[PATCH 0/3] rbd: make sure we have latest osdmap on 'rbd map'

[PATCH 0/3] rbd: make sure we have latest osdmap on 'rbd map'

[Ilya Dryomov]

Hello,

This is a rewrite of the fix for #8184 to use MMonGetVersion message
instead of a kludgy timeout.

Thanks,

                Ilya


Ilya Dryomov (3):
  libceph: mon_get_version request infrastructure
  libceph: add ceph_monc_wait_osdmap()
  rbd: make sure we have latest osdmap on 'rbd map'

 drivers/block/rbd.c             |   27 ++++++--
 include/linux/ceph/mon_client.h |   13 ++--
 net/ceph/ceph_common.c          |    2 +
 net/ceph/debugfs.c              |    2 +
 net/ceph/mon_client.c           |  146 +++++++++++++++++++++++++++++++++++++--
 5 files changed, 175 insertions(+), 15 deletions(-)

-- 
1.7.10.4

[PATCH 1/3] libceph: mon_get_version request infrastructure

[Ilya Dryomov]

Add support for mon_get_version requests to libceph.  This reuses much
of the ceph_mon_generic_request infrastructure, with one exception.
The mon_get_version reply hdr->tid is always 0 and that makes it
impossible to lookup ceph_mon_generic_request contexts by tid in
get_generic_reply().  So, instead of preallocating reply messages like
its done for statfs and poolop requests, we allocate a reply message on
the reply path.  This can probably interfere with revoke, but I don't
see a better way.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
---
 include/linux/ceph/mon_client.h |   11 ++--
 net/ceph/ceph_common.c          |    2 +
 net/ceph/debugfs.c              |    2 +
 net/ceph/mon_client.c           |  119 ++++++++++++++++++++++++++++++++++++---
 4 files changed, 123 insertions(+), 11 deletions(-)

diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index a486f390dfbe..d8060dd87f16 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -40,9 +40,9 @@ struct ceph_mon_request {
 };
 
 /*
- * ceph_mon_generic_request is being used for the statfs and poolop requests
- * which are bening done a bit differently because we need to get data back
- * to the caller
+ * ceph_mon_generic_request is being used for the statfs, poolop and
+ * mon_get_version requests which are being done a bit differently
+ * because we need to get data back to the caller
  */
 struct ceph_mon_generic_request {
 	struct kref kref;
@@ -53,7 +53,7 @@ struct ceph_mon_generic_request {
 	int buf_len;
 	struct completion completion;
 	struct ceph_msg *request;  /* original request */
-	struct ceph_msg *reply;    /* and reply */
+	struct ceph_msg *reply;    /* and reply, NULL for mon_get_version */
 };
 
 struct ceph_mon_client {
@@ -108,6 +108,9 @@ extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
 extern int ceph_monc_do_statfs(struct ceph_mon_client *monc,
 			       struct ceph_statfs *buf);
 
+extern int ceph_monc_do_get_version(struct ceph_mon_client *monc,
+				    const char *what, u64 *newest);
+
 extern int ceph_monc_open_session(struct ceph_mon_client *monc);
 
 extern int ceph_monc_validate_auth(struct ceph_mon_client *monc);
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 67d7721d237e..1675021d8c12 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -72,6 +72,8 @@ const char *ceph_msg_type_name(int type)
 	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
 	case CEPH_MSG_STATFS: return "statfs";
 	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+	case CEPH_MSG_MON_GET_VERSION: return "mon_get_version";
+	case CEPH_MSG_MON_GET_VERSION_REPLY: return "mon_get_version_reply";
 	case CEPH_MSG_MDS_MAP: return "mds_map";
 	case CEPH_MSG_CLIENT_SESSION: return "client_session";
 	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 10421a4b76f8..45405aadee11 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -127,6 +127,8 @@ static int monc_show(struct seq_file *s, void *p)
 		op = le16_to_cpu(req->request->hdr.type);
 		if (op == CEPH_MSG_STATFS)
 			seq_printf(s, "%lld statfs\n", req->tid);
+		else if (op == CEPH_MSG_MON_GET_VERSION)
+			seq_printf(s, "%llu get_version", req->tid);
 		else
 			seq_printf(s, "%lld unknown\n", req->tid);
 	}
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 2ac9ef35110b..d64023965d1c 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -477,15 +477,12 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
 	return m;
 }
 
