We’re using foundationdb on prod, with fdb-kubernetes-operator to deploy on k8s. Recently we saw the whole cluster going down, with a lot of pods in ‘Completed’ or ‘StatusUnknownState’ [ screenshot ]
I’ve verified that the storage nodes have enough storage space, and couldn’t find any other obvious issues. I’m not sure about a couple of things
- When do pods reach (and stay) in the Completed state? I thought the operator should have rescheduled them
- Why did the operator not kill pods in ContainerStatusUnknown and reschedule new pods to get the cluster up automatically?
Here are some more logs of the operator pod
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.chooseRemovals"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.chooseRemovals","duration_seconds":0.000013421}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.excludeProcesses"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"current exclusions","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.excludeProcesses","exclusions":[]}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.excludeProcesses","duration_seconds":0.00001296}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.changeCoordinators"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Skip process with empty localities","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.changeCoordinators","process":""}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Cluster has an unhealthy coordinator","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.changeCoordinators","address":"xyz-fdb-abcd-log-55193.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local:4501"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Cluster has not enough running coordinators","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.changeCoordinators","runningCoordinators":2,"desiredCount":3}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Deferring coordinator change due to safety check","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.changeCoordinators","error":"cannot: change coordinators: cluster has 3 missing coordinators, clusters last recovery was 74.20 seconds ago, waiting until the last recovery was 120 seconds ago"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.changeCoordinators","duration_seconds":0.00008847}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Delaying requeue for sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.changeCoordinators","message":"","delayedRequeueDuration":"10s","error":"cannot: change coordinators: cluster has 3 missing coordinators, clusters last recovery was 74.20 seconds ago, waiting until the last recovery was 120 seconds ago"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.bounceProcesses"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Ignoring process with missing localities","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.bounceProcesses","address":"10.0.27.119:4501"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"ignore process group with missing process","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.bounceProcesses","processGroupID":"log-55193"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"ignore process group with missing process","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.bounceProcesses","processGroupID":"stateless-10681"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"ignore process group with missing process","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.bounceProcesses","processGroupID":"stateless-39362"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"ignore process group with missing process","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.bounceProcesses","processGroupID":"stateless-40726"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.bounceProcesses","duration_seconds":0.00003758}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.maintenanceModeChecker"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.maintenanceModeChecker","duration_seconds":0.00000259}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updatePods"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updatePods","duration_seconds":0.00028216}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.removeProcessGroups"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.removeProcessGroups","duration_seconds":0.00000603}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.removeServices"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.removeServices","duration_seconds":0.00000322}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"skip updating fault domain for process group with missing process in FoundationDB cluster status","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","processGroupID":"log-55193"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"skip updating fault domain for process group with missing process in FoundationDB cluster status","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","processGroupID":"stateless-10681"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"skip updating fault domain for process group with missing process in FoundationDB cluster status","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","processGroupID":"stateless-39362"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"skip updating fault domain for process group with missing process in FoundationDB cluster status","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","processGroupID":"stateless-40726"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Disable taint feature","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","Disabled":true}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Skip process with empty localities","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","process":""}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Cluster has an unhealthy coordinator","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","address":"xyz-fdb-abcd-log-55193.