change metric names from ccp_container to ccp_nodemx, update dashboar…

…ds with new names, remove invalid panel links
CrunchyData · Aug 7, 2020 · 4c13eb5 · 4c13eb5
1 parent ab8c2c3
commit 4c13eb5
Show file tree

Hide file tree

Showing 8 changed files with 200 additions and 111 deletions.
diff --git a/exporter/postgres/queries_containers.yml b/exporter/postgres/queries_containers.yml
@@ -3,8 +3,8 @@
 # Begin File: pod_metrics.yml
 #
 ###
-ccp_container_network:
-  query: "SELECT interface,tx_bytes,tx_packets, rx_bytes,rx_packets from public.proc_network_stats()"
+ccp_nodemx_network:
+  query: "SELECT interface,tx_bytes,tx_packets, rx_bytes,rx_packets from monitor.proc_network_stats()"
   metrics:
     - interface:
         usage: "LABEL"
@@ -21,16 +21,16 @@ ccp_container_network:
         usage: "GAUGE"
         description: "Number of packets received"
 
-ccp_container_process:
-  query: "SELECT public.cgroup_process_count() as count"
+ccp_nodemx_process:
+  query: "SELECT monitor.cgroup_process_count() as count"
   metrics:
     - count:
         usage: "GAUGE"
         description: "Total number of processes on database container"
 
 
-ccp_container_mem:
-  query: "SELECT public.kdapi_scalar_bigint('mem_request') as request, public.kdapi_scalar_bigint('mem_limit') as limit, (select val from cgroup_setof_kv('memory.stat') where key='cache') as cache, (select val from cgroup_setof_kv('memory.stat') where key='rss') as rss, (select val from cgroup_setof_kv('memory.stat') where key='shmem') as shmem, (select val from cgroup_setof_kv('memory.stat') where key='mapped_file') as mapped_file, (select val from cgroup_setof_kv('memory.stat') where key='dirty') as dirty, (select val from cgroup_setof_kv('memory.stat') where key='active_anon') as active_anon, (select val from cgroup_setof_kv('memory.stat') where key='inactive_anon') as inactive_anon, (select val from cgroup_setof_kv('memory.stat') where key='active_file') as active_file, (select val from cgroup_setof_kv('memory.stat') where key='inactive_file') as inactive_file"
+ccp_nodemx_mem:
+  query: "SELECT monitor.kdapi_scalar_bigint('mem_request') as request, monitor.kdapi_scalar_bigint('mem_limit') as limit, (select val from monitor.cgroup_setof_kv('memory.stat') where key='cache') as cache, (select val from monitor.cgroup_setof_kv('memory.stat') where key='rss') as rss, (select val from monitor.cgroup_setof_kv('memory.stat') where key='shmem') as shmem, (select val from monitor.cgroup_setof_kv('memory.stat') where key='mapped_file') as mapped_file, (select val from monitor.cgroup_setof_kv('memory.stat') where key='dirty') as dirty, (select val from monitor.cgroup_setof_kv('memory.stat') where key='active_anon') as active_anon, (select val from monitor.cgroup_setof_kv('memory.stat') where key='inactive_anon') as inactive_anon, (select val from monitor.cgroup_setof_kv('memory.stat') where key='active_file') as active_file, (select val from monitor.cgroup_setof_kv('memory.stat') where key='inactive_file') as inactive_file"
   metrics:
     - request:
         usage: "GAUGE"
@@ -70,8 +70,8 @@ ccp_container_mem:
         description: "Total bytes of file-backed memory on inactive LRU list"
 
 
-ccp_container_cpu:
-  query: "SELECT public.kdapi_scalar_bigint('cpu_request') as request, public.kdapi_scalar_bigint('cpu_limit') as limit"
+ccp_nodemx_cpu:
+  query: "SELECT monitor.kdapi_scalar_bigint('cpu_request') as request, monitor.kdapi_scalar_bigint('cpu_limit') as limit"
   metrics:
     - request:
         usage: "GAUGE"
@@ -80,8 +80,8 @@ ccp_container_cpu:
         usage: "GAUGE"
         description: "CPU limit value in milli cores"
 
-ccp_container_cpucfs:
-  query: "SELECT  cgroup_scalar_bigint('cpu.cfs_period_us') as period_us, cgroup_scalar_bigint('cpu.cfs_quota_us') as quota_us"
+ccp_nodemx_cpucfs:
+  query: "SELECT  monitor.cgroup_scalar_bigint('cpu.cfs_period_us') as period_us, monitor.cgroup_scalar_bigint('cpu.cfs_quota_us') as quota_us"
   metrics:
     - period_us:
         usage: "GAUGE"
@@ -90,15 +90,15 @@ ccp_container_cpucfs:
         usage: "GAUGE"
         description: "the length of a period (in microseconds)"
 
-ccp_container_cpuacct:
-  query: "SELECT cgroup_scalar_bigint('cpuacct.usage') as usage"
+ccp_nodemx_cpuacct:
+  query: "SELECT monitor.cgroup_scalar_bigint('cpuacct.usage') as usage"
   metrics:
     - usage:
         usage: "GAUGE"
         description: "CPU usage in nanoseconds"
 
