloc_subrange(struct btrfs_inode *inode, u64 start, u64 end
 	if (delalloc_len > 0)
 		*delalloc_end_ret = *delalloc_start_ret + delalloc_len - 1;
 
-	spin_lock(&inode->lock);
-	if (inode->outstanding_extents == 0) {
-		/*
-		 * No outstanding extents means we don't have any delalloc that
-		 * is flushing, so return the unflushed range found in the io
-		 * tree (if any).
-		 */
-		spin_unlock(&inode->lock);
+	/*
+	 * No outstanding extents means we don't have any delalloc that is
+	 * flushing, so return the unflushed range found in the io tree (if any).
+	 */
+	if (outstanding_extents == 0)
 		return (delalloc_len > 0);
-	}
-	spin_unlock(&inode->lock);
 
 	/*
 	 * Now also check if there's any extent map in the range that does not