summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorJosef Bacik <josef@redhat.com>2010-05-23 11:00:55 -0400
committerChris Mason <chris.mason@oracle.com>2010-05-25 10:34:56 -0400
commitc2c6ca417e2db7a519e6e92c82f4a933d940d076 (patch)
tree4b5f71682270b151e38e9649a40da30564dacfdd /fs
parentfacd07b07d2a7988f5ce849558838cc953847637 (diff)
direct-io: do not merge logically non-contiguous requests
Btrfs cannot handle having logically non-contiguous requests submitted. For example if you have Logical: [0-4095][HOLE][8192-12287] Physical: [0-4095] [4096-8191] Normally the DIO code would put these into the same BIO's. The problem is we need to know exactly what offset is associated with what BIO so we can do our checksumming and unlocking properly, so putting them in the same BIO doesn't work. So add another check where we submit the current BIO if the physical blocks are not contigous OR the logical blocks are not contiguous. Signed-off-by: Josef Bacik <josef@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs')
-rw-r--r--fs/direct-io.c20
1 files changed, 18 insertions, 2 deletions
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 5949947b060..da111aacb46 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -632,10 +632,26 @@ static int dio_send_cur_page(struct dio *dio)
int ret = 0;
if (dio->bio) {
+ loff_t cur_offset = dio->block_in_file << dio->blkbits;
+ loff_t bio_next_offset = dio->logical_offset_in_bio +
+ dio->bio->bi_size;
+
/*
- * See whether this new request is contiguous with the old
+ * See whether this new request is contiguous with the old.
+ *
+ * Btrfs cannot handl having logically non-contiguous requests
+ * submitted. For exmple if you have
+ *
+ * Logical: [0-4095][HOLE][8192-12287]
+ * Phyiscal: [0-4095] [4096-8181]
+ *
+ * We cannot submit those pages together as one BIO. So if our
+ * current logical offset in the file does not equal what would
+ * be the next logical offset in the bio, submit the bio we
+ * have.
*/
- if (dio->final_block_in_bio != dio->cur_page_block)
+ if (dio->final_block_in_bio != dio->cur_page_block ||
+ cur_offset != bio_next_offset)
dio_bio_submit(dio);
/*
* Submit now if the underlying fs is about to perform a