-static int do_generic_request(struct ceph_mon_client *monc,
-			      struct ceph_mon_generic_request *req)
+static int __do_generic_request(struct ceph_mon_client *monc,
+				struct ceph_mon_generic_request *req)
 {
 	int err;
 
 	/* register request */
-	mutex_lock(&monc->mutex);
-	req->tid = ++monc->last_tid;
-	req->request->hdr.tid = cpu_to_le64(req->tid);
 	__insert_generic_request(monc, req);
 	monc->num_generic_requests++;
 	ceph_con_send(&monc->con, ceph_msg_get(req->request));
@@ -496,13 +493,27 @@ static int do_generic_request(struct ceph_mon_client *monc,
 	mutex_lock(&monc->mutex);
 	rb_erase(&req->node, &monc->generic_request_tree);
 	monc->num_generic_requests--;
-	mutex_unlock(&monc->mutex);
 
 	if (!err)
 		err = req->result;
 	return err;
 }
 
+static int do_generic_request(struct ceph_mon_client *monc,
+			      struct ceph_mon_generic_request *req)
+{
+	int err;
+
+	mutex_lock(&monc->mutex);
+	req->tid = ++monc->last_tid;
+	req->request->hdr.tid = cpu_to_le64(req->tid);
+
+	err = __do_generic_request(monc, req);
+
+	mutex_unlock(&monc->mutex);
+	return err;
+}
+
 /*
  * statfs
  */
@@ -579,6 +590,94 @@ out:
 }
 EXPORT_SYMBOL(ceph_monc_do_statfs);
 
+static void handle_get_version_reply(struct ceph_mon_client *monc,
+				     struct ceph_msg *msg)
+{
+	struct ceph_mon_generic_request *req;
+	void *p, *end;
+	u64 handle;
+	u64 version;
+
+	p = msg->front.iov_base;
+	end = p + msg->front_alloc_len;
+
+	ceph_decode_64_safe(&p, end, handle, bad);
+	ceph_decode_64_safe(&p, end, version, bad);
+
+	mutex_lock(&monc->mutex);
+	req = __lookup_generic_req(monc, handle);
+	if (req) {
+		dout("%s handle %llu version %llu\n", __func__, handle,
+		     version);
+		*(u64 *)req->buf = version;
+		req->result = 0;
+		get_generic_request(req);
+	} else {
+		pr_info("%s unknown handle %llu\n", __func__, handle);
+	}
+	mutex_unlock(&monc->mutex);
+	if (req) {
+		complete_all(&req->completion);
+		put_generic_request(req);
+	}
+
+	BUG_ON(req && req->reply);
+
+	return;
+bad:
+	pr_err("corrupt mon_get_version reply\n");
+	ceph_msg_dump(msg);
+}
+
+int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
+			     u64 *newest)
+{
+	struct ceph_mon_generic_request *req;
+	void *p, *end;
+	int err;
+
+	req = kzalloc(sizeof(*req), GFP_NOFS);
+	if (!req)
+		return -ENOMEM;
+
+	kref_init(&req->kref);
+	req->buf = newest;
+	req->buf_len = sizeof(*newest);
+	init_completion(&req->completion);
+
+	req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION,
+				    sizeof(u64) + sizeof(u32) + strlen(what),
+				    GFP_NOFS, true);
+	if (!req->request) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * Preallocating a reply ceph_msg for mon_get_version requests
+	 * is pointless - their reply hdr->tid is always 0, which means
+	 * that the ceph_mon_generic_request cannot be looked up in
+	 * get_generic_reply().
+	 */
+
+	p = req->request->front.iov_base;
+	end = p + req->request->front_alloc_len;
+
+	/* fill out request */
+	mutex_lock(&monc->mutex);
+	req->tid = ++monc->last_tid;
+	ceph_encode_64(&p, req->tid); /* handle */
+	ceph_encode_string(&p, end, what, strlen(what));
+
+	err = __do_generic_request(monc, req);
+
+	mutex_unlock(&monc->mutex);
+out:
+	kref_put(&req->kref, release_generic_request);
+	return err;
+}
+EXPORT_SYMBOL(ceph_monc_do_get_version);
+
 /*
  * pool ops
  */
@@ -712,7 +811,8 @@ static void __resend_generic_request(struct ceph_mon_client *monc)
 	for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) {
 		req = rb_entry(p, struct ceph_mon_generic_request, node);
 		ceph_msg_revoke(req->request);
-		ceph_msg_revoke_incoming(req->reply);
+		if (req->reply)
+			ceph_msg_revoke_incoming(req->reply);
 		ceph_con_send(&monc->con, ceph_msg_get(req->request));
 	}
 }
@@ -981,6 +1081,10 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 		handle_statfs_reply(monc, msg);
 		break;
 
