From: Miao Xie <miaox@cn.fujitsu.com>
To: <linux-btrfs@vger.kernel.org>
Subject: [PATCH v2 04/12] Btrfs: do file data check by sub-bio's self
Date: Tue, 29 Jul 2014 17:24:02 +0800 [thread overview]
Message-ID: <1406625850-32168-5-git-send-email-miaox@cn.fujitsu.com> (raw)
In-Reply-To: <1406625850-32168-1-git-send-email-miaox@cn.fujitsu.com>
Direct IO splits the original bio to several sub-bios because of the limit of
raid stripe, and the filesystem will wait for all sub-bios and then run final
end io process.
But it was very hard to implement the data repair when dio read failure happens,
because at the final end io function, we didn't know which mirror the data was
read from. So in order to implement the data repair, we have to move the file data
check in the final end io function to the sub-bio end io function, in which we can
get the mirror number of the device we access. This patch did this work as the
first step of the direct io data repair implementation.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
---
Changelog v1-v2:
- None
---
fs/btrfs/btrfs_inode.h | 9 +++++
fs/btrfs/extent_io.c | 2 +-
fs/btrfs/inode.c | 100 ++++++++++++++++++++++++++++++++++++-------------
fs/btrfs/volumes.h | 5 ++-
4 files changed, 87 insertions(+), 29 deletions(-)
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index b69bf7e..745fca40 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -245,8 +245,11 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
return 0;
}
+#define BTRFS_DIO_ORIG_BIO_SUBMITTED 0x1
+
struct btrfs_dio_private {
struct inode *inode;
+ unsigned long flags;
u64 logical_offset;
u64 disk_bytenr;
u64 bytes;
@@ -263,6 +266,12 @@ struct btrfs_dio_private {
/* dio_bio came from fs/direct-io.c */
struct bio *dio_bio;
+
+ /*
+ * The original bio may be splited to several sub-bios, this is
+ * done during endio of sub-bios
+ */
+ int (*subio_endio)(struct inode *, struct btrfs_io_bio *);
};
/*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 0fb63c4..881fc49 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2469,7 +2469,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
struct inode *inode = page->mapping->host;
pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
- "mirror=%lu\n", (u64)bio->bi_iter.bi_sector, err,
+ "mirror=%u\n", (u64)bio->bi_iter.bi_sector, err,
io_bio->mirror_num);
tree = &BTRFS_I(inode)->io_tree;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2e261b1..3e95a2b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7083,29 +7083,40 @@ unlock_err:
return ret;
}
-static void btrfs_endio_direct_read(struct bio *bio, int err)
+static int btrfs_subio_endio_read(struct inode *inode,
+ struct btrfs_io_bio *io_bio)
{
- struct btrfs_dio_private *dip = bio->bi_private;
struct bio_vec *bvec;
- struct inode *inode = dip->inode;
- struct bio *dio_bio;
- struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
u64 start;
- int ret;
int i;
+ int ret;
+ int err = 0;
- if (err || (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
- goto skip_checksum;
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
+ return 0;
- start = dip->logical_offset;
- bio_for_each_segment_all(bvec, bio, i) {
+ start = io_bio->logical;
+ bio_for_each_segment_all(bvec, &io_bio->bio, i) {
ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
0, start, bvec->bv_len);
if (ret)
err = -EIO;
start += bvec->bv_len;
}
-skip_checksum:
+
+ return err;
+}
+
+static void btrfs_endio_direct_read(struct bio *bio, int err)
+{
+ struct btrfs_dio_private *dip = bio->bi_private;
+ struct inode *inode = dip->inode;
+ struct bio *dio_bio;
+ struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+
+ if (!err && (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED))
+ err = btrfs_subio_endio_read(inode, io_bio);
+
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
dip->logical_offset + dip->bytes - 1);
dio_bio = dip->dio_bio;
@@ -7182,6 +7193,7 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode, int rw,
static void btrfs_end_dio_bio(struct bio *bio, int err)
{
struct btrfs_dio_private *dip = bio->bi_private;
+ int ret;
if (err) {
btrfs_err(BTRFS_I(dip->inode)->root->fs_info,
@@ -7189,6 +7201,13 @@ static void btrfs_end_dio_bio(struct bio *bio, int err)
btrfs_ino(dip->inode), bio->bi_rw,
(unsigned long long)bio->bi_iter.bi_sector,
bio->bi_iter.bi_size, err);
+ } else if (dip->subio_endio) {
+ ret = dip->subio_endio(dip->inode, btrfs_io_bio(bio));
+ if (ret)
+ err = ret;
+ }
+
+ if (err) {
dip->errors = 1;
/*
@@ -7219,6 +7238,38 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
return btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags);
}
+static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root,
+ struct inode *inode,
+ struct btrfs_dio_private *dip,
+ struct bio *bio,
+ u64 file_offset)
+{
+ struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+ struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio);
+ int ret;
+
+ /*
+ * We load all the csum data we need when we submit
+ * the first bio to reduce the csum tree search and
+ * contention.
