Add cluster load metrics

2 files changed, 8 insertions, 2 deletions

diff --git a/metrics/src/main/java/ai/vespa/metrics/ConfigServerMetrics.java b/metrics/src/main/java/ai/vespa/metrics/ConfigServerMetrics.java
index 013c50e77cf..d323026e4ca 100644
--- a/metrics/src/main/java/ai/vespa/metrics/ConfigServerMetrics.java
+++ b/metrics/src/main/java/ai/vespa/metrics/ConfigServerMetrics.java
@@ -27,7 +27,6 @@ public enum ConfigServerMetrics implements VespaMetrics {
     MAINTENANCE_DEPLOYMENT_TRANSIENT_FAILURE("maintenanceDeployment.transientFailure", Unit.OPERATION, "Number of maintenance deployments that failed with a transient failure"),
     MAINTENANCE_DEPLOYMENT_FAILURE("maintenanceDeployment.failure", Unit.OPERATION, "Number of maintenance deployments that failed with a permanent failure"),
 
-
     // ZooKeeper related metrics
     ZK_CONNECTIONS_LOST("configserver.zkConnectionLost", Unit.CONNECTION, "Number of ZooKeeper connections lost"),
     ZK_RECONNECTED("configserver.zkReconnected", Unit.CONNECTION, "Number of ZooKeeper reconnections"),
@@ -45,8 +44,13 @@ public enum ConfigServerMetrics implements VespaMetrics {
     ORCHESTRATOR_LOCK_ACQUIRE_TIMEOUT("orchestrator.lock.acquire-timedout", Unit.OPERATION, "Number of times zookeeper lock couldn't be acquired within timeout"),
     ORCHESTRATOR_LOCK_ACQUIRE("orchestrator.lock.acquire", Unit.OPERATION, "Number of attempts to acquire zookeeper lock"),
     ORCHESTRATOR_LOCK_ACQUIRED("orchestrator.lock.acquired", Unit.OPERATION, "Number of times zookeeper lock was acquired"),
-    ORCHESTRATOR_LOCK_HOLD_LATENCY("orchestrator.lock.hold-latency", Unit.SECOND, "Time zookeeper lock was held before it was released");
+    ORCHESTRATOR_LOCK_HOLD_LATENCY("orchestrator.lock.hold-latency", Unit.SECOND, "Time zookeeper lock was held before it was released"),
 
+    // Node repository metrics
+    CLUSTER_COST("cluster.cost", Unit.DOLLAR_PER_HOUR, "The cost of the nodes allocated to a certain cluster, in $/hr"),
+    CLUSTER_LOAD_IDEAL_CPU("cluster.load.ideal.cpu", Unit.FRACTION, "The ideal cpu load of a certain cluster"),
+    CLUSTER_LOAD_IDEAL_MEMORY("cluster.load.ideal.memory", Unit.FRACTION, "The ideal memory load of a certain cluster"),
+    CLUSTER_LOAD_IDEAL_DISK("cluster.load.ideal.disk", Unit.FRACTION, "The ideal disk load of a certain cluster");
 
     private final String name;
     private final Unit unit;
diff --git a/metrics/src/main/java/ai/vespa/metrics/Unit.java b/metrics/src/main/java/ai/vespa/metrics/Unit.java
index a2123d72246..d5769707b76 100644
--- a/metrics/src/main/java/ai/vespa/metrics/Unit.java
+++ b/metrics/src/main/java/ai/vespa/metrics/Unit.java
@@ -12,6 +12,7 @@ public enum Unit {
     CONNECTION(BaseUnit.CONNECTION, "A link used for communication between a client and a server"),
     DOCUMENT(BaseUnit.DOCUMENT, "Vespa document, a collection of fields defined in a schema file"),
     DOCUMENTID(BaseUnit.DOCUMENTID, "A unique document identifier"),
+    DOLLAR_PER_HOUR(BaseUnit.MAGNITUDE, "$/hr"),
     FAILURE(BaseUnit.FAILURE, "Failures, typically for requests, operations or nodes"),
     FILE(BaseUnit.FILE, "Data file stored on the disk on a node"),
     FRACTION(BaseUnit.FRACTION, "A value in the range [0..1]. Higher values can occur for some metrics, but would indicate the value is outside of the allowed range."),
@@ -86,6 +87,7 @@ public enum Unit {
         HIT("hit"),
         INSTANCE("instance"),
         ITEM("item"),
+        MAGNITUDE("magnitude"),
         MILLISECOND("millisecond", "ms"),
         NANOSECOND("nanosecond", "ns"),
         NODE("node"),