From 29c342e743468b1f6b07db4839d7cd652922e8dd Mon Sep 17 00:00:00 2001 From: GitHub Actions Date: Fri, 11 Dec 2020 15:19:50 +0000 Subject: [PATCH] Generated updated K8s templates --- .../generated/grafana/overview.dashboard.yaml | 413 +++++++++--------- 1 file changed, 207 insertions(+), 206 deletions(-) diff --git a/dashboards/k8s-build/generated/grafana/overview.dashboard.yaml b/dashboards/k8s-build/generated/grafana/overview.dashboard.yaml index 04bcf02..a74e58c 100644 --- a/dashboards/k8s-build/generated/grafana/overview.dashboard.yaml +++ b/dashboards/k8s-build/generated/grafana/overview.dashboard.yaml @@ -50,98 +50,98 @@ spec: \ \"targets\": [\n {\n \"expr\":\ \ \"sum by (cluster, request_type) (rate(mcac_client_request_latency_total{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"{{request_type}}\"\ - ,\n \"refId\": \"A\"\n }\n \ - \ ],\n \"thresholds\": [ ],\n \"timeFrom\": null,\n\ - \ \"timeShift\": null,\n \"title\": \"Request Throughputs\"\ - ,\n \"tooltip\": {\n \"shared\": false,\n \ - \ \"sort\": 0,\n \"value_type\": \"individual\"\n\ - \ },\n \"transparent\": true,\n \"type\"\ - : \"graph\",\n \"xaxis\": {\n \"buckets\": null,\n\ - \ \"mode\": \"time\",\n \"name\": null,\n \ - \ \"show\": true,\n \"values\": [ ]\n \ - \ },\n \"yaxes\": [\n {\n \ - \ \"format\": \"rps\",\n \"label\": null,\n \ - \ \"logBase\": 1,\n \"max\": null,\n \ - \ \"min\": 0,\n \"show\": true\n \ - \ },\n {\n \"format\": \"rps\",\n \ - \ \"label\": null,\n \"logBase\": 1,\n \ - \ \"max\": null,\n \"min\": 0,\n \ - \ \"show\": true\n }\n ]\n \ - \ },\n {\n \"aliasColors\": { },\n \"\ - bars\": false,\n \"dashLength\": 10,\n \"dashes\"\ - : false,\n \"datasource\": \"$PROMETHEUS_DS\",\n \"\ - description\": \"Total Timeouts, Failures, Unavailable Rates for each cluster\"\ - ,\n \"fill\": 0,\n \"fillGradient\": 0,\n \ - \ \"gridPos\": { },\n \"id\": 6,\n \"legend\"\ - : {\n \"alignAsTable\": true,\n \"avg\": false,\n\ - \ \"current\": true,\n \"max\": false,\n \ - \ \"min\": false,\n \"rightSide\": false,\n \ - \ \"show\": true,\n \"sideWidth\": null,\n \ - \ \"sort\": \"current\",\n \"sortDesc\": true,\n\ - \ \"total\": false,\n \"values\": true\n \ - \ },\n \"lines\": true,\n \"linewidth\"\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + {{request_type}}\",\n \"refId\": \"A\"\n \ + \ }\n ],\n \"thresholds\": [ ],\n \"\ + timeFrom\": null,\n \"timeShift\": null,\n \"title\"\ + : \"Request Throughputs\",\n \"tooltip\": {\n \"\ + shared\": false,\n \"sort\": 0,\n \"value_type\"\ + : \"individual\"\n },\n \"transparent\": true,\n \ + \ \"type\": \"graph\",\n \"xaxis\": {\n \ + \ \"buckets\": null,\n \"mode\": \"time\",\n \ + \ \"name\": null,\n \"show\": true,\n \ + \ \"values\": [ ]\n },\n \"yaxes\": [\n \ + \ {\n \"format\": \"rps\",\n \"\ + label\": null,\n \"logBase\": 1,\n \"\ + max\": null,\n \"min\": 0,\n \"show\"\ + : true\n },\n {\n \"format\"\ + : \"rps\",\n \"label\": null,\n \"logBase\"\ + : 1,\n \"max\": null,\n \"min\": 0,\n\ + \ \"show\": true\n }\n ]\n\ + \ },\n {\n \"aliasColors\": { },\n \ + \ \"bars\": false,\n \"dashLength\": 10,\n \ + \ \"dashes\": false,\n \"datasource\": \"$PROMETHEUS_DS\",\n \ + \ \"description\": \"Total Timeouts, Failures, Unavailable Rates for\ + \ each cluster\",\n \"fill\": 0,\n \"fillGradient\"\ + : 0,\n \"gridPos\": { },\n \"id\": 6,\n \ + \ \"legend\": {\n \"alignAsTable\": true,\n \ + \ \"avg\": false,\n \"current\": true,\n \ + \ \"max\": false,\n \"min\": false,\n \"rightSide\"\ + : false,\n \"show\": true,\n \"sideWidth\":\ + \ null,\n \"sort\": \"current\",\n \"sortDesc\"\ + : true,\n \"total\": false,\n \"values\": true\n\ + \ },\n \"lines\": true,\n \"linewidth\"\ : 1,\n \"links\": [ ],\n \"nullPointMode\": \"null\"\ ,\n \"percentage\": false,\n \"pointradius\": 5,\n\ \ \"points\": false,\n \"renderer\": \"flot\",\n \ \ \"repeat\": null,\n \"seriesOverrides\": [ ],\n \ \ \"spaceLength\": 10,\n \"stack\": false,\n \ \ \"steppedLine\": false,\n \"targets\": [\n \ - \ {\n \"expr\": \"sum by (cluster, request_type) (irate(mcac_client_request_failures_total{cluster=~\\\ + \ {\n \"expr\": \"sum by (cluster, request_type) (rate(mcac_client_request_failures_total{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"{{request_type}}\ - \ failures\",\n \"refId\": \"A\"\n },\n \ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + {{request_type}} failures\",\n \"refId\": \"A\"\n \ + \ },\n {\n \"expr\": \"sum by (cluster,\ + \ request_type) (rate(mcac_client_request_timeouts_total{cluster=~\\\"$cluster\\\ + \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s]))\"\ + ,\n \"format\": \"time_series\",\n \"\ + intervalFactor\": 2,\n \"legendFormat\": \"{{request_type}}\ + \ timeouts\",\n \"refId\": \"B\"\n },\n \ \ {\n \"expr\": \"sum by (cluster, request_type)\ - \ (irate(mcac_client_request_timeouts_total{cluster=~\\\"$cluster\\\", dc=~\\\"\ - $dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m]))\",\n \ - \ \"format\": \"time_series\",\n \"intervalFactor\"\ - : 2,\n \"legendFormat\": \"{{request_type}} timeouts\",\n\ - \ \"refId\": \"B\"\n },\n \ - \ {\n \"expr\": \"sum by (cluster, request_type) (irate(mcac_client_request_unavailables_total{cluster=~\\\ + \ (rate(mcac_client_request_unavailables_total{cluster=~\\\"$cluster\\\", dc=~\\\ + \"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s]))\",\n \ + \ \"format\": \"time_series\",\n \"intervalFactor\"\ + : 2,\n \"legendFormat\": \"{{request_type}} unavailable errors\"\ + ,\n \"refId\": \"C\"\n },\n \ + \ {\n \"expr\": \"sum by (cluster, request_type) (rate(mcac_client_request_unfinished_commit_total{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"{{request_type}}\ - \ unavailable errors\",\n \"refId\": \"C\"\n \ - \ },\n {\n \"expr\": \"sum by (cluster,\ - \ request_type) (irate(mcac_client_request_unfinished_commit_total{cluster=~\\\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + {{request_type}} unfinished commit errors\",\n \"refId\":\ + \ \"D\"\n },\n {\n \"expr\"\ + : \"sum by (cluster, request_type) (rate(mcac_client_request_condition_not_met_total{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"{{request_type}}\ - \ unfinished commit errors\",\n \"refId\": \"D\"\n \ - \ },\n {\n \"expr\": \"sum by (cluster,\ - \ request_type) (irate(mcac_client_request_condition_not_met_total{cluster=~\\\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + {{request_type}} condition not met errors\",\n \"refId\":\ + \ \"E\"\n },\n {\n \"expr\"\ + : \"sum by (cluster, request_type) (rate(mcac_client_request_contention_histogram_total{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"{{request_type}}\ - \ condition not met errors\",\n \"refId\": \"E\"\n \ - \ },\n {\n \"expr\": \"sum by (cluster,\ - \ request_type) (irate(mcac_client_request_contention_histogram_total{cluster=~\\\ - \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"{{request_type}}\ - \ contention histogram errors\",\n \"refId\": \"F\"\n \ - \ }\n ],\n \"thresholds\": [ ],\n \ - \ \"timeFrom\": null,\n \"timeShift\": null,\n \ - \ \"title\": \"Error throughputs\",\n \"tooltip\": {\n \ - \ \"shared\": false,\n \"sort\": 0,\n \ - \ \"value_type\": \"individual\"\n },\n \ - \ \"transparent\": true,\n \"type\": \"graph\",\n \ - \ \"xaxis\": {\n \"buckets\": null,\n \"mode\"\ - : \"time\",\n \"name\": null,\n \"show\": true,\n\ - \ \"values\": [ ]\n },\n \"yaxes\"\ - : [\n {\n \"format\": \"rps\",\n \ - \ \"label\": null,\n \"logBase\": 1,\n \ - \ \"max\": null,\n \"min\": 0,\n \ - \ \"show\": true\n },\n {\n \ - \ \"format\": \"rps\",\n \"label\": null,\n \ - \ \"logBase\": 1,\n \"max\": null,\n \ - \ \"min\": 0,\n \"show\": true\n \ - \ }\n ]\n },\n {\n \ - \ \"cacheTimeout\": null,\n \"colorBackground\": false,\n \ - \ \"colorValue\": false,\n \"colors\": [\n \ - \ \"#DEB6F2\",\n \"#CA95E5\",\n \"#8F3BB8\"\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + {{request_type}} contention histogram errors\",\n \"refId\"\ + : \"F\"\n }\n ],\n \"thresholds\"\ + : [ ],\n \"timeFrom\": null,\n \"timeShift\": null,\n\ + \ \"title\": \"Error throughputs\",\n \"tooltip\"\ + : {\n \"shared\": false,\n \"sort\": 0,\n \ + \ \"value_type\": \"individual\"\n },\n \ + \ \"transparent\": true,\n \"type\": \"graph\",\n \ + \ \"xaxis\": {\n \"buckets\": null,\n \"\ + mode\": \"time\",\n \"name\": null,\n \"show\"\ + : true,\n \"values\": [ ]\n },\n \ + \ \"yaxes\": [\n {\n \"format\": \"rps\"\ + ,\n \"label\": null,\n \"logBase\": 1,\n\ + \ \"max\": null,\n \"min\": 0,\n \ + \ \"show\": true\n },\n {\n \ + \ \"format\": \"rps\",\n \"label\": null,\n\ + \ \"logBase\": 1,\n \"max\": null,\n \ + \ \"min\": 0,\n \"show\": true\n \ + \ }\n ]\n },\n {\n \ + \ \"cacheTimeout\": null,\n \"colorBackground\": false,\n \ + \ \"colorValue\": false,\n \"colors\": [\n \ + \ \"#DEB6F2\",\n \"#CA95E5\",\n \"#8F3BB8\"\ \n ],\n \"datasource\": \"$PROMETHEUS_DS\",\n \ \ \"decimals\": 2,\n \"description\": \"Part of reads\ \ in the total of standard requests (Reads+Writes). CAS, Views, ... operations\ @@ -166,16 +166,17 @@ spec: \ \"full\": false,\n \"lineColor\": \"#FFB357\",\n \ \ \"show\": false\n },\n \"tableColumn\"\ : \"\",\n \"targets\": [\n {\n \ - \ \"expr\": \"sum by (cluster, request_type) (irate(mcac_client_request_latency_total{cluster=~\\\ + \ \"expr\": \"sum by (cluster, request_type) (rate(mcac_client_request_latency_total{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - , request_type=\\\"read\\\"}[1m])) / ignoring (request_type) (sum by (cluster,\ - \ request_type) (irate(mcac_client_request_latency_total{cluster=~\\\"$cluster\\\ + , request_type=\\\"read\\\"}[1m:30s])) / ignoring (request_type) (sum by (cluster,\ + \ request_type) (rate(mcac_client_request_latency_total{cluster=~\\\"$cluster\\\ \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\", request_type=\\\ - \"read\\\"}[1m])) + ignoring (request_type) sum by (cluster, request_type) (irate(mcac_client_request_latency_total{cluster=~\\\ - \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - , request_type=\\\"write\\\"}[1m])))\",\n \"format\": \"time_series\"\ - ,\n \"intervalFactor\": 2,\n \"legendFormat\"\ - : \"\",\n \"refId\": \"A\"\n }\n \ + \"read\\\"}[1m:30s])) + ignoring (request_type) sum by (cluster, request_type)\ + \ (rate(mcac_client_request_latency_total{cluster=~\\\"$cluster\\\", dc=~\\\"\ + $dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\", request_type=\\\"write\\\ + \"}[1m:30s])))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\":\ + \ \"\",\n \"refId\": \"A\"\n }\n \ \ ],\n \"thresholds\": \"0.25,0.5,0.75\",\n \ \ \"timeFrom\": \"\",\n \"title\": \"Read / Write Distribution\"\ ,\n \"transparent\": true,\n \"type\": \"singlestat\"\ @@ -206,19 +207,19 @@ spec: \ }\n ],\n \"spaceLength\": 10,\n\ \ \"stack\": false,\n \"steppedLine\": false,\n \ \ \"targets\": [\n {\n \"expr\"\ - : \"histogram_quantile(0.98, sum(irate(mcac_client_request_latency_bucket{cluster=~\\\ + : \"histogram_quantile(0.98, sum(rate(mcac_client_request_latency_bucket{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ , request_type=\\\"read\\\"}[5m])) by (le, cluster))\",\n \ \ \"format\": \"time_series\",\n \"intervalFactor\": 2,\n\ \ \"legendFormat\": \"p98\",\n \"refId\"\ : \"A\"\n },\n {\n \"expr\"\ - : \"histogram_quantile(0.99, sum(irate(mcac_client_request_latency_bucket{cluster=~\\\ + : \"histogram_quantile(0.99, sum(rate(mcac_client_request_latency_bucket{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ , request_type=\\\"read\\\"}[5m])) by (le, cluster))\",\n \ \ \"format\": \"time_series\",\n \"intervalFactor\": 2,\n\ \ \"legendFormat\": \"p99\",\n \"refId\"\ : \"B\"\n },\n {\n \"expr\"\ - : \"histogram_quantile(0.999, sum(irate(mcac_client_request_latency_bucket{cluster=~\\\ + : \"histogram_quantile(0.999, sum(rate(mcac_client_request_latency_bucket{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ , request_type=\\\"read\\\"}[5m])) by (le, cluster))\",\n \ \ \"format\": \"time_series\",\n \"intervalFactor\": 2,\n\ @@ -263,19 +264,19 @@ spec: \ }\n ],\n \"spaceLength\": 10,\n\ \ \"stack\": false,\n \"steppedLine\": false,\n \ \ \"targets\": [\n {\n \"expr\"\ - : \"histogram_quantile(0.98, sum(irate(mcac_client_request_latency_bucket{cluster=~\\\ + : \"histogram_quantile(0.98, sum(rate(mcac_client_request_latency_bucket{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ , request_type=\\\"write\\\"}[5m])) by (le, cluster))\",\n \ \ \"format\": \"time_series\",\n \"intervalFactor\": 2,\n\ \ \"legendFormat\": \"p98\",\n \"refId\"\ : \"A\"\n },\n {\n \"expr\"\ - : \"histogram_quantile(0.99, sum(irate(mcac_client_request_latency_bucket{cluster=~\\\ + : \"histogram_quantile(0.99, sum(rate(mcac_client_request_latency_bucket{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ , request_type=\\\"write\\\"}[5m])) by (le, cluster))\",\n \ \ \"format\": \"time_series\",\n \"intervalFactor\": 2,\n\ \ \"legendFormat\": \"p99\",\n \"refId\"\ : \"B\"\n },\n {\n \"expr\"\ - : \"histogram_quantile(0.999, sum(irate(mcac_client_request_latency_bucket{cluster=~\\\ + : \"histogram_quantile(0.999, sum(rate(mcac_client_request_latency_bucket{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ , request_type=\\\"write\\\"}[5m])) by (le, cluster))\",\n \ \ \"format\": \"time_series\",\n \"intervalFactor\": 2,\n\ @@ -318,7 +319,7 @@ spec: \ \"steppedLine\": false,\n \"targets\": [\n \ \ {\n \"expr\": \"histogram_quantile(0.99, sum(rate(mcac_client_request_latency_bucket{cluster=~\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - , request_type!~\\\"write|read|.*-.*\\\"}[1m])) by (le, request_type, cluster))\"\ + , request_type!~\\\"write|read|.*-.*\\\"}[1m:30s])) by (le, request_type, cluster))\"\ ,\n \"format\": \"time_series\",\n \"\ intervalFactor\": 2,\n \"legendFormat\": \"p99 {{request_type}}\"\ ,\n \"refId\": \"A\"\n }\n \ @@ -770,20 +771,20 @@ spec: \ \"repeat\": null,\n \"seriesOverrides\": [ ],\n \ \ \"spaceLength\": 10,\n \"stack\": false,\n \ \ \"steppedLine\": false,\n \"targets\": [\n \ - \ {\n \"expr\": \"sum by (cluster, pool_name) (irate(mcac_thread_pools_total_blocked_tasks_total{cluster=\\\ + \ {\n \"expr\": \"sum by (cluster, pool_name) (rate(mcac_thread_pools_total_blocked_tasks_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"{{cluster}}\ - \ - blocked {{pool_name}}\",\n \"refId\": \"A\"\n \ - \ }\n ],\n \"thresholds\": [ ],\n \ - \ \"timeFrom\": null,\n \"timeShift\": null,\n \ - \ \"title\": \"Blocked Tasks\",\n \"tooltip\": {\n \ - \ \"shared\": false,\n \"sort\": 0,\n \ - \ \"value_type\": \"individual\"\n },\n \"transparent\"\ - : true,\n \"type\": \"graph\",\n \"xaxis\": {\n \ - \ \"buckets\": null,\n \"mode\": \"time\",\n \ - \ \"name\": null,\n \"show\": true,\n \ - \ \"values\": [ ]\n },\n \"yaxes\": [\n\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + {{cluster}} - blocked {{pool_name}}\",\n \"refId\": \"A\"\n\ + \ }\n ],\n \"thresholds\": [ ],\n\ + \ \"timeFrom\": null,\n \"timeShift\": null,\n \ + \ \"title\": \"Blocked Tasks\",\n \"tooltip\": {\n \ + \ \"shared\": false,\n \"sort\": 0,\n \ + \ \"value_type\": \"individual\"\n },\n \"\ + transparent\": true,\n \"type\": \"graph\",\n \"xaxis\"\ + : {\n \"buckets\": null,\n \"mode\": \"time\"\ + ,\n \"name\": null,\n \"show\": true,\n \ + \ \"values\": [ ]\n },\n \"yaxes\": [\n\ \ {\n \"format\": \"short\",\n \ \ \"label\": null,\n \"logBase\": 1,\n \ \ \"max\": null,\n \"min\": 0,\n \ @@ -810,40 +811,40 @@ spec: \ \"repeat\": null,\n \"seriesOverrides\": [ ],\n \ \ \"spaceLength\": 10,\n \"stack\": false,\n \ \ \"steppedLine\": false,\n \"targets\": [\n \ - \ {\n \"expr\": \"sum by (cluster, message_type) (irate(mcac_dropped_message_dropped_total{cluster=\\\ + \ {\n \"expr\": \"sum by (cluster, message_type) (rate(mcac_dropped_message_dropped_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"{{cluster}}\ - \ - dropped {{message_type}}\",\n \"refId\": \"A\"\n \ - \ }\n ],\n \"thresholds\": [ ],\n \ - \ \"timeFrom\": null,\n \"timeShift\": null,\n \ - \ \"title\": \"Dropped Messages\",\n \"tooltip\": {\n \ - \ \"shared\": false,\n \"sort\": 0,\n \ - \ \"value_type\": \"individual\"\n },\n \"\ - transparent\": true,\n \"type\": \"graph\",\n \"xaxis\"\ - : {\n \"buckets\": null,\n \"mode\": \"time\"\ - ,\n \"name\": null,\n \"show\": true,\n \ - \ \"values\": [ ]\n },\n \"yaxes\": [\n\ - \ {\n \"format\": \"short\",\n \ - \ \"label\": null,\n \"logBase\": 1,\n \ - \ \"max\": null,\n \"min\": 0,\n \ - \ \"show\": true\n },\n {\n \ - \ \"format\": \"short\",\n \"label\": null,\n \ - \ \"logBase\": 1,\n \"max\": null,\n \ - \ \"min\": 0,\n \"show\": true\n \ - \ }\n ]\n },\n {\n \ - \ \"aliasColors\": { },\n \"bars\": false,\n \"dashLength\"\ - : 10,\n \"dashes\": false,\n \"datasource\": \"$PROMETHEUS_DS\"\ - ,\n \"description\": \"active threads summed per cluster\",\n \ - \ \"fill\": 0,\n \"fillGradient\": 0,\n \ - \ \"gridPos\": { },\n \"id\": 22,\n \"legend\":\ - \ {\n \"alignAsTable\": true,\n \"avg\": false,\n\ - \ \"current\": true,\n \"max\": false,\n \ - \ \"min\": false,\n \"rightSide\": false,\n \ - \ \"show\": true,\n \"sideWidth\": null,\n \ - \ \"sort\": \"current\",\n \"sortDesc\": true,\n\ - \ \"total\": false,\n \"values\": true\n \ - \ },\n \"lines\": true,\n \"linewidth\"\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + {{cluster}} - dropped {{message_type}}\",\n \"refId\": \"\ + A\"\n }\n ],\n \"thresholds\": [\ + \ ],\n \"timeFrom\": null,\n \"timeShift\": null,\n\ + \ \"title\": \"Dropped Messages\",\n \"tooltip\":\ + \ {\n \"shared\": false,\n \"sort\": 0,\n \ + \ \"value_type\": \"individual\"\n },\n \ + \ \"transparent\": true,\n \"type\": \"graph\",\n \ + \ \"xaxis\": {\n \"buckets\": null,\n \"\ + mode\": \"time\",\n \"name\": null,\n \"show\"\ + : true,\n \"values\": [ ]\n },\n \ + \ \"yaxes\": [\n {\n \"format\": \"short\"\ + ,\n \"label\": null,\n \"logBase\": 1,\n\ + \ \"max\": null,\n \"min\": 0,\n \ + \ \"show\": true\n },\n {\n \ + \ \"format\": \"short\",\n \"label\": null,\n\ + \ \"logBase\": 1,\n \"max\": null,\n \ + \ \"min\": 0,\n \"show\": true\n \ + \ }\n ]\n },\n {\n \ + \ \"aliasColors\": { },\n \"bars\": false,\n \"\ + dashLength\": 10,\n \"dashes\": false,\n \"datasource\"\ + : \"$PROMETHEUS_DS\",\n \"description\": \"active threads summed\ + \ per cluster\",\n \"fill\": 0,\n \"fillGradient\"\ + : 0,\n \"gridPos\": { },\n \"id\": 22,\n \ + \ \"legend\": {\n \"alignAsTable\": true,\n \ + \ \"avg\": false,\n \"current\": true,\n \ + \ \"max\": false,\n \"min\": false,\n \"rightSide\"\ + : false,\n \"show\": true,\n \"sideWidth\":\ + \ null,\n \"sort\": \"current\",\n \"sortDesc\"\ + : true,\n \"total\": false,\n \"values\": true\n\ + \ },\n \"lines\": true,\n \"linewidth\"\ : 1,\n \"links\": [ ],\n \"nullPointMode\": \"null\"\ ,\n \"percentage\": false,\n \"pointradius\": 5,\n\ \ \"points\": false,\n \"renderer\": \"flot\",\n \ @@ -941,25 +942,25 @@ spec: \ \"steppedLine\": false,\n \"targets\": [\n \ \ {\n \"expr\": \"max by (cluster) (1 - (sum by (cluster,\ \ dc, rack, instance) (rate(collectd_cpu_total{type=\\\"idle\\\", cluster=\\\"\ - $cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m]))\ + $cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s]))\ \ / sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{cluster=\\\"\ - $cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[5m:1m]))))\"\ + $cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s]))))\"\ ,\n \"format\": \"time_series\",\n \"\ intervalFactor\": 2,\n \"legendFormat\": \"max\",\n \ \ \"refId\": \"A\"\n },\n {\n\ \ \"expr\": \"min by (cluster) (1 - (sum by (cluster, dc,\ \ rack, instance) (rate(collectd_cpu_total{type=\\\"idle\\\", cluster=\\\"$cluster\\\ - \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m])) / sum\ - \ by (cluster, dc, rack, instance) (rate(collectd_cpu_total{cluster=\\\"$cluster\\\ - \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[5m:1m]))))\"\ + \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s])) /\ + \ sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{cluster=\\\"$cluster\\\ + \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s]))))\"\ ,\n \"format\": \"time_series\",\n \"\ intervalFactor\": 2,\n \"legendFormat\": \"min\",\n \ \ \"refId\": \"B\"\n },\n {\n\ \ \"expr\": \"avg by (cluster) (1 - (sum by (cluster, dc,\ \ rack, instance) (rate(collectd_cpu_total{type=\\\"idle\\\", cluster=\\\"$cluster\\\ - \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m])) / sum\ - \ by (cluster, dc, rack, instance) (rate(collectd_cpu_total{cluster=\\\"$cluster\\\ - \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[5m:1m]))))\"\ + \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s])) /\ + \ sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{cluster=\\\"$cluster\\\ + \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s]))))\"\ ,\n \"format\": \"time_series\",\n \"\ intervalFactor\": 2,\n \"legendFormat\": \"avg\",\n \ \ \"refId\": \"C\"\n }\n ],\n \ @@ -1106,20 +1107,20 @@ spec: \ \"targets\": [\n {\n \"expr\"\ : \"max by (cluster) (rate(collectd_processes_disk_octets_read_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"max\"\ - ,\n \"refId\": \"A\"\n },\n \ - \ {\n \"expr\": \"min by (cluster) (rate(collectd_processes_disk_octets_read_total{cluster=\\\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + