diff options
| author | Yan, Zheng <zheng.z.yan@intel.com> | 2013-03-01 10:55:39 +0800 |
|---|---|---|
| committer | Sage Weil <sage@inktank.com> | 2013-05-01 21:16:10 -0700 |
| commit | 6070e0c1e2b515ad5edc2f8224031b051bd08109 (patch) | |
| tree | 2a9bb6aea63854927ce03a2ecee8ccaa6b914008 /fs/ceph | |
| parent | 7971bd92baf729fcebe04d7330ac22dc668d0261 (diff) | |
| download | linux-6070e0c1e2b515ad5edc2f8224031b051bd08109.tar.gz linux-6070e0c1e2b515ad5edc2f8224031b051bd08109.tar.bz2 linux-6070e0c1e2b515ad5edc2f8224031b051bd08109.zip | |
ceph: don't early drop Fw cap
ceph_aio_write() has an optimization that marks CEPH_CAP_FILE_WR
cap dirty before data is copied to page cache and inode size is
updated. The optimization avoids slow cap revocation caused by
balance_dirty_pages(), but introduces inode size update race. If
ceph_check_caps() flushes the dirty cap before the inode size is
updated, MDS can miss the new inode size. So just remove the
optimization.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Diffstat (limited to 'fs/ceph')
| -rw-r--r-- | fs/ceph/file.c | 42 |
1 files changed, 17 insertions, 25 deletions
diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b86d2a0eb145..3d1aefeee948 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -724,9 +724,12 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; + sb_start_write(inode->i_sb); retry_snap: - if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) - return -ENOSPC; + if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) { + ret = -ENOSPC; + goto out; + } __ceph_do_pending_vmtruncate(inode); dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n", inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len, @@ -750,29 +753,10 @@ retry_snap: ret = ceph_sync_write(file, iov->iov_base, iov->iov_len, &iocb->ki_pos); } else { - /* - * buffered write; drop Fw early to avoid slow - * revocation if we get stuck on balance_dirty_pages - */ - int dirty; - - spin_lock(&ci->i_ceph_lock); - dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR); - spin_unlock(&ci->i_ceph_lock); - ceph_put_cap_refs(ci, got); - - ret = generic_file_aio_write(iocb, iov, nr_segs, pos); - if ((ret >= 0 || ret == -EIOCBQUEUED) && - ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host) - || ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) { - err = vfs_fsync_range(file, pos, pos + ret - 1, 1); - if (err < 0) - ret = err; - } - - if (dirty) - __mark_inode_dirty(inode, dirty); - goto out; + mutex_lock(&inode->i_mutex); + ret = __generic_file_aio_write(iocb, iov, nr_segs, + &iocb->ki_pos); + mutex_unlock(&inode->i_mutex); } if (ret >= 0) { @@ -790,12 +774,20 @@ out_put: ceph_cap_string(got)); ceph_put_cap_refs(ci, got); + if (ret >= 0 && + ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) { + err = vfs_fsync_range(file, pos, pos + ret - 1, 1); + if (err < 0) + ret = err; + } out: if (ret == -EOLDSNAPC) { dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n", inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len); goto retry_snap; } + sb_end_write(inode->i_sb); return ret; } |