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local:4501"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Cluster has not enough running coordinators","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","runningCoordinators":2,"desiredCount":3}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Has unhealthy process group","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","method":"CheckReconciliation","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","processGroupID":"log-55193","state":"HasUnhealthyProcess","conditions":["MissingProcesses","PodFailing"]}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Has unhealthy process group","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","method":"CheckReconciliation","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","processGroupID":"stateless-10681","state":"HasUnhealthyProcess","conditions":["MissingProcesses","PodFailing"]}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Has unhealthy process group","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","method":"CheckReconciliation","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","processGroupID":"stateless-39362","state":"HasUnhealthyProcess","conditions":["MissingProcesses","PodFailing"]}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Has unhealthy process group","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","method":"CheckReconciliation","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","processGroupID":"stateless-40726","state":"HasUnhealthyProcess","conditions":["MissingProcesses","PodFailing","PodPending"]}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Not all process groups are reconciled","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","method":"CheckReconciliation","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","desiredProcessGroups":9,"reconciledProcessGroups":5}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Pending coordinator change","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","method":"CheckReconciliation","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","state":"NeedsNewCoordinators"}
{"level":"info","ts":"2026-04-10T05:34:04Z","msg":"unknown field \"spec.processes.general.podTemplate.metadata.creationTimestamp\"","controller":"foundationdbcluster","controllerGroup":"apps.foundationdb.org","controllerKind":"FoundationDBCluster","FoundationDBCluster":{"name":"xyz-fdb-abcd","namespace":"xyz-fdb-abcd"},"namespace":"xyz-fdb-abcd","name":"xyz-fdb-abcd","reconcileID":"621fa184-2655-44c4-a706-312d4e0fddeb"}
{"level":"info","ts":"2026-04-10T05:34:04Z","msg":"unknown field \"spec.processes.log.volumeClaimTemplate.metadata.creationTimestamp\"","controller":"foundationdbcluster","controllerGroup":"apps.foundationdb.org","controllerKind":"FoundationDBCluster","FoundationDBCluster":{"name":"xyz-fdb-abcd","namespace":"xyz-fdb-abcd"},"namespace":"xyz-fdb-abcd","name":"xyz-fdb-abcd","reconcileID":"621fa184-2655-44c4-a706-312d4e0fddeb"}
{"level":"info","ts":"2026-04-10T05:34:04Z","msg":"unknown field \"spec.processes.stateless.volumeClaimTemplate.metadata.creationTimestamp\"","controller":"foundationdbcluster","controllerGroup":"apps.foundationdb.org","controllerKind":"FoundationDBCluster","FoundationDBCluster":{"name":"xyz-fdb-abcd","namespace":"xyz-fdb-abcd"},"namespace":"xyz-fdb-abcd","name":"xyz-fdb-abcd","reconcileID":"621fa184-2655-44c4-a706-312d4e0fddeb"}
{"level":"info","ts":"2026-04-10T05:34:04Z","msg":"unknown field \"spec.processes.storage.volumeClaimTemplate.metadata.creationTimestamp\"","controller":"foundationdbcluster","controllerGroup":"apps.foundationdb.org","controllerKind":"FoundationDBCluster","FoundationDBCluster":{"name":"xyz-fdb-abcd","namespace":"xyz-fdb-abcd"},"namespace":"xyz-fdb-abcd","name":"xyz-fdb-abcd","reconcileID":"621fa184-2655-44c4-a706-312d4e0fddeb"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","duration_seconds":0.017100822}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Delaying requeue for sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","reconciler":"controllers.updateStatus","message":"cluster is not fully reconciled","delayedRequeueDuration":"10s","error":null}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Cluster was not fully reconciled by reconciliation process","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","status":{"reconciled":1,"needsCoordinatorChange":1,"hasUnhealthyProcess":1},"CurrentGeneration":1,"OriginalGeneration":1,"DelayedRequeue":"10s"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Reconciliation run finished","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"5a007819-4815-4f68-b5b7-f619788013e9","duration_seconds":1.579783953,"cacheStatus":true}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Attempting to run sub-reconciler","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"ba36628c-a354-4bcb-934d-a5460d59755a","reconciler":"controllers.addPods"}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Subreconciler finished run","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"ba36628c-a354-4bcb-934d-a5460d59755a","reconciler":"controllers.addPods","duration_seconds":0.00024448}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller","msg":"Fetch machine-readable status for reconciliation loop","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"ba36628c-a354-4bcb-934d-a5460d59755a","cacheStatus":true}
