ceph: MDS client

The MDS (metadata server) client is responsible for submitting
requests to the MDS cluster and parsing the response.  We decide which
MDS to submit each request to based on cached information about the
current partition of the directory hierarchy across the cluster.  A
stateful session is opened with each MDS before we submit requests to
it, and a mutex is used to control the ordering of messages within
each session.

An MDS request may generate two responses.  The first indicates the
operation was a success and returns any result.  A second reply is
sent when the operation commits to disk.  Note that locking on the MDS
ensures that the results of updates are visible only to the updating
client before the operation commits.  Requests are linked to the
containing directory so that an fsync will wait for them to commit.

If an MDS fails and/or recovers, we resubmit requests as needed.  We
also reconnect existing capabilities to a recovering MDS to
reestablish that shared session state.  Old dentry leases are
invalidated.

Signed-off-by: Sage Weil <sage@newdream.net>

1 files changed, 53 insertions, 0 deletions

diff --git a/fs/ceph/mdsmap.h b/fs/ceph/mdsmap.h
new file mode 100644
index 000000000000..d317308648fb
--- /dev/null
+++ b/fs/ceph/mdsmap.h
@@ -0,0 +1,53 @@
+#ifndef _FS_CEPH_MDSMAP_H
+#define _FS_CEPH_MDSMAP_H
+
+#include "types.h"
+
+/*
+ * mds map - describe servers in the mds cluster.
+ *
+ * we limit fields to those the client actually xcares about
+ */
+struct ceph_mds_info {
+	struct ceph_entity_addr addr;
+	s32 state;
+	int num_export_targets;
+	u32 *export_targets;
+};
+
+struct ceph_mdsmap {
+	u32 m_epoch, m_client_epoch, m_last_failure;
+	u32 m_root;
+	u32 m_session_timeout;          /* seconds */
+	u32 m_session_autoclose;        /* seconds */
+	u64 m_max_file_size;
+	u32 m_max_mds;                  /* size of m_addr, m_state arrays */
+	struct ceph_mds_info *m_info;
+
+	/* which object pools file data can be stored in */
+	int m_num_data_pg_pools;
+	u32 *m_data_pg_pools;
+	u32 m_cas_pg_pool;
+};
+
+static inline struct ceph_entity_addr *
+ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
+{
+	if (w >= m->m_max_mds)
+		return NULL;
+	return &m->m_info[w].addr;
+}
+
+static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
+{
+	BUG_ON(w < 0);
+	if (w >= m->m_max_mds)
+		return CEPH_MDS_STATE_DNE;
+	return m->m_info[w].state;
+}
+
+extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m);
+extern struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end);
+extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m);
+
+#endif