ceph: cache layout in parent dir on first sync create

If a create is done, then typically we'll end up writing to the file
soon afterward. We don't want to wait for the reply before doing that
when doing an async create, so that means we need the layout for the
new file before we've gotten the response from the MDS.

All files created in a directory will initially inherit the same layout,
so copy off the requisite info from the first synchronous create in the
directory, and save it in a new i_cached_layout field. Zero out the
layout when we lose Dc caps in the dir.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d09b9d91cf4f55411d8ac5203dd64752b9d27325..be85225b962c802a211cbced702c2858740dd818 100644 (file)
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -561,14 +561,14 @@ static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
        spin_unlock(&mdsc->cap_delay_lock);
 }
 
-/*
- * Common issue checks for add_cap, handle_cap_grant.
- */
+/* Common issue checks for add_cap, handle_cap_grant. */
 static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
                              unsigned issued)
 {
        unsigned had = __ceph_caps_issued(ci, NULL);
 
+       lockdep_assert_held(&ci->i_ceph_lock);
+
        /*
         * Each time we receive FILE_CACHE anew, we increment
         * i_rdcache_gen.
@@ -593,6 +593,13 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
                        __ceph_dir_clear_complete(ci);
                }
        }
+
+       /* Wipe saved layout if we're losing DIR_CREATE caps */
+       if (S_ISDIR(ci->vfs_inode.i_mode) && (had & CEPH_CAP_DIR_CREATE) &&
+               !(issued & CEPH_CAP_DIR_CREATE)) {
+            ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns));
+            memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
+       }
 }
 
 /*

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 7f8c4e3083018f0866d39b929c2a48ee2481f56c..b6ad64b8863a2cce9f9ed274e8dcdaf20f281fd6 100644 (file)
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -430,6 +430,23 @@ out:
        return err;
 }
 
+/* Clone the layout from a synchronous create, if the dir now has Dc caps */
+static void
+cache_file_layout(struct inode *dst, struct inode *src)
+{
+       struct ceph_inode_info *cdst = ceph_inode(dst);
+       struct ceph_inode_info *csrc = ceph_inode(src);
+
+       spin_lock(&cdst->i_ceph_lock);
+       if ((__ceph_caps_issued(cdst, NULL) & CEPH_CAP_DIR_CREATE) &&
+           !ceph_file_layout_is_valid(&cdst->i_cached_layout)) {
+               memcpy(&cdst->i_cached_layout, &csrc->i_layout,
+                       sizeof(cdst->i_cached_layout));
+               rcu_assign_pointer(cdst->i_cached_layout.pool_ns,
+                                  ceph_try_get_string(csrc->i_layout.pool_ns));
+       }
+       spin_unlock(&cdst->i_ceph_lock);
+}
 
 /*
  * Do a lookup + open with a single request.  If we get a non-existent
@@ -518,7 +535,10 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
        } else {
                dout("atomic_open finish_open on dn %p\n", dn);
                if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
-                       ceph_init_inode_acls(d_inode(dentry), &as_ctx);
+                       struct inode *newino = d_inode(dentry);
+
+                       cache_file_layout(dir, newino);
+                       ceph_init_inode_acls(newino, &as_ctx);
                        file->f_mode |= FMODE_CREATED;
                }
                err = finish_open(file, dentry, ceph_open);

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 4056c7968b86c37e3d417e99fc46a5a3700d46eb..73f986efb1fd6943177d80c7ba7c87e13cf28343 100644 (file)
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -447,6 +447,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
        ci->i_max_files = 0;
 
        memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
+       memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
        RCU_INIT_POINTER(ci->i_layout.pool_ns, NULL);
 
        ci->i_fragtree = RB_ROOT;
@@ -587,6 +588,7 @@ void ceph_evict_inode(struct inode *inode)
                ceph_buffer_put(ci->i_xattrs.prealloc_blob);
 
        ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns));
+       ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns));
 }
 
 static inline blkcnt_t calc_inode_blocks(u64 size)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a0ad9bd56b7f4a973eacf358242d5541a22d53b9..177acb9f456b6e0f0f16bb18b803ae54e8390af8 100644 (file)
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3535,8 +3535,13 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap,
        cap->cap_gen = cap->session->s_cap_gen;
 
        /* These are lost when the session goes away */
-       if (S_ISDIR(inode->i_mode))
+       if (S_ISDIR(inode->i_mode)) {
+               if (cap->issued & CEPH_CAP_DIR_CREATE) {
+                       ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns));
+                       memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
+               }
                cap->issued &= ~CEPH_CAP_ANY_DIR_OPS;
+       }
 
        if (recon_state->msg_version >= 2) {
                rec.v2.cap_id = cpu_to_le64(cap->cap_id);

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 2c479d761d327aba2bf31ee2ebaa99db5ad86f65..22b89eaeaad44b82163e4e05266780c7d31aa36d 100644 (file)
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -326,6 +326,7 @@ struct ceph_inode_info {
 
        struct ceph_dir_layout i_dir_layout;
        struct ceph_file_layout i_layout;
+       struct ceph_file_layout i_cached_layout;        // for async creates
        char *i_symlink;
 
        /* for dirs */