{"level":"info","ts":"2026-04-10T05:34:04Z","logger":"controller.fdbclient","msg":"Fetch values from FDB","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"ba36628c-a354-4bcb-934d-a5460d59755a","key":"\ufffd\ufffd/status/json"}
{"level":"info","ts":"2026-04-10T05:34:05Z","logger":"controller.fdbclient","msg":"Done fetching values from FDB","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"ba36628c-a354-4bcb-934d-a5460d59755a","key":"\ufffd\ufffd/status/json"}
{"level":"info","ts":"2026-04-10T05:34:05Z","logger":"controller.fdbclient","msg":"database is unavailable","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"ba36628c-a354-4bcb-934d-a5460d59755a","status":{"client":{"coordinators":{"coordinators":[{"address":"xyz-fdb-abcd-log-48370.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local:4501","reachable":true},{"address":"xyz-fdb-abcd-log-55193.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local:4501"},{"address":"xyz-fdb-abcd-log-60478.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local:4501","reachable":true}],"quorum_reachable":true},"database_status":{}},"cluster":{"configuration":{"redundancy_mode":"double","storage_engine":"ssd-2","usable_regions":1,"logs":3,"proxies":3,"commit_proxies":2,"grv_proxies":1,"resolvers":1,"log_routers":-1,"remote_logs":-1,"log_spill":2,"storage_migration_type":"disabled","perpetual_storage_wiggle":0,"perpetual_storage_wiggle_locality":"0","perpetual_storage_wiggle_engine":"none"},"processes":{"345b3f029e79da96931a5aecc83fc3e5":{"address":"10.0.27.113:4501","class_type":"storage","command_line":"/usr/bin/fdbserver --cluster_file=/var/fdb/data/fdb.cluster --seed_cluster_file=/var/dynamic-conf/fdb.cluster --public_address=[10.0.27.113]:4501 --class=storage --logdir=/var/log/fdb-trace-logs --loggroup=xyz-fdb-abcd --datadir=/var/fdb/data/1 --locality_process_id=storage-10819-1 --locality_instance_id=storage-10819 --locality_machineid=xyz-fdb-abcd-storage-10819 --locality_zoneid=xyz-fdb-abcd-storage-10819 --listen_address=[10.0.27.113]:4501 --locality_dns_name=xyz-fdb-abcd-storage-10819.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","locality":{"dns_name":"xyz-fdb-abcd-storage-10819.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","instance_id":"storage-10819","machineid":"xyz-fdb-abcd-storage-10819","process_id":"storage-10819-1","processid":"345b3f029e79da96931a5aecc83fc3e5","zoneid":"xyz-fdb-abcd-storage-10819"},"version":"7.3.69","uptime_seconds":700.004,"run_loop_busy":0.0391424,"roles":[{"role":"log","id":"36fc1d16f8af228d","data_lag":{},"kvstore_used_bytes":104861752,"kvstore_total_bytes":20940668928,"kvstore_free_bytes":20723617792,"kvstore_available_bytes":20723617792,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}}]},"5177543970da0444bc5f4a6f4e0a6a97":{"address":"10.0.27.143:4501","class_type":"log","command_line":"/usr/bin/fdbserver --cluster_file=/var/fdb/data/fdb.cluster --seed_cluster_file=/var/dynamic-conf/fdb.cluster --public_address=[10.0.27.143]:4501 --class=log --logdir=/var/log/fdb-trace-logs --loggroup=xyz-fdb-abcd --datadir=/var/fdb/data/1 --locality_process_id=log-48370-1 --locality_instance_id=log-48370 --locality_machineid=xyz-fdb-abcd-log-48370 --locality_zoneid=xyz-fdb-abcd-log-48370 --listen_address=[10.0.27.143]:4501 --locality_dns_name=xyz-fdb-abcd-log-48370.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","locality":{"dns_name":"xyz-fdb-abcd-log-48370.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","instance_id":"log-48370","machineid":"xyz-fdb-abcd-log-48370","process_id":"log-48370-1","processid":"5177543970da0444bc5f4a6f4e0a6a97","zoneid":"xyz-fdb-abcd-log-48370"},"version":"7.3.69","uptime_seconds":80.0002,"run_loop_busy":0.014618599999999999,"roles":[{"role":"data_distributor","id":"724c965074c79300","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}},{"role":"ratekeeper","id":"3d37276fb82b13c3","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}},{"role":"log","id":"1d35c76aeaae9209","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}},{"role":"coordinator","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}},{"role":"log","id":"7f35d6b16861f03b","data_lag":{},"kvstore_used_bytes":104882352,"kvstore_total_bytes":3077349376,"kvstore_free_bytes":2812010496,"kvstore_available_bytes":2812010496,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}}]},"9a1c56e284882ec31d8b9642e891f10b":{"address":"10.0.27.167:4501","class_type":"storage","command_line":"/usr/bin/fdbserver --cluster_file=/var/fdb/data/fdb.cluster --seed_cluster_file=/var/dynamic-conf/fdb.cluster --public_address=[10.0.27.167]:4501 --class=storage --logdir=/var/log/fdb-trace-logs --loggroup=xyz-fdb-abcd --datadir=/var/fdb/data/1 --locality_process_id=storage-16106-1 --locality_instance_id=storage-16106 --locality_machineid=xyz-fdb-abcd-storage-16106 --locality_zoneid=xyz-fdb-abcd-storage-16106 --listen_address=[10.0.27.167]:4501 --locality_dns_name=xyz-fdb-abcd-storage-16106.