Add support for split OSD adds

Allows creating multiple OSDs on a single (NVMe) block device,
leveraging the "ceph-volume lvm batch" command. Replaces the previous
method of creating OSDs.

Also adds a new ZK item for each OSD indicating if it is split or not.

daemon-common/ceph.py

@@ -211,6 +211,7 @@ def getOSDInformation(zkhandler, osd_id):
     # Get the devices
     osd_node = zkhandler.read(("osd.node", osd_id))
     osd_device = zkhandler.read(("osd.device", osd_id))
+    osd_is_split = zkhandler.read(("osd.is_split", osd_id))
     osd_db_device = zkhandler.read(("osd.db_device", osd_id))
     # Parse the stats data
     osd_stats_raw = zkhandler.read(("osd.stats", osd_id))
@@ -220,6 +221,7 @@ def getOSDInformation(zkhandler, osd_id):
         "id": osd_id,
         "node": osd_node,
         "device": osd_device,
+        "is_split": osd_is_split,
         "db_device": osd_db_device,
         "stats": osd_stats,
     }
@@ -266,7 +268,16 @@ def add_osd_db_vg(zkhandler, node, device):
 
 # OSD actions use the /cmd/ceph pipe
 # These actions must occur on the specific node they reference
-def add_osd(zkhandler, node, device, weight, ext_db_flag=False, ext_db_ratio=0.05):
+def add_osd(
+    zkhandler,
+    node,
+    device,
+    weight,
+    ext_db_flag=False,
+    ext_db_ratio=0.05,
+    split_flag=False,
+    split_count=1,
+):
     # Verify the target node exists
     if not common.verifyNode(zkhandler, node):
         return False, 'ERROR: No node named "{}" is present in the cluster.'.format(
@@ -284,8 +295,8 @@ def add_osd(zkhandler, node, device, weight, ext_db_flag=False, ext_db_ratio=0.0
         )
 
     # Tell the cluster to create a new OSD for the host
-    add_osd_string = "osd_add {},{},{},{},{}".format(
-        node, device, weight, ext_db_flag, ext_db_ratio
+    add_osd_string = "osd_add {},{},{},{},{},{},{}".format(
+        node, device, weight, ext_db_flag, ext_db_ratio, split_flag, split_count
     )
     zkhandler.write([("base.cmd.ceph", add_osd_string)])
     # Wait 1/2 second for the cluster to get the message and start working
@@ -295,14 +306,10 @@ def add_osd(zkhandler, node, device, weight, ext_db_flag=False, ext_db_ratio=0.0
         try:
             result = zkhandler.read("base.cmd.ceph").split()[0]
             if result == "success-osd_add":
-                message = 'Created new OSD with block device "{}" on node "{}".'.format(
-                    device, node
-                )
+                message = f'Created {split_count} new OSD(s) on node "{node}" block device "{device}"'
                 success = True
             else:
-                message = (
-                    "ERROR: Failed to create new OSD; check node logs for details."
-                )
+                message = "ERROR: Failed to create OSD(s); check node logs for details."
                 success = False
         except Exception:
             message = "ERROR: Command ignored by node."