+	case CEPH_MSG_MON_GET_VERSION_REPLY:
+		handle_get_version_reply(monc, msg);
+		break;
+
 	case CEPH_MSG_POOLOP_REPLY:
 		handle_poolop_reply(monc, msg);
 		break;
@@ -1032,6 +1136,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	case CEPH_MSG_MON_MAP:
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
+	case CEPH_MSG_MON_GET_VERSION_REPLY:
 		m = ceph_msg_new(type, front_len, GFP_NOFS, false);
 		if (!m)
 			return NULL;	/* ENOMEM--return skip == 0 */
-- 
1.7.10.4

[PATCH 2/3] libceph: add ceph_monc_wait_osdmap()

[Ilya Dryomov]

Add ceph_monc_wait_osdmap(), which will block until the osdmap with the
specified epoch is received or timeout occurs.

Export both of these as they are going to be needed by rbd.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
---
 include/linux/ceph/mon_client.h |    2 ++
 net/ceph/mon_client.c           |   27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index d8060dd87f16..99ea0d60042f 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -104,6 +104,8 @@ extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have);
 extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have);
 
 extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
+extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
+				 unsigned long timeout);
 
 extern int ceph_monc_do_statfs(struct ceph_mon_client *monc,
 			       struct ceph_statfs *buf);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index d64023965d1c..7aa1ab1dbbf6 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -296,6 +296,33 @@ void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc)
 		__send_subscribe(monc);
 	mutex_unlock(&monc->mutex);
 }
+EXPORT_SYMBOL(ceph_monc_request_next_osdmap);
+
+int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
+			  unsigned long timeout)
+{
+	unsigned long started = jiffies;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	while (monc->have_osdmap < epoch) {
+		mutex_unlock(&monc->mutex);
+
+		if (timeout != 0 && time_after_eq(jiffies, started + timeout))
+			return -ETIMEDOUT;
+
+		ret = wait_event_interruptible_timeout(monc->client->auth_wq,
+					 monc->have_osdmap >= epoch, timeout);
+		if (ret < 0)
+			return ret;
+
+		mutex_lock(&monc->mutex);
+	}
+
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_monc_wait_osdmap);
 
 /*
  *
-- 
1.7.10.4

[PATCH 3/3] rbd: make sure we have latest osdmap on 'rbd map'

[Ilya Dryomov]

Given an existing idle mapping (img1), mapping an image (img2) in
a newly created pool (pool2) fails:

    $ ceph osd pool create pool1 8 8
    $ rbd create --size 1000 pool1/img1
    $ sudo rbd map pool1/img1
    $ ceph osd pool create pool2 8 8
    $ rbd create --size 1000 pool2/img2
    $ sudo rbd map pool2/img2
    rbd: sysfs write failed
    rbd: map failed: (2) No such file or directory

This is because client instances are shared by default and we don't
request an osdmap update when bumping a ref on an existing client.  The
fix is to use the mon_get_version request to see if the osdmap we have
is the latest, and block until the requested update is received if it's
not.