max\",\n \"refId\": \"A\"\n },\n \ + \ {\n \"expr\": \"min by (cluster) (rate(collectd_processes_disk_octets_read_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"min\"\ - ,\n \"refId\": \"B\"\n },\n \ - \ {\n \"expr\": \"avg by (cluster) (rate(collectd_processes_disk_octets_read_total{cluster=\\\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + min\",\n \"refId\": \"B\"\n },\n \ + \ {\n \"expr\": \"avg by (cluster) (rate(collectd_processes_disk_octets_read_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"avg\"\ - ,\n \"refId\": \"C\"\n }\n \ - \ ],\n \"thresholds\": [ ],\n \"timeFrom\": null,\n\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + avg\",\n \"refId\": \"C\"\n }\n \ + \ ],\n \"thresholds\": [ ],\n \"timeFrom\": null,\n\ \ \"timeShift\": null,\n \"title\": \"Disk Read Thoughput\"\ ,\n \"tooltip\": {\n \"shared\": false,\n \ \ \"sort\": 0,\n \"value_type\": \"individual\"\n\ @@ -1160,20 +1161,20 @@ spec: \ \"targets\": [\n {\n \"expr\"\ : \"max by (cluster) (rate(collectd_processes_disk_octets_write_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"max\"\ - ,\n \"refId\": \"A\"\n },\n \ - \ {\n \"expr\": \"min by (cluster) (rate(collectd_processes_disk_octets_write_total{cluster=\\\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + max\",\n \"refId\": \"A\"\n },\n \ + \ {\n \"expr\": \"min by (cluster) (rate(collectd_processes_disk_octets_write_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"min\"\ - ,\n \"refId\": \"B\"\n },\n \ - \ {\n \"expr\": \"avg by (cluster) (rate(collectd_processes_disk_octets_write_total{cluster=\\\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + min\",\n \"refId\": \"B\"\n },\n \ + \ {\n \"expr\": \"avg by (cluster) (rate(collectd_processes_disk_octets_write_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"avg\"\ - ,\n \"refId\": \"C\"\n }\n \ - \ ],\n \"thresholds\": [ ],\n \"timeFrom\": null,\n\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + avg\",\n \"refId\": \"C\"\n }\n \ + \ ],\n \"thresholds\": [ ],\n \"timeFrom\": null,\n\ \ \"timeShift\": null,\n \"title\": \"Disk Write Thoughput\"\ ,\n \"tooltip\": {\n \"shared\": false,\n \ \ \"sort\": 0,\n \"value_type\": \"individual\"\n\ @@ -1212,28 +1213,28 @@ spec: \ \"steppedLine\": false,\n \"targets\": [\n \ \ {\n \"expr\": \"sum by (cluster) (rate(collectd_interface_if_octets_rx_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"outgoing\"\ - ,\n \"refId\": \"A\"\n },\n \ - \ {\n \"expr\": \"sum by (cluster) (rate(collectd_interface_if_octets_rx_total{cluster=\\\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + outgoing\",\n \"refId\": \"A\"\n },\n \ + \ {\n \"expr\": \"sum by (cluster) (rate(collectd_interface_if_octets_rx_total{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"incoming\"\ - ,\n \"refId\": \"B\"\n }\n \ - \ ],\n \"thresholds\": [ ],\n \"timeFrom\": null,\n\ - \ \"timeShift\": null,\n \"title\": \"Network I/O\"\ - ,\n \"tooltip\": {\n \"shared\": false,\n \ - \ \"sort\": 0,\n \"value_type\": \"individual\"\n\ - \ },\n \"transparent\": true,\n \"type\"\ - : \"graph\",\n \"xaxis\": {\n \"buckets\": null,\n\ - \ \"mode\": \"time\",\n \"name\": null,\n \ - \ \"show\": true,\n \"values\": [ ]\n \ - \ },\n \"yaxes\": [\n {\n \ - \ \"format\": \"bytes\",\n \"label\": null,\n \ - \ \"logBase\": 1,\n \"max\": null,\n \ - \ \"min\": null,\n \"show\": true\n \ - \ },\n {\n \"format\": \"bytes\",\n\ - \ \"label\": null,\n \"logBase\": 1,\n\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + