ceph-devel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: xiubli@redhat.com
To: jlayton@kernel.org
Cc: idryomov@gmail.com, pdonnell@redhat.com,
	ceph-devel@vger.kernel.org, Xiubo Li <xiubli@redhat.com>
Subject: [PATCH] ceph: try to reconnect to the export targets
Date: Thu, 12 Aug 2021 12:10:42 +0800	[thread overview]
Message-ID: <20210812041042.132984-1-xiubli@redhat.com> (raw)

From: Xiubo Li <xiubli@redhat.com>

In case the export MDS is crashed just after the EImportStart journal
is flushed, so when a standby MDS takes over it and when replaying
the EImportStart journal the MDS will wait the client to reconnect,
but the client may never register/open the sessions yet.

We will try to reconnect that MDSes if they're in the export targets
and in RECONNECT state.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
---
 fs/ceph/mds_client.c | 58 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 14e44de05812..7dfe7a804320 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4182,13 +4182,24 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			  struct ceph_mdsmap *newmap,
 			  struct ceph_mdsmap *oldmap)
 {
-	int i;
+	int i, err;
+	int *export_targets;
 	int oldstate, newstate;
 	struct ceph_mds_session *s;
+	struct ceph_mds_info *m_info;
 
 	dout("check_new_map new %u old %u\n",
 	     newmap->m_epoch, oldmap->m_epoch);
 
+	m_info = newmap->m_info;
+	export_targets = kcalloc(newmap->possible_max_rank, sizeof(int), GFP_NOFS);
+	if (export_targets && m_info) {
+		for (i = 0; i < m_info->num_export_targets; i++) {
+			BUG_ON(m_info->export_targets[i] >= newmap->possible_max_rank);
+			export_targets[m_info->export_targets[i]] = 1;
+		}
+	}
+
 	for (i = 0; i < oldmap->possible_max_rank && i < mdsc->max_sessions; i++) {
 		if (!mdsc->sessions[i])
 			continue;
@@ -4242,6 +4253,8 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		if (s->s_state == CEPH_MDS_SESSION_RESTARTING &&
 		    newstate >= CEPH_MDS_STATE_RECONNECT) {
 			mutex_unlock(&mdsc->mutex);
+			if (export_targets)
+				export_targets[i] = 0;
 			send_mds_reconnect(mdsc, s);
 			mutex_lock(&mdsc->mutex);
 		}
@@ -4264,6 +4277,47 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		}
 	}
 
+	for (i = 0; i < newmap->possible_max_rank; i++) {
+		if (!export_targets)
+			break;
+
+		/*
+		 * Only open and reconnect sessions that don't
+		 * exist yet.
+		 */
+		if (!export_targets[i] || __have_session(mdsc, i))
+			continue;
+
+		/*
+		 * In case the export MDS is crashed just after
+		 * the EImportStart journal is flushed, so when
+		 * a standby MDS takes over it and is replaying
+		 * the EImportStart journal the new MDS daemon
+		 * will wait the client to reconnect it, but the
+		 * client may never register/open the sessions
+		 * yet.
+		 *
+		 * It will try to reconnect that MDS daemons if
+		 * the MDSes are in the export targets and is the
+		 * RECONNECT state.
+		 */
+		newstate = ceph_mdsmap_get_state(newmap, i);
+		if (newstate != CEPH_MDS_STATE_RECONNECT)
+			continue;
+		s = __open_export_target_session(mdsc, i);
+		if (IS_ERR(s)) {
+			err = PTR_ERR(s);
+			pr_err("failed to open export target session, err %d\n",
+			       err);
+			continue;
+		}
+		dout("send reconnect to target mds.%d\n", i);
+		mutex_unlock(&mdsc->mutex);
+		send_mds_reconnect(mdsc, s);
+		mutex_lock(&mdsc->mutex);
+		ceph_put_mds_session(s);
+	}
+
 	for (i = 0; i < newmap->possible_max_rank && i < mdsc->max_sessions; i++) {
 		s = mdsc->sessions[i];
 		if (!s)
@@ -4278,6 +4332,8 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			__open_export_target_sessions(mdsc, s);
 		}
 	}
+
+	kfree(export_targets);
 }
 
 
-- 
2.27.0


             reply	other threads:[~2021-08-12  4:11 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-12  4:10 xiubli [this message]
2021-08-16 12:05 ` [PATCH] ceph: try to reconnect to the export targets Jeff Layton
2021-08-17  3:03   ` Xiubo Li
2021-08-17 17:56   ` Gregory Farnum
2021-08-17 18:14     ` Jeff Layton
2021-08-17 18:48       ` Gregory Farnum

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210812041042.132984-1-xiubli@redhat.com \
    --to=xiubli@redhat.com \
    --cc=ceph-devel@vger.kernel.org \
    --cc=idryomov@gmail.com \
    --cc=jlayton@kernel.org \
    --cc=pdonnell@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).