+ */
+ if (dip->logical_offset == file_offset) {
+ ret = btrfs_lookup_bio_sums_dio(root, inode, dip->orig_bio,
+ file_offset);
+ if (ret)
+ return ret;
+ }
+
+ if (bio == dip->orig_bio)
+ return 0;
+
+ file_offset -= dip->logical_offset;
+ file_offset >>= inode->i_sb->s_blocksize_bits;
+ io_bio->csum = (u8 *)(((u32 *)orig_io_bio->csum) + file_offset);
+
+ return 0;
+}
+
static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
int rw, u64 file_offset, int skip_sum,
int async_submit)
@@ -7258,16 +7309,8 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
if (ret)
goto err;
} else {
- /*
- * We have loaded all the csum data we need when we submit
- * the first bio, so skip it.
- */
- if (dip->logical_offset != file_offset)
- goto map;
-
- /* Load all csum data at once. */
- ret = btrfs_lookup_bio_sums_dio(root, inode, dip->orig_bio,
- file_offset);
+ ret = btrfs_lookup_and_bind_dio_csum(root, inode, dip, bio,
+ file_offset);
if (ret)
goto err;
}
@@ -7302,6 +7345,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
if (map_length >= orig_bio->bi_iter.bi_size) {
bio = orig_bio;
+ dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED;
goto submit;
}
@@ -7318,6 +7362,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
+ btrfs_io_bio(bio)->logical = file_offset;
atomic_inc(&dip->pending_bios);
while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
@@ -7352,6 +7397,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
goto out_err;
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
+ btrfs_io_bio(bio)->logical = file_offset;
map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw,
@@ -7408,7 +7454,7 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
goto free_ordered;
}
- dip = kmalloc(sizeof(*dip), GFP_NOFS);
+ dip = kzalloc(sizeof(*dip), GFP_NOFS);
if (!dip) {
ret = -ENOMEM;
goto free_io_bio;
@@ -7420,21 +7466,23 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
dip->bytes = dio_bio->bi_iter.bi_size;
dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
io_bio->bi_private = dip;
- dip->errors = 0;
dip->orig_bio = io_bio;
dip->dio_bio = dio_bio;
atomic_set(&dip->pending_bios, 0);
+ btrfs_bio = btrfs_io_bio(io_bio);
+ btrfs_bio->logical = file_offset;
- if (write)
+ if (write) {
io_bio->bi_end_io = btrfs_endio_direct_write;
- else
+ } else {
io_bio->bi_end_io = btrfs_endio_direct_read;
+ dip->subio_endio = btrfs_subio_endio_read;
+ }
ret = btrfs_submit_direct_hook(rw, dip, skip_sum);
if (!ret)
return;
- btrfs_bio = btrfs_io_bio(io_bio);
if (btrfs_bio->end_io)
btrfs_bio->end_io(btrfs_bio, ret);
free_io_bio:
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2aaa00c..cd31de1 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -167,8 +167,9 @@ struct btrfs_fs_devices {
*/
typedef void (btrfs_io_bio_end_io_t) (struct btrfs_io_bio *bio, int err);
struct btrfs_io_bio {
- unsigned long mirror_num;
- unsigned long stripe_index;
+ unsigned int mirror_num;
+ unsigned int stripe_index;
+ u64 logical;
u8 *csum;
u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
u8 *csum_allocated;
--
1.9.3
next prev parent reply other threads:[~2014-07-29 9:22 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-28 11:34 [PATCH 00/12] Implement the data repair function for direct read Miao Xie
2014-06-28 11:34 ` [PATCH 01/12] Btrfs: fix put dio bio twice when we submit dio bio fail Miao Xie
2014-06-28 11:34 ` [PATCH 02/12] Btrfs: load checksum data once when submitting a direct read io Miao Xie
2014-07-28 17:24 ` Filipe David Manana
2014-07-29 1:56 ` Miao Xie
2014-06-28 11:34 ` [PATCH 03/12] Btrfs: cleanup similar code of the buffered data data check and dio read data check Miao Xie
2014-06-28 11:34 ` [PATCH 04/12] Btrfs: do file data check by sub-bio's self Miao Xie
2014-06-28 11:34 ` [PATCH 05/12] Btrfs: fix missing error handler if submiting re-read bio fails Miao Xie