-ccp_container_cpustat:
-  query: "select (SELECT val as nr_periods FROM cgroup_setof_kv('cpu.stat') where key='nr_periods'), (SELECT val as nr_throttled FROM cgroup_setof_kv('cpu.stat') where key='nr_throttled'), (SELECT val as throttled_time FROM cgroup_setof_kv('cpu.stat') where key='throttled_time')"
+ccp_nodemx_cpustat:
+  query: "select (SELECT val as nr_periods FROM monitor.cgroup_setof_kv('cpu.stat') where key='nr_periods'), (SELECT val as nr_throttled FROM monitor.cgroup_setof_kv('cpu.stat') where key='nr_throttled'), (SELECT val as throttled_time FROM monitor.cgroup_setof_kv('cpu.stat') where key='throttled_time')"
   metrics:
     - nr_threads:
         usage: "GAUGE"
@@ -108,14 +108,14 @@ ccp_container_cpustat:
         description: "number of runnable periods in which the application used its entire quota and was throttled"
     - throttled_time:
         usage: "GAUGE"
-        description: "sum total amount of time individual threads within the cgroup were throttled"
+        description: "sum total amount of time individual threads within the monitor.cgroup were throttled"
 
 
-ccp_container_data_disk:
+ccp_nodemx_data_disk:
   query: "SELECT mount_point, fs_type,reads_completed_successfully as reads, sectors_read, writes_completed as writes,sectors_written, total_bytes,available_bytes,total_file_nodes,free_file_nodes
-          FROM proc_mountinfo() m
-          JOIN proc_diskstats() d USING (major_number, minor_number)
-          JOIN fsinfo(m.mount_point) f USING (major_number, minor_number) 
+          FROM monitor.proc_mountinfo() m
+          JOIN monitor.proc_diskstats() d USING (major_number, minor_number)
+          JOIN monitor.fsinfo(m.mount_point) f USING (major_number, minor_number) 
           WHERE m.mount_point like '/pg%' or m.mount_point like '/tablespace%'"
   metrics:
     - mount_point:

diff --git a/grafana/containers/crud_details.json b/grafana/containers/crud_details.json
@@ -2,7 +2,6 @@
   "annotations": {
     "list": [
       {
-        "$$hashKey": "object:111",
         "builtIn": 1,
         "datasource": "-- Grafana --",
         "enable": true,
@@ -17,7 +16,7 @@
   "gnetId": null,
   "graphTooltip": 0,
   "id": 3,
-  "iteration": 1596723524049,
+  "iteration": 1596814000168,
   "links": [
     {
       "icon": "external link",
@@ -147,9 +146,8 @@
       {
         "allValue": null,
         "current": {
-          "selected": true,
-          "text": "dcsi:dcsi",
-          "value": "dcsi:dcsi"
+          "text": "postgres-operations:democluster1",
+          "value": "postgres-operations:democluster1"
         },
         "datasource": "PROMETHEUS",
         "definition": "",
@@ -180,15 +178,15 @@
           ]
         },
         "datasource": "PROMETHEUS",
-        "definition": "",
+        "definition": "label_values({pg_cluster=\"[[cluster]]\"},pod)",
         "hide": 0,
         "includeAll": true,
         "index": -1,
         "label": "pod",
         "multi": true,
         "name": "pod",
         "options": [],
-        "query": "label_values({pg_cluster=\"[[cluster]]\"},instance)",
+        "query": "label_values({pg_cluster=\"[[cluster]]\"},pod)",
         "refresh": 1,
         "regex": "",
         "skipUrlSync": false,
@@ -317,5 +315,5 @@
   "variables": {
     "list": []
   },
-  "version": 1
-}
+  "version": 2
+}
diff --git a/grafana/containers/pgbackrest.json b/grafana/containers/pgbackrest.json
@@ -2,7 +2,6 @@
   "annotations": {
     "list": [
       {
-        "$$hashKey": "object:183",
         "builtIn": 1,
         "datasource": "-- Grafana --",
         "enable": true,
@@ -17,7 +16,7 @@
   "gnetId": null,
   "graphTooltip": 0,
   "id": 4,
-  "iteration": 1596723551280,
+  "iteration": 1596814171540,
   "links": [
     {
       "asDropdown": false,
@@ -248,8 +247,8 @@
       {
         "allValue": null,
         "current": {
-          "text": "dcsi:dcsi",
-          "value": "dcsi:dcsi"
+          "text": "postgres-operations:democluster1",
+          "value": "postgres-operations:democluster1"
         },
         "datasource": "PROMETHEUS",
         "definition": "label_values(pg_cluster)",
@@ -274,7 +273,7 @@
     ]
   },
   "time": {
-    "from": "now-3h",
+    "from": "now-5m",
     "to": "now"
   },
   "timepicker": {
@@ -304,4 +303,4 @@
     "list": []
   },
   "version": 1
-}
+}