summaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
authorJeff Layton <jlayton@kernel.org>2020-04-01 18:27:25 -0400
committerIlya Dryomov <idryomov@gmail.com>2020-06-01 13:22:52 +0200
commitd67c72e6cce99eab5ab9d62c599e33e5141ff8b4 (patch)
tree9f615fbcc18b0ce30ac10f6a6809691c38f5359b /fs/ceph
parent1cf03a68e791b1673bc4daaa88a0820f34f538f8 (diff)
ceph: request expedited service on session's last cap flush
When flushing a lot of caps to the MDS's at once (e.g. for syncfs), we can end up waiting a substantial amount of time for MDS replies, due to the fact that it may delay some of them so that it can batch them up together in a single journal transaction. This can lead to stalls when calling sync or syncfs. What we'd really like to do is request expedited service on the _last_ cap we're flushing back to the server. If the CHECK_CAPS_FLUSH flag is set on the request and the current inode was the last one on the session->s_cap_dirty list, then mark the request with CEPH_CLIENT_CAPS_SYNC. Note that this heuristic is not perfect. New inodes can race onto the list after we've started flushing, but it does seem to fix some common use cases. URL: https://tracker.ceph.com/issues/44744 Reported-by: Jan Fajerski <jfajerski@suse.com> Signed-off-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: "Yan, Zheng" <zyan@redhat.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/caps.c8
1 files changed, 6 insertions, 2 deletions
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d5ad2434bb07..2558fd14126a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1997,6 +1997,7 @@ retry_locked:
}
for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
+ int mflags = 0;
struct cap_msg_args arg;
cap = rb_entry(p, struct ceph_cap, ci_node);
@@ -2128,6 +2129,9 @@ ack:
flushing = ci->i_dirty_caps;
flush_tid = __mark_caps_flushing(inode, session, false,
&oldest_flush_tid);
+ if (flags & CHECK_CAPS_FLUSH &&
+ list_empty(&session->s_cap_dirty))
+ mflags |= CEPH_CLIENT_CAPS_SYNC;
} else {
flushing = 0;
flush_tid = 0;
@@ -2138,8 +2142,8 @@ ack:
mds = cap->mds; /* remember mds, so we don't repeat */
- __prep_cap(&arg, cap, CEPH_CAP_OP_UPDATE, 0, cap_used, want,
- retain, flushing, flush_tid, oldest_flush_tid);
+ __prep_cap(&arg, cap, CEPH_CAP_OP_UPDATE, mflags, cap_used,
+ want, retain, flushing, flush_tid, oldest_flush_tid);
spin_unlock(&ci->i_ceph_lock);
__send_cap(mdsc, &arg, ci);