From 8b62f87bad9cf06e536799bf8cb942ab95f6bfa4 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 19 Oct 2017 14:15:55 -0400 Subject: Btrfs: rework outstanding_extents Right now we do a lot of weird hoops around outstanding_extents in order to keep the extent count consistent. This is because we logically transfer the outstanding_extent count from the initial reservation through the set_delalloc_bits. This makes it pretty difficult to get a handle on how and when we need to mess with outstanding_extents. Fix this by revamping the rules of how we deal with outstanding_extents. Now instead everybody that is holding on to a delalloc extent is required to increase the outstanding extents count for itself. This means we'll have something like this btrfs_delalloc_reserve_metadata - outstanding_extents = 1 btrfs_set_extent_delalloc - outstanding_extents = 2 btrfs_release_delalloc_extents - outstanding_extents = 1 for an initial file write. Now take the append write where we extend an existing delalloc range but still under the maximum extent size btrfs_delalloc_reserve_metadata - outstanding_extents = 2 btrfs_set_extent_delalloc btrfs_set_bit_hook - outstanding_extents = 3 btrfs_merge_extent_hook - outstanding_extents = 2 btrfs_delalloc_release_extents - outstanding_extnets = 1 In order to make the ordered extent transition we of course must now make ordered extents carry their own outstanding_extent reservation, so for cow_file_range we end up with btrfs_add_ordered_extent - outstanding_extents = 2 clear_extent_bit - outstanding_extents = 1 btrfs_remove_ordered_extent - outstanding_extents = 0 This makes all manipulations of outstanding_extents much more explicit. Every successful call to btrfs_delalloc_reserve_metadata _must_ now be combined with btrfs_release_delalloc_extents, even in the error case, as that is the only function that actually modifies the outstanding_extents counter. The drawback to this is now we are much more likely to have transient cases where outstanding_extents is much larger than it actually should be. This could happen before as we manipulated the delalloc bits, but now it happens basically at every write. This may put more pressure on the ENOSPC flushing code, but I think making this code simpler is worth the cost. I have another change coming to mitigate this side-effect somewhat. I also added trace points for the counter manipulation. These were used by a bpf script I wrote to help track down leak issues. Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/tests/inode-tests.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'fs/btrfs/tests') diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 330815eb07b4..f797642c013d 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -968,7 +968,6 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) btrfs_test_inode_set_ops(inode); /* [BTRFS_MAX_EXTENT_SIZE] */ - BTRFS_I(inode)->outstanding_extents++; ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, NULL, 0); if (ret) { @@ -983,7 +982,6 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) } /* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */ - BTRFS_I(inode)->outstanding_extents++; ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE, BTRFS_MAX_EXTENT_SIZE + sectorsize - 1, NULL, 0); @@ -1003,7 +1001,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, EXTENT_DELALLOC | EXTENT_DIRTY | - EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0, + EXTENT_UPTODATE, 0, 0, NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); @@ -1017,7 +1015,6 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) } /* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */ - BTRFS_I(inode)->outstanding_extents++; ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, @@ -1035,12 +1032,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize HOLE][BTRFS_MAX_EXTENT_SIZE+sectorsize] - * - * I'm artificially adding 2 to outstanding_extents because in the - * buffered IO case we'd add things up as we go, but I don't feel like - * doing that here, this isn't the interesting case we want to test. */ - BTRFS_I(inode)->outstanding_extents += 2; ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize, (BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1, @@ -1059,7 +1051,6 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize][BTRFS_MAX_EXTENT_SIZE+sectorsize] */ - BTRFS_I(inode)->outstanding_extents++; ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL, 0); @@ -1079,7 +1070,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, + EXTENT_UPTODATE, 0, 0, NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); @@ -1096,7 +1087,6 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) * Refill the hole again just for good measure, because I thought it * might fail and I'd rather satisfy my paranoia at this point. */ - BTRFS_I(inode)->outstanding_extents++; ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL, 0); @@ -1114,7 +1104,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* Empty */ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, + EXTENT_UPTODATE, 0, 0, NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); @@ -1131,7 +1121,7 @@ out: if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, + EXTENT_UPTODATE, 0, 0, NULL, GFP_KERNEL); iput(inode); btrfs_free_dummy_root(root); -- cgit v1.2.3-70-g09d2