From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Layton Subject: [PATCH v2 0/2] ceph: fix long stalls on sync/syncfs Date: Thu, 2 Apr 2020 07:29:09 -0400 Message-ID: <20200402112911.17023-1-jlayton@kernel.org> Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Return-path: Received: from mail.kernel.org ([198.145.29.99]:50168 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2388049AbgDBL3N (ORCPT ); Thu, 2 Apr 2020 07:29:13 -0400 Sender: ceph-devel-owner@vger.kernel.org List-ID: To: ceph-devel@vger.kernel.org Cc: ukernel@gmail.com, idryomov@gmail.com, sage@redhat.com, jfajerski@suse.com, lhenriques@suse.com, gfarnum@redhat.com This is v2 of the patch I sent the other day to fix the problem of long stalls when calling sync or syncfs. This set converts the mdsc->cap_dirty list to a per-session list, and then has the only caller that looks at cap_dirty walk the list of sessions and issue flushes for each session in turn. With this, we can use an empty s_cap_dirty list as an indicator that the cap flush is the last one going to the session and can mark that one as one we're waiting on so the MDS can expedite it. This also attempts to clarify some of the locking around s_cap_dirty, and adds a FIXME comment to raise the question about locking around s_cap_flushing. Jeff Layton (2): ceph: convert mdsc->cap_dirty to a per-session list ceph: request expedited service on session's last cap flush fs/ceph/caps.c | 72 +++++++++++++++++++++++++++++++++++++++----- fs/ceph/mds_client.c | 2 +- fs/ceph/mds_client.h | 5 +-- fs/ceph/super.h | 21 +++++++++++-- 4 files changed, 87 insertions(+), 13 deletions(-) -- 2.25.1