Fixes: http://tracker.ceph.com/issues/8184

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
---
 drivers/block/rbd.c |   27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 552a2edcaa74..a3734726eef9 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -723,15 +723,34 @@ static int parse_rbd_opts_token(char *c, void *private)
 static struct rbd_client *rbd_get_client(struct ceph_options *ceph_opts)
 {
 	struct rbd_client *rbdc;
+	u64 newest_epoch;
 
 	mutex_lock_nested(&client_mutex, SINGLE_DEPTH_NESTING);
 	rbdc = rbd_client_find(ceph_opts);
-	if (rbdc)	/* using an existing client */
-		ceph_destroy_options(ceph_opts);
-	else
+	if (!rbdc) {
 		rbdc = rbd_client_create(ceph_opts);
-	mutex_unlock(&client_mutex);
+		mutex_unlock(&client_mutex);
+		return rbdc;
+	}
+
+	/*
+	 * Using an existing client, make sure we've got the latest
+	 * osdmap.  Ignore the errors though, as failing to get it
+	 * doesn't necessarily prevent from working.
+	 */
+	if (ceph_monc_do_get_version(&rbdc->client->monc, "osdmap",
+				     &newest_epoch) < 0)
+		goto out;
+
+	if (rbdc->client->osdc.osdmap->epoch < newest_epoch) {
+		ceph_monc_request_next_osdmap(&rbdc->client->monc);
+		(void) ceph_monc_wait_osdmap(&rbdc->client->monc, newest_epoch,
+				    rbdc->client->options->mount_timeout * HZ);
+	}
 
+out:
+	mutex_unlock(&client_mutex);
+	ceph_destroy_options(ceph_opts);
 	return rbdc;
 }
 
-- 
1.7.10.4

[PATCH v2] rbd: make sure we have latest osdmap on 'rbd map'

[Ilya Dryomov]

Given an existing idle mapping (img1), mapping an image (img2) in
a newly created pool (pool2) fails:

    $ ceph osd pool create pool1 8 8
    $ rbd create --size 1000 pool1/img1
    $ sudo rbd map pool1/img1
    $ ceph osd pool create pool2 8 8
    $ rbd create --size 1000 pool2/img2
    $ sudo rbd map pool2/img2
    rbd: sysfs write failed
    rbd: map failed: (2) No such file or directory

This is because client instances are shared by default and we don't
request an osdmap update when bumping a ref on an existing client.  The
fix is to use the mon_get_version request to see if the osdmap we have
is the latest, and block until the requested update is received if it's
not.

Fixes: http://tracker.ceph.com/issues/8184

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
---
v2:
- send mon_get_version request and wait for a reply only if we were
  unable to locate the pool (i.e. don't hurt the common case)

 drivers/block/rbd.c |   36 +++++++++++++++++++++++++++++++++---
 1 file changed, 33 insertions(+), 3 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 552a2edcaa74..daf7b4659b4a 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4683,6 +4683,38 @@ out_err:
 }
 
 /*
+ * Return pool id (>= 0) or a negative error code.
+ */
+static int rbd_add_get_pool_id(struct rbd_client *rbdc, const char *pool_name)
+{
+	u64 newest_epoch;
+	unsigned long timeout = rbdc->client->options->mount_timeout * HZ;
+	int tries = 0;
+	int ret;
+
+again:
+	ret = ceph_pg_poolid_by_name(rbdc->client->osdc.osdmap, pool_name);
+	if (ret == -ENOENT && tries++ < 1) {
+		ret = ceph_monc_do_get_version(&rbdc->client->monc, "osdmap",
+					       &newest_epoch);
+		if (ret < 0)
+			return ret;
+
+		if (rbdc->client->osdc.osdmap->epoch < newest_epoch) {
+			ceph_monc_request_next_osdmap(&rbdc->client->monc);
+			(void) ceph_monc_wait_osdmap(&rbdc->client->monc,
+						     newest_epoch, timeout);
+			goto again;
+		} else {
+			/* the osdmap we have is new enough */
+			return -ENOENT;
+		}
+	}
+
+	return ret;
+}
+
+/*
  * An rbd format 2 image has a unique identifier, distinct from the
  * name given to it by the user.  Internally, that identifier is
  * what's used to specify the names of objects related to the image.
@@ -5053,7 +5085,6 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	struct rbd_options *rbd_opts = NULL;
 	struct rbd_spec *spec = NULL;
 	struct rbd_client *rbdc;
-	struct ceph_osd_client *osdc;
 	bool read_only;
 	int rc = -ENOMEM;
 