2014-06-28 11:34 ` [PATCH 06/12] Btrfs: Cleanup unused variant and argument of IO failure handlers Miao Xie
2014-06-28 11:34 ` [PATCH 07/12] Btrfs: split bio_readpage_error into several functions Miao Xie
2014-06-28 11:34 ` [PATCH 08/12] Btrfs: modify repair_io_failure and make it suit direct io Miao Xie
2014-06-28 11:34 ` [PATCH 09/12] Btrfs: modify clean_io_failure " Miao Xie
2014-06-28 11:35 ` [PATCH 10/12] Btrfs: Set real mirror number for read operation on RAID0/5/6 Miao Xie
2014-06-28 11:35 ` [PATCH 11/12] Btrfs: implement repair function when direct read fails Miao Xie
2014-06-28 11:35 ` [PATCH 12/12] Btrfs: cleanup the read failure record after write or when the inode is freeing Miao Xie
2014-07-29 9:23 ` [PATCH v2 00/12] Implement the data repair function for direct read Miao Xie
2014-07-29 9:23 ` [PATCH v2 01/12] Btrfs: fix put dio bio twice when we submit dio bio fail Miao Xie
2014-07-29 9:24 ` [PATCH v2 02/12] Btrfs: load checksum data once when submitting a direct read io Miao Xie
2014-08-08 0:32 ` Filipe David Manana
2014-08-08 9:22 ` Miao Xie
2014-08-08 9:23 ` [PATCH v3 " Miao Xie
2014-07-29 9:24 ` [PATCH v2 03/12] Btrfs: cleanup similar code of the buffered data data check and dio read data check Miao Xie
2014-07-29 9:24 ` Miao Xie [this message]
2014-07-29 9:24 ` [PATCH v2 05/12] Btrfs: fix missing error handler if submiting re-read bio fails Miao Xie
2014-07-29 9:24 ` [PATCH v2 06/12] Btrfs: Cleanup unused variant and argument of IO failure handlers Miao Xie
2014-07-29 9:24 ` [PATCH v2 07/12] Btrfs: split bio_readpage_error into several functions Miao Xie
2014-07-29 9:24 ` [PATCH v2 08/12] Btrfs: modify repair_io_failure and make it suit direct io Miao Xie
2014-07-29 9:24 ` [PATCH v2 09/12] Btrfs: modify clean_io_failure " Miao Xie
2014-07-29 9:24 ` [PATCH v2 10/12] Btrfs: Set real mirror number for read operation on RAID0/5/6 Miao Xie
2014-07-29 9:24 ` [PATCH v2 11/12] Btrfs: implement repair function when direct read fails Miao Xie
2014-08-29 18:31 ` Chris Mason
2014-09-01 6:56 ` Miao Xie
2014-09-02 12:33 ` Liu Bo
2014-09-02 13:05 ` Chris Mason
2014-09-03 9:02 ` Miao Xie
2014-09-12 10:43 ` [PATCH v4 00/11] Implement the data repair function for direct read Miao Xie
2014-09-12 10:43 ` [PATCH v4 01/11] Btrfs: load checksum data once when submitting a direct read io Miao Xie
2014-09-12 10:43 ` [PATCH v4 02/11] Btrfs: cleanup similar code of the buffered data data check and dio read data check Miao Xie
2014-09-12 10:43 ` [PATCH v4 03/11] Btrfs: do file data check by sub-bio's self Miao Xie
2014-09-12 10:43 ` [PATCH v4 04/11] Btrfs: fix missing error handler if submiting re-read bio fails Miao Xie
2014-09-12 10:43 ` [PATCH v4 05/11] Btrfs: Cleanup unused variant and argument of IO failure handlers Miao Xie
2014-09-12 10:43 ` [PATCH v4 06/11] Btrfs: split bio_readpage_error into several functions Miao Xie
2014-09-12 10:44 ` [PATCH v4 07/11] Btrfs: modify repair_io_failure and make it suit direct io Miao Xie
2014-09-12 10:44 ` [PATCH v4 08/11] Btrfs: modify clean_io_failure " Miao Xie
2014-09-12 10:44 ` [PATCH v4 09/11] Btrfs: Set real mirror number for read operation on RAID0/5/6 Miao Xie
2014-09-12 10:44 ` [PATCH v4 10/11] Btrfs: implement repair function when direct read fails Miao Xie
2014-09-12 10:44 ` [PATCH v4 11/11] Btrfs: cleanup the read failure record after write or when the inode is freeing Miao Xie
2014-09-12 14:50 ` [PATCH v4 00/11] Implement the data repair function for direct read Chris Mason
2014-07-29 9:24 ` [PATCH v2 12/12] Btrfs: cleanup the read failure record after write or when the inode is freeing Miao Xie
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=1406625850-32168-5-git-send-email-miaox@cn.fujitsu.com \
--to=miaox@cn.fujitsu.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.