incoming\",\n \"refId\": \"B\"\n }\n \ + \ ],\n \"thresholds\": [ ],\n \"timeFrom\"\ + : null,\n \"timeShift\": null,\n \"title\": \"Network\ + \ I/O\",\n \"tooltip\": {\n \"shared\": false,\n\ + \ \"sort\": 0,\n \"value_type\": \"individual\"\ + \n },\n \"transparent\": true,\n \"\ + type\": \"graph\",\n \"xaxis\": {\n \"buckets\"\ + : null,\n \"mode\": \"time\",\n \"name\": null,\n\ + \ \"show\": true,\n \"values\": [ ]\n \ + \ },\n \"yaxes\": [\n {\n \ + \ \"format\": \"bytes\",\n \"label\": null,\n \ + \ \"logBase\": 1,\n \"max\": null,\n \ + \ \"min\": null,\n \"show\": true\n \ + \ },\n {\n \"format\": \"bytes\"\ + ,\n \"label\": null,\n \"logBase\": 1,\n\ \ \"max\": null,\n \"min\": null,\n \ \ \"show\": true\n }\n ]\n \ \ }\n ],\n \"repeat\": null,\n \"repeatIteration\"\ @@ -1267,18 +1268,18 @@ spec: \ \"targets\": [\n {\n \"expr\"\ : \"max by (cluster) (1 - (sum by (cluster, dc, rack, instance) (rate(mcac_jvm_gc_time{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m])) / 1000))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\"\ + }[1m:30s])) / 1000))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\"\ : \"max\",\n \"refId\": \"A\"\n },\n \ \ {\n \"expr\": \"min by (cluster) (1 - (sum\ \ by (cluster, dc, rack, instance) (rate(mcac_jvm_gc_time{cluster=\\\"$cluster\\\ - \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[5m:1m])) /\ + \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s])) /\ \ 1000))\",\n \"format\": \"time_series\",\n \ \ \"intervalFactor\": 2,\n \"legendFormat\": \"min\"\ ,\n \"refId\": \"B\"\n },\n \ \ {\n \"expr\": \"avg by (cluster) (1 - (sum by (cluster,\ \ dc, rack, instance) (rate(mcac_jvm_gc_time{cluster=\\\"$cluster\\\", dc=~\\\"\ - $dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[5m:1m])) / 1000))\",\n\ + $dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s])) / 1000))\",\n\ \ \"format\": \"time_series\",\n \"intervalFactor\"\ : 2,\n \"legendFormat\": \"avg\",\n \"\ refId\": \"C\"\n }\n ],\n \"thresholds\"\ @@ -1323,21 +1324,21 @@ spec: \ \"stack\": false,\n \"steppedLine\": false,\n \ \ \"targets\": [\n {\n \"expr\"\ : \"max by (cluster) (rate(mcac_jvm_gc_time{cluster=\\\"$cluster\\\", dc=~\\\"\ - $dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[5m:1m]))\",\n \ - \ \"format\": \"time_series\",\n \"intervalFactor\"\ + $dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s]))\",\n \ + \ \"format\": \"time_series\",\n \"intervalFactor\"\ : 2,\n \"legendFormat\": \"max\",\n \"\ refId\": \"A\"\n },\n {\n \ \ \"expr\": \"min by (cluster) (rate(mcac_jvm_gc_time{cluster=\\\"$cluster\\\ - \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[5m:1m]))\"\ + \", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"}[1m:30s]))\"\ ,\n \"format\": \"time_series\",\n \"\ intervalFactor\": 2,\n \"legendFormat\": \"min\",\n \ \ \"refId\": \"B\"\n },\n {\n\ \ \"expr\": \"avg by (cluster) (rate(mcac_jvm_gc_time{cluster=\\\ \"$cluster\\\", dc=~\\\"$dc\\\", rack=~\\\"$rack\\\", instance=~\\\"$node\\\"\ - }[5m:1m]))\",\n \"format\": \"time_series\",\n \ - \ \"intervalFactor\": 2,\n \"legendFormat\": \"avg\"\ - ,\n \"refId\": \"C\"\n }\n \ - \ ],\n \"thresholds\": [ ],\n \"timeFrom\": null,\n\ + }[1m:30s]))\",\n \"format\": \"time_series\",\n \ + \ \"intervalFactor\": 2,\n \"legendFormat\": \"\ + avg\",\n \"refId\": \"C\"\n }\n \ + \ ],\n \"thresholds\": [ ],\n \"timeFrom\": null,\n\ \ \"timeShift\": null,\n \"title\": \"Garbage Collection\ \ Time\",\n \"tooltip\": {\n \"shared\": false,\n\ \ \"sort\": 0,\n \"value_type\": \"individual\"\