@@ -5075,8 +5106,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	}
 
 	/* pick the pool */
-	osdc = &rbdc->client->osdc;
-	rc = ceph_pg_poolid_by_name(osdc->osdmap, spec->pool_name);
+	rc = rbd_add_get_pool_id(rbdc, spec->pool_name);
 	if (rc < 0)
 		goto err_out_client;
 	spec->pool_id = (u64)rc;
-- 
1.7.10.4

Re: [PATCH 3/3] rbd: make sure we have latest osdmap on 'rbd map'

[Sage Weil]

On Thu, 24 Apr 2014, Ilya Dryomov wrote:
> Given an existing idle mapping (img1), mapping an image (img2) in
> a newly created pool (pool2) fails:
> 
>     $ ceph osd pool create pool1 8 8
>     $ rbd create --size 1000 pool1/img1
>     $ sudo rbd map pool1/img1
>     $ ceph osd pool create pool2 8 8
>     $ rbd create --size 1000 pool2/img2
>     $ sudo rbd map pool2/img2
>     rbd: sysfs write failed
>     rbd: map failed: (2) No such file or directory
> 
> This is because client instances are shared by default and we don't
> request an osdmap update when bumping a ref on an existing client.  The
> fix is to use the mon_get_version request to see if the osdmap we have
> is the latest, and block until the requested update is received if it's
> not.

This is slightly more heavyweight than the userspace client's approach.  
There, we only check for a newer osdmap if we find that the pool doesn't 
exist.  That shouldn't be too difficult to mirror here... probably just 
expose a wait_for_latest_map() function, and call that + retry from the 
rbd map code?

sage

> 
> Fixes: http://tracker.ceph.com/issues/8184
> 
> Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
> ---
>  drivers/block/rbd.c |   27 +++++++++++++++++++++++----
>  1 file changed, 23 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
> index 552a2edcaa74..a3734726eef9 100644
> --- a/drivers/block/rbd.c
> +++ b/drivers/block/rbd.c
> @@ -723,15 +723,34 @@ static int parse_rbd_opts_token(char *c, void *private)
>  static struct rbd_client *rbd_get_client(struct ceph_options *ceph_opts)
>  {
>  	struct rbd_client *rbdc;
> +	u64 newest_epoch;
>  
>  	mutex_lock_nested(&client_mutex, SINGLE_DEPTH_NESTING);
>  	rbdc = rbd_client_find(ceph_opts);
> -	if (rbdc)	/* using an existing client */
> -		ceph_destroy_options(ceph_opts);
> -	else
> +	if (!rbdc) {
>  		rbdc = rbd_client_create(ceph_opts);
> -	mutex_unlock(&client_mutex);
> +		mutex_unlock(&client_mutex);
> +		return rbdc;
> +	}
> +
> +	/*
> +	 * Using an existing client, make sure we've got the latest
> +	 * osdmap.  Ignore the errors though, as failing to get it
> +	 * doesn't necessarily prevent from working.
> +	 */
> +	if (ceph_monc_do_get_version(&rbdc->client->monc, "osdmap",
> +				     &newest_epoch) < 0)
> +		goto out;
> +
> +	if (rbdc->client->osdc.osdmap->epoch < newest_epoch) {
> +		ceph_monc_request_next_osdmap(&rbdc->client->monc);
> +		(void) ceph_monc_wait_osdmap(&rbdc->client->monc, newest_epoch,
> +				    rbdc->client->options->mount_timeout * HZ);
> +	}
>  
> +out:
> +	mutex_unlock(&client_mutex);
> +	ceph_destroy_options(ceph_opts);
>  	return rbdc;
>  }
>  
> -- 
> 1.7.10.4
> 
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
> 