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","locality":{"dns_name":"xyz-fdb-abcd-storage-16106.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","instance_id":"storage-16106","machineid":"xyz-fdb-abcd-storage-16106","process_id":"storage-16106-1","processid":"9a1c56e284882ec31d8b9642e891f10b","zoneid":"xyz-fdb-abcd-storage-16106"},"version":"7.3.69","uptime_seconds":340.007,"run_loop_busy":0.0313403,"roles":[{"role":"log","id":"2eb91fd600d2affd","data_lag":{},"kvstore_used_bytes":104861752,"kvstore_total_bytes":20940668928,"kvstore_free_bytes":20723617792,"kvstore_available_bytes":20723617792,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}}]},"c41ff8d4f58a6d7a1295866c42ba4af6":{"address":"10.0.27.13:4501","class_type":"storage","command_line":"/usr/bin/fdbserver --cluster_file=/var/fdb/data/fdb.cluster --seed_cluster_file=/var/dynamic-conf/fdb.cluster --public_address=[10.0.27.13]:4501 --class=storage --logdir=/var/log/fdb-trace-logs --loggroup=xyz-fdb-abcd --datadir=/var/fdb/data/1 --locality_process_id=storage-18963-1 --locality_instance_id=storage-18963 --locality_machineid=xyz-fdb-abcd-storage-18963 --locality_zoneid=xyz-fdb-abcd-storage-18963 --listen_address=[10.0.27.13]:4501 --locality_dns_name=xyz-fdb-abcd-storage-18963.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","locality":{"dns_name":"xyz-fdb-abcd-storage-18963.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","instance_id":"storage-18963","machineid":"xyz-fdb-abcd-storage-18963","process_id":"storage-18963-1","processid":"c41ff8d4f58a6d7a1295866c42ba4af6","zoneid":"xyz-fdb-abcd-storage-18963"},"version":"7.3.69","uptime_seconds":340.001,"run_loop_busy":0.0057557,"roles":[{"role":"consistency_scan","id":"55da43bacd8c0733","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}}]},"e140142d674b9df941bd73f1afe76727":{"address":"10.0.27.119:4501","class_type":"stateless","command_line":"/usr/bin/fdbserver --cluster_file=/var/fdb/data/fdb.cluster --seed_cluster_file=/var/dynamic-conf/fdb.cluster --public_address=[10.0.27.119]:4501 --class=stateless --logdir=/var/log/fdb-trace-logs --loggroup=xyz-fdb-abcd --datadir=/var/fdb/data/1 --locality_process_id=stateless-40726-1 --locality_instance_id=stateless-40726 --locality_machineid=xyz-fdb-abcd-stateless-40726 --locality_zoneid=xyz-fdb-abcd-stateless-40726 --listen_address=[10.0.27.119]:4501 --locality_dns_name=xyz-fdb-abcd-stateless-40726.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local","version":"7.3.69","roles":[{"role":"master","id":"74013759391c5855","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}},{"role":"cluster_controller","id":"25d553c9b89bb9e7","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}},{"role":"commit_proxy","id":"bed406b911a58dd3","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}},{"role":"grv_proxy","id":"bd3b22dfd8643e01","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}},{"role":"resolver","id":"ddb04176fb27353c","data_lag":{},"kvstore_used_bytes":null,"kvstore_total_bytes":null,"kvstore_free_bytes":null,"kvstore_available_bytes":null,"read_latency_statistics":{"count":null,"median":null,"p99":null},"commit_latency_statistics":{"count":null,"median":null,"p99":null},"grv_latency_statistics":{"batch":{"count":null,"median":null,"p99":null},"default":{"count":null,"median":null,"p99":null}}}]}},"data":{"total_kv_size_bytes":15271718,"moving_data":{},"state":{"healthy":true,"name":"healthy","min_replicas_remaining":2},"team_trackers":[{"primary":true,"state":{"healthy":true,"name":"healthy","min_replicas_remaining":2},"unhealthy_servers":0}],"total_disk_used_bytes":329105408},"full_replication":true,"generation":178,"clients":{},"layers":{"_valid":true,"backup":{}},"logs":[{"current":true,"log_fault_tolerance":1,"log_replication_factor":2},{"log_replication_factor":2}],"qos":{"limiting_durability_lag_storage_server":{"seconds":5.07766,"versions":5077658},"worst_data_lag_storage_server":{},"worst_durability_lag_storage_server":{"seconds":5.08494,"versions":5084936},"worst_queue_bytes_storage_server":9991865},"fault_tolerance":{},"recovery_state":{},"connection_string":"xyz_fdb_abcd:qfPNwpLRByg4F4gBo5k6G3CC6DA0dwZP@xyz-fdb-abcd-log-48370.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local:4501,xyz-fdb-abcd-log-55193.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local:4501,xyz-fdb-abcd-log-60478.xyz-fdb-abcd.xyz-fdb-abcd.svc.cluster.local:4501","messages":[{"name":"status_incomplete","description":"Unable to retrieve all status information."}],"bounce_impact":{"can_clean_bounce":false},"database_available":true,"active_primary_dc":"","database_lock_state":{"locked":false}}}}
{"level":"info","ts":"2026-04-10T05:34:05Z","logger":"controller","msg":"could not fetch machine-readable status and therefore didn't cache it","namespace":"xyz-fdb-abcd","cluster":"xyz-fdb-abcd","traceID":"ba36628c-a354-4bcb-934d-a5460d59755a","error":"fdb timeout: database is unavailable"}
