ceph: perform lazy writes when file mode and caps permit

If we have marked a file as "lazy" (using the ceph ioctl), perform buffered
writes when the MDS caps allow it.

Signed-off-by: Sage Weil <sage@newdream.net>

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b81be9a..1a70a3e 100644 (file)
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -337,8 +337,7 @@ static struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, int mds)
 }
 
 /*
- * Return id of any MDS with a cap, preferably FILE_WR|WRBUFFER|EXCL, else
- * -1.
+ * Return id of any MDS with a cap, preferably FILE_WR|BUFFER|EXCL, else -1.
  */
 static int __ceph_get_cap_mds(struct ceph_inode_info *ci, u32 *mseq)
 {
@@ -346,7 +345,7 @@ static int __ceph_get_cap_mds(struct ceph_inode_info *ci, u32 *mseq)
        int mds = -1;
        struct rb_node *p;
 
-       /* prefer mds with WR|WRBUFFER|EXCL caps */
+       /* prefer mds with WR|BUFFER|EXCL caps */
        for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
                cap = rb_entry(p, struct ceph_cap, ci_node);
                mds = cap->mds;
@@ -831,7 +830,7 @@ int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
 {
        int want = 0;
        int mode;
-       for (mode = 0; mode < 4; mode++)
+       for (mode = 0; mode < CEPH_FILE_MODE_NUM; mode++)
                if (ci->i_nr_by_mode[mode])
                        want |= ceph_caps_for_mode(mode);
        return want;

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 7c08698..85c86ed 100644 (file)
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -807,11 +807,12 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
                       unsigned long nr_segs, loff_t pos)
 {
        struct file *file = iocb->ki_filp;
+       struct ceph_file_info *fi = file->private_data;
        struct inode *inode = file->f_dentry->d_inode;
        struct ceph_inode_info *ci = ceph_inode(inode);
        struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc;
        loff_t endoff = pos + iov->iov_len;
-       int got = 0;
+       int want, got = 0;
        int ret, err;
 
        if (ceph_snap(inode) != CEPH_NOSNAP)
@@ -824,8 +825,11 @@ retry_snap:
        dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
             inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
             inode->i_size);
-       ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, CEPH_CAP_FILE_BUFFER,
-                           &got, endoff);
+       if (fi->fmode & CEPH_FILE_MODE_LAZY)
+               want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
+       else
+               want = CEPH_CAP_FILE_BUFFER;
+       ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff);
        if (ret < 0)
                goto out;
 
@@ -833,7 +837,7 @@ retry_snap:
             inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
             ceph_cap_string(got));
 
-       if ((got & CEPH_CAP_FILE_BUFFER) == 0 ||
+       if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
            (iocb->ki_filp->f_flags & O_DIRECT) ||
            (inode->i_sb->s_flags & MS_SYNCHRONOUS)) {
                ret = ceph_sync_write(file, iov->iov_base, iov->iov_len,