Re: [PATCH 3/3] rbd: make sure we have latest osdmap on 'rbd map'

[Sage Weil]

On Wed, 7 May 2014, Sage Weil wrote:
> On Thu, 24 Apr 2014, Ilya Dryomov wrote:
> > Given an existing idle mapping (img1), mapping an image (img2) in
> > a newly created pool (pool2) fails:
> > 
> >     $ ceph osd pool create pool1 8 8
> >     $ rbd create --size 1000 pool1/img1
> >     $ sudo rbd map pool1/img1
> >     $ ceph osd pool create pool2 8 8
> >     $ rbd create --size 1000 pool2/img2
> >     $ sudo rbd map pool2/img2
> >     rbd: sysfs write failed
> >     rbd: map failed: (2) No such file or directory
> > 
> > This is because client instances are shared by default and we don't
> > request an osdmap update when bumping a ref on an existing client.  The
> > fix is to use the mon_get_version request to see if the osdmap we have
> > is the latest, and block until the requested update is received if it's
> > not.
> 
> This is slightly more heavyweight than the userspace client's approach.  
> There, we only check for a newer osdmap if we find that the pool doesn't 
> exist.  That shouldn't be too difficult to mirror here... probably just 
> expose a wait_for_latest_map() function, and call that + retry from the 
> rbd map code?

(Der, and I see now that your 2/3 patch already exposes that method. :)

sage


> 
> sage
> 
> > 
> > Fixes: http://tracker.ceph.com/issues/8184
> > 
> > Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
> > ---
> >  drivers/block/rbd.c |   27 +++++++++++++++++++++++----
> >  1 file changed, 23 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
> > index 552a2edcaa74..a3734726eef9 100644
> > --- a/drivers/block/rbd.c
> > +++ b/drivers/block/rbd.c
> > @@ -723,15 +723,34 @@ static int parse_rbd_opts_token(char *c, void *private)
> >  static struct rbd_client *rbd_get_client(struct ceph_options *ceph_opts)
> >  {
> >  	struct rbd_client *rbdc;
> > +	u64 newest_epoch;
> >  
> >  	mutex_lock_nested(&client_mutex, SINGLE_DEPTH_NESTING);
> >  	rbdc = rbd_client_find(ceph_opts);
> > -	if (rbdc)	/* using an existing client */
> > -		ceph_destroy_options(ceph_opts);
> > -	else
> > +	if (!rbdc) {
> >  		rbdc = rbd_client_create(ceph_opts);
> > -	mutex_unlock(&client_mutex);
> > +		mutex_unlock(&client_mutex);
> > +		return rbdc;
> > +	}
> > +
> > +	/*
> > +	 * Using an existing client, make sure we've got the latest
> > +	 * osdmap.  Ignore the errors though, as failing to get it
> > +	 * doesn't necessarily prevent from working.
> > +	 */
> > +	if (ceph_monc_do_get_version(&rbdc->client->monc, "osdmap",
> > +				     &newest_epoch) < 0)
> > +		goto out;
> > +
> > +	if (rbdc->client->osdc.osdmap->epoch < newest_epoch) {
> > +		ceph_monc_request_next_osdmap(&rbdc->client->monc);
> > +		(void) ceph_monc_wait_osdmap(&rbdc->client->monc, newest_epoch,
> > +				    rbdc->client->options->mount_timeout * HZ);
> > +	}
> >  
> > +out:
> > +	mutex_unlock(&client_mutex);
> > +	ceph_destroy_options(ceph_opts);
> >  	return rbdc;
> >  }
> >  
> > -- 
> > 1.7.10.4
> > 
> > --
> > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html
> > 
> > 
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
>