diff options
author | Sage Weil <sage@newdream.net> | 2011-06-13 16:22:18 -0700 |
---|---|---|
committer | Sage Weil <sage@newdream.net> | 2011-06-13 16:26:22 -0700 |
commit | d7f124f129a6aea99938e0d4172c741b56fefeda (patch) | |
tree | 25ee1b2b91de6e490ddd05b00d6a3f844a224987 /fs/ceph | |
parent | 9bb0ce2b0b734f3325ea5cd6b351856eeac94f78 (diff) | |
download | linux-exynos-d7f124f129a6aea99938e0d4172c741b56fefeda.tar.gz linux-exynos-d7f124f129a6aea99938e0d4172c741b56fefeda.tar.bz2 linux-exynos-d7f124f129a6aea99938e0d4172c741b56fefeda.zip |
ceph: fix sync and dio writes across stripe boundaries
We were iterating across stripe boundaries properly, but not moving the
write buffer pointer forward. This caused us to rewrite the same data
after the break. Fix by adjusting the data pointer forward, and
recalculating the io and buffer alignment after the break.
Signed-off-by: Sage Weil <sage@newdream.net>
Diffstat (limited to 'fs/ceph')
-rw-r--r-- | fs/ceph/file.c | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 2be0f35afdfb..4698a5c553dc 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -476,9 +476,6 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, else pos = *offset; - io_align = pos & ~PAGE_MASK; - buf_align = (unsigned long)data & ~PAGE_MASK; - ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left); if (ret < 0) return ret; @@ -502,6 +499,8 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, * boundary. this isn't atomic, unfortunately. :( */ more: + io_align = pos & ~PAGE_MASK; + buf_align = (unsigned long)data & ~PAGE_MASK; len = left; if (file->f_flags & O_DIRECT) { /* write from beginning of first page, regardless of @@ -591,6 +590,7 @@ out: pos += len; written += len; left -= len; + data += written; if (left) goto more; |