From mboxrd@z Thu Jan 1 00:00:00 1970 From: Alex Elder Subject: Re: [PATCH] libceph: init sent and completed when starting Date: Sat, 11 May 2013 12:48:37 -0500 Message-ID: <518E8475.6010608@inktank.com> References: <518E81BC.5020702@inktank.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: Received: from mail-ia0-f178.google.com ([209.85.210.178]:62606 "EHLO mail-ia0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751416Ab3EKRsi (ORCPT ); Sat, 11 May 2013 13:48:38 -0400 Received: by mail-ia0-f178.google.com with SMTP id i9so1961862iad.23 for ; Sat, 11 May 2013 10:48:38 -0700 (PDT) Received: from [172.22.22.4] (c-71-195-31-37.hsd1.mn.comcast.net. [71.195.31.37]) by mx.google.com with ESMTPSA id xf4sm5658029igb.8.2013.05.11.10.48.37 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Sat, 11 May 2013 10:48:37 -0700 (PDT) In-Reply-To: <518E81BC.5020702@inktank.com> Sender: ceph-devel-owner@vger.kernel.org List-ID: To: ceph-devel@vger.kernel.org On 05/11/2013 12:37 PM, Alex Elder wrote: > The rbd code has a need to be able to restart an osd request that > has already been started and completed once before. This currently > wouldn't work right because the osd client code assumes an osd > request will be started exactly once Certain fields in a request > are never cleared and this leads to trouble if you try to reuse it. This patch and the next two, and the two series of patches that follow them, are available in the "review/wip-flatten" branch of the ceph-glient git repository. -Alex > Specifically, the r_sent, r_got_reply, and r_completed fields are > never cleared. The r_sent field records the osd incarnation at the > time the request was sent to that osd. If that's non-zero, the > message won't get re-mapped to a target osd properly, and won't be > put on the unsafe requests list the first time it's sent as it > should. The r_got_reply field is used in handle_reply() to ensure > the reply to a request is processed only once. And the r_completed > field is used for lingering requests to avoid calling the callback > function every time the osd client re-sends the request on behalf of > its initiator. > > Each osd request passes through ceph_osdc_start_request() when > responsibility for the request is handed over to the osd client for > completion. We can safely zero these three fields there each time a > request gets started. > > One last related change--clear the r_linger flag when a request > is no longer registered as a linger request. > > This resolves: > http://tracker.ceph.com/issues/5026 > > Signed-off-by: Alex Elder > --- > net/ceph/osd_client.c | 5 ++++- > 1 file changed, 4 insertions(+), 1 deletion(-) > > diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c > index a3395fd..d5953b8 100644 > --- a/net/ceph/osd_client.c > +++ b/net/ceph/osd_client.c > @@ -1204,6 +1204,7 @@ void ceph_osdc_unregister_linger_request(struct > ceph_osd_client *osdc, > mutex_lock(&osdc->request_mutex); > if (req->r_linger) { > __unregister_linger_request(osdc, req); > + req->r_linger = 0; > ceph_osdc_put_request(req); > } > mutex_unlock(&osdc->request_mutex); > @@ -2120,7 +2121,9 @@ int ceph_osdc_start_request(struct ceph_osd_client > *osdc, > down_read(&osdc->map_sem); > mutex_lock(&osdc->request_mutex); > __register_request(osdc, req); > - WARN_ON(req->r_sent); > + req->r_sent = 0; > + req->r_got_reply = 0; > + req->r_completed = 0; > rc = __map_request(osdc, req, 0); > if (rc < 0) { > if (nofail) { >