daemon-common/migrations/versions/10.json

@@ -0,0 +1 @@
+{"version": "10", "root": "", "base": {"root": "", "schema": "/schema", "schema.version": "/schema/version", "config": "/config", "config.maintenance": "/config/maintenance", "config.primary_node": "/config/primary_node", "config.primary_node.sync_lock": "/config/primary_node/sync_lock", "config.upstream_ip": "/config/upstream_ip", "config.migration_target_selector": "/config/migration_target_selector", "cmd": "/cmd", "cmd.node": "/cmd/nodes", "cmd.domain": "/cmd/domains", "cmd.ceph": "/cmd/ceph", "logs": "/logs", "node": "/nodes", "domain": "/domains", "network": "/networks", "storage": "/ceph", "storage.health": "/ceph/health", "storage.util": "/ceph/util", "osd": "/ceph/osds", "pool": "/ceph/pools", "volume": "/ceph/volumes", "snapshot": "/ceph/snapshots"}, "logs": {"node": "", "messages": "/messages"}, "node": {"name": "", "keepalive": "/keepalive", "mode": "/daemonmode", "data.active_schema": "/activeschema", "data.latest_schema": "/latestschema", "data.static": "/staticdata", "data.pvc_version": "/pvcversion", "running_domains": "/runningdomains", "count.provisioned_domains": "/domainscount", "count.networks": "/networkscount", "state.daemon": "/daemonstate", "state.router": "/routerstate", "state.domain": "/domainstate", "cpu.load": "/cpuload", "vcpu.allocated": "/vcpualloc", "memory.total": "/memtotal", "memory.used": "/memused", "memory.free": "/memfree", "memory.allocated": "/memalloc", "memory.provisioned": "/memprov", "ipmi.hostname": "/ipmihostname", "ipmi.username": "/ipmiusername", "ipmi.password": "/ipmipassword", "sriov": "/sriov", "sriov.pf": "/sriov/pf", "sriov.vf": "/sriov/vf", "monitoring.plugins": "/monitoring_plugins", "monitoring.data": "/monitoring_data", "monitoring.health": "/monitoring_health"}, "monitoring_plugin": {"name": "", "last_run": "/last_run", "health_delta": "/health_delta", "message": "/message", "data": "/data", "runtime": "/runtime"}, "sriov_pf": {"phy": "", "mtu": "/mtu", "vfcount": "/vfcount"}, "sriov_vf": {"phy": "", "pf": "/pf", "mtu": "/mtu", "mac": "/mac", "phy_mac": "/phy_mac", "config": "/config", "config.vlan_id": "/config/vlan_id", "config.vlan_qos": "/config/vlan_qos", "config.tx_rate_min": "/config/tx_rate_min", "config.tx_rate_max": "/config/tx_rate_max", "config.spoof_check": "/config/spoof_check", "config.link_state": "/config/link_state", "config.trust": "/config/trust", "config.query_rss": "/config/query_rss", "pci": "/pci", "pci.domain": "/pci/domain", "pci.bus": "/pci/bus", "pci.slot": "/pci/slot", "pci.function": "/pci/function", "used": "/used", "used_by": "/used_by"}, "domain": {"name": "", "xml": "/xml", "state": "/state", "profile": "/profile", "stats": "/stats", "node": "/node", "last_node": "/lastnode", "failed_reason": "/failedreason", "storage.volumes": "/rbdlist", "console.log": "/consolelog", "console.vnc": "/vnc", "meta.autostart": "/node_autostart", "meta.migrate_method": "/migration_method", "meta.node_selector": "/node_selector", "meta.node_limit": "/node_limit", "meta.tags": "/tags", "migrate.sync_lock": "/migrate_sync_lock"}, "tag": {"name": "", "type": "/type", "protected": "/protected"}, "network": {"vni": "", "type": "/nettype", "mtu": "/mtu", "rule": "/firewall_rules", "rule.in": "/firewall_rules/in", "rule.out": "/firewall_rules/out", "nameservers": "/name_servers", "domain": "/domain", "reservation": "/dhcp4_reservations", "lease": "/dhcp4_leases", "ip4.gateway": "/ip4_gateway", "ip4.network": "/ip4_network", "ip4.dhcp": "/dhcp4_flag", "ip4.dhcp_start": "/dhcp4_start", "ip4.dhcp_end": "/dhcp4_end", "ip6.gateway": "/ip6_gateway", "ip6.network": "/ip6_network", "ip6.dhcp": "/dhcp6_flag"}, "reservation": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname"}, "lease": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname", "expiry": "/expiry", "client_id": "/clientid"}, "rule": {"description": "", "rule": "/rule", "order": "/order"}, "osd": {"id": "", "node": "/node", "device": "/device", "db_device": "/db_device", "fsid": "/fsid", "ofsid": "/fsid/osd", "cfsid": "/fsid/cluster", "lvm": "/lvm", "vg": "/lvm/vg", "lv": "/lvm/lv", "is_split": "/is_split", "stats": "/stats"}, "pool": {"name": "", "pgs": "/pgs", "tier": "/tier", "stats": "/stats"}, "volume": {"name": "", "stats": "/stats"}, "snapshot": {"name": "", "stats": "/stats"}}

daemon-common/zkhandler.py

@@ -540,7 +540,7 @@ class ZKHandler(object):
 #
 class ZKSchema(object):
     # Current version
-    _version = 9
+    _version = 10
 
     # Root for doing nested keys
     _schema_root = ""
@@ -719,6 +719,7 @@ class ZKSchema(object):
             "lvm": "/lvm",
             "vg": "/lvm/vg",
             "lv": "/lvm/lv",
+            "is_split": "/is_split",
             "stats": "/stats",
         },
         # The schema of an individual pool entry (/ceph/pools/{pool_name})
@@ -963,7 +964,9 @@ class ZKSchema(object):
                     kpath = f"{elem}.{ikey}"
                     # Validate that the key exists for that child
                     if not zkhandler.zk_conn.exists(self.path(kpath, child)):
-                        if elem == "pool" and ikey == "tier":
+                        if elem == "osd" and ikey == "is_split":
+                            default_data = "False"
+                        elif elem == "pool" and ikey == "tier":
                             default_data = "default"
                         else:
                             default_data = ""