Commit c604480171c510c1beeb81b82418e5bc4de8f1ae
1 parent
3b30c22f64
Btrfs: avoid allocation clusters that are too spread out
In SSD mode for data, and all the time for metadata the allocator will try to find a cluster of nearby blocks for allocations. This commit adds extra checks to make sure that each free block in the cluster is close to the last one. Signed-off-by: Chris Mason <chris.mason@oracle.com>
Showing 1 changed file with 2 additions and 1 deletions Side-by-side Diff
fs/btrfs/free-space-cache.c
| ... | ... | @@ -645,7 +645,8 @@ |
| 645 | 645 | * we haven't filled the empty size and the window is |
| 646 | 646 | * very large. reset and try again |
| 647 | 647 | */ |
| 648 | - if (next->offset - window_start > (bytes + empty_size) * 2) { | |
| 648 | + if (next->offset - (last->offset + last->bytes) > 128 * 1024 || | |
| 649 | + next->offset - window_start > (bytes + empty_size) * 2) { | |
| 649 | 650 | entry = next; |
| 650 | 651 | window_start = entry->offset; |
| 651 | 652 | window_free = entry->bytes; |