From 4185eb7607086e650b3210e3c1426f8160710038 Mon Sep 17 00:00:00 2001 From: Thomas Newton Date: Wed, 8 Nov 2023 12:51:00 +0000 Subject: [PATCH] Update flyteuser dashboard Signed-off-by: Thomas Newton --- deployment/stats/prometheus/flyteuser-dashboard.json | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/deployment/stats/prometheus/flyteuser-dashboard.json b/deployment/stats/prometheus/flyteuser-dashboard.json index a07a2bc5ec..55c7ad5851 100644 --- a/deployment/stats/prometheus/flyteuser-dashboard.json +++ b/deployment/stats/prometheus/flyteuser-dashboard.json @@ -1416,7 +1416,7 @@ "targets": [ { "datasource": null, - "expr": "(100 * max(container_memory_rss{image!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\",namespace=~\"$project-$domain\",label_workflow_name=~\"$workflow\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\", app_kubernetes_io_instance=\"prometheus\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name) / max(kube_pod_container_resource_limits_memory_bytes{container!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\", app_kubernetes_io_instance=\"prometheus\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name)) > 0", + "expr": "(100 * max(container_memory_rss{image!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\",namespace=~\"$project-$domain\",label_workflow_name=~\"$workflow\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name) / max(kube_pod_container_resource_limits_memory_bytes{container!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name)) > 0", "format": "time_series", "hide": false, "instant": false, @@ -1424,7 +1424,7 @@ "intervalFactor": 2, "legendFormat": "", "metric": "", - "query": "(100 * max(container_memory_rss{image!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\",namespace=~\"$project-$domain\",label_workflow_name=~\"$workflow\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\", app_kubernetes_io_instance=\"prometheus\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name) / max(kube_pod_container_resource_limits_memory_bytes{container!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\", app_kubernetes_io_instance=\"prometheus\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name)) > 0", + "query": "(100 * max(container_memory_rss{image!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\",namespace=~\"$project-$domain\",label_workflow_name=~\"$workflow\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name) / max(kube_pod_container_resource_limits_memory_bytes{container!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name)) > 0", "refId": "A", "step": 10, "target": "" @@ -1543,7 +1543,7 @@ "targets": [ { "datasource": null, - "expr": "(100* sum(rate(container_cpu_usage_seconds_total{image!=\"\"}[2m]) * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\",namespace=~\"$project-$domain\",label_workflow_name=~\"$workflow\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\", app_kubernetes_io_instance=\"prometheus\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name) / sum(kube_pod_container_resource_limits_cpu_cores{container!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\", app_kubernetes_io_instance=\"prometheus\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name)) > 0", + "expr": "(100* sum(rate(container_cpu_usage_seconds_total{image!=\"\"}[2m]) * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\",namespace=~\"$project-$domain\",label_workflow_name=~\"$workflow\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name) / sum(kube_pod_container_resource_limits_cpu_cores{container!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name)) > 0", "format": "time_series", "hide": false, "instant": false, @@ -1551,7 +1551,7 @@ "intervalFactor": 2, "legendFormat": "", "metric": "", - "query": "(100* sum(rate(container_cpu_usage_seconds_total{image!=\"\"}[2m]) * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\",namespace=~\"$project-$domain\",label_workflow_name=~\"$workflow\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\", app_kubernetes_io_instance=\"prometheus\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name) / sum(kube_pod_container_resource_limits_cpu_cores{container!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\", app_kubernetes_io_instance=\"prometheus\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name)) > 0", + "query": "(100* sum(rate(container_cpu_usage_seconds_total{image!=\"\"}[2m]) * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\",namespace=~\"$project-$domain\",label_workflow_name=~\"$workflow\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name) / sum(kube_pod_container_resource_limits_cpu_cores{container!=\"\"} * on(pod) group_left(label_execution_id, label_task_name, label_node_id, label_workflow_name) kube_pod_labels{label_execution_id !=\"\"} * on(pod) group_left(phase) kube_pod_status_phase{phase=\"Running\"}) by (namespace, pod, label_execution_id, label_task_name, label_node_id, label_workflow_name)) > 0", "refId": "A", "step": 10, "target": ""