* Copyright (c) 2024 Huawei Technologies Co., Ltd.
* openFuyao is licensed under Mulan PSL v2.
* You can use this software according to the terms and conditions of the Mulan PSL v2.
* You may obtain a copy of Mulan PSL v2 at:
* http://license.coscl.org.cn/MulanPSL2
* THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
* EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT,
* MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
* See the Mulan PSL v2 for more details.
*/
package service
var clusterLevelMetrics = []string{
"cluster_cpu_total",
"cluster_memory_total",
"cluster_total_cpu_usage",
"cluster_total_memory_usage",
"cluster_hls_cpu_usage",
"cluster_hls_memory_usage",
"cluster_ls_cpu_usage",
"cluster_ls_memory_usage",
"cluster_be_cpu_usage",
"cluster_be_memory_usage",
"cluster_noncolo_cpu_usage",
"cluster_noncolo_memory_usage",
"cluster_be_cpu_allocatable",
"cluster_be_memory_allocatable",
"cluster_be_cpu_request",
"cluster_be_memory_request",
"cluster_hls_cpu_request",
"cluster_hls_memory_request",
"cluster_ls_cpu_request",
"cluster_ls_memory_request",
"cluster_noncolo_cpu_request",
"cluster_noncolo_memory_request",
}
var nodeLevelMetrics = []string{
"node_cpu_total",
"node_memory_total",
"node_total_cpu_usage",
"node_total_memory_usage",
"node_hls_cpu_usage",
"node_hls_memory_usage",
"node_ls_cpu_usage",
"node_ls_memory_usage",
"node_be_cpu_usage",
"node_be_memory_usage",
"node_noncolo_cpu_usage",
"node_noncolo_memory_usage",
"node_be_cpu_allocatable",
"node_be_memory_allocatable",
"node_be_cpu_request",
"node_be_memory_request",
"node_hls_cpu_request",
"node_hls_memory_request",
"node_ls_cpu_request",
"node_ls_memory_request",
"node_noncolo_cpu_request",
"node_noncolo_memory_request",
}
var prometheusQLSet = map[string]string{
"cluster_cpu_total": `sum(machine_cpu_cores) by (cluster)`,
"cluster_memory_total": `sum(node_memory_MemTotal_bytes{job="node-exporter"}) by (cluster)`,
"cluster_total_cpu_usage": `sum(rate(node_cpu_seconds_total{mode!="idle", mode!="iowait", ` +
`mode!="steal"}[5m])) by (cluster)`,
"cluster_total_memory_usage": `sum(node_memory_MemTotal_bytes{job="node-exporter"}) by (cluster) - ` +
`sum(:node_memory_MemAvailable_bytes:sum) by (cluster)`,
"cluster_hls_cpu_usage": `sum(pod_cpu_usage_by_colocation{type="HLS"})`,
"cluster_hls_memory_usage": `sum(pod_memory_usage_by_colocation{type="HLS"})`,
"cluster_ls_cpu_usage": `sum(pod_cpu_usage_by_colocation{type="LS"})`,
"cluster_ls_memory_usage": `sum(pod_memory_usage_by_colocation{type="LS"})`,
"cluster_be_cpu_usage": `sum(pod_cpu_usage_by_colocation{type="BE"})`,
"cluster_be_memory_usage": `sum(pod_memory_usage_by_colocation{type="BE"})`,
"cluster_noncolo_cpu_usage": `sum(pod_cpu_usage_by_colocation{type="None"})`,
"cluster_noncolo_memory_usage": `sum(pod_memory_usage_by_colocation{type="None"})`,
"cluster_be_cpu_allocatable": `sum(node_overquota_cpu_allocatable) / 1000`,
"cluster_be_memory_allocatable": `sum(node_overquota_memory_allocatable)`,
"cluster_be_cpu_request": `sum(pod_overquota_cpu_request) / 1000`,
"cluster_be_memory_request": `sum(pod_overquota_memory_request)`,
"cluster_hls_cpu_request": `sum (
kube_pod_container_resource_requests{resource="cpu", unit="core"}
and on(pod, namespace)
label_replace(
label_replace(
pod_cpu_usage_by_colocation{type="HLS"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
)
)`,
"cluster_hls_memory_request": `sum (
kube_pod_container_resource_requests{resource="memory", unit="byte"}
and on(pod, namespace)
label_replace(
label_replace(
pod_memory_usage_by_colocation{type="HLS"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
)
)`,
"cluster_ls_cpu_request": `sum (
kube_pod_container_resource_requests{resource="cpu", unit="core"}
and on(pod, namespace)
label_replace(
label_replace(
pod_cpu_usage_by_colocation{type="LS"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
)
)`,
"cluster_ls_memory_request": `sum (
kube_pod_container_resource_requests{resource="memory", unit="byte"}
and on(pod, namespace)
label_replace(
label_replace(
pod_memory_usage_by_colocation{type="LS"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
)
)`,
"cluster_noncolo_cpu_request": `sum (
kube_pod_container_resource_requests{resource="cpu", unit="core"}
and on(namespace, pod)
label_replace(
label_replace(
pod_cpu_usage_by_colocation{type="None"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
)
)`,
"cluster_noncolo_memory_request": `sum (
kube_pod_container_resource_requests{resource="memory", unit="byte"}
and on(pod, namespace)
label_replace(
label_replace(
pod_memory_usage_by_colocation{type="None"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
)
)`,
"node_cpu_total": `sum(label_replace(sum(machine_cpu_cores) by (cluster, node), "instance", "$1", ` +
`"node", "(.*)")) by (cluster, instance)`,
"node_memory_total": `sum(node_memory_MemTotal_bytes{job="node-exporter"}) by (cluster, instance)`,
"node_total_cpu_usage": `sum(label_replace(sum(machine_cpu_cores) by (cluster, node), "instance", "$1", ` +
`"node", "(.*)")) by (cluster, instance) * (1 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) ` +
`by (cluster, instance)))`,
"node_total_memory_usage": `sum(node_memory_MemTotal_bytes{job="node-exporter"}) by (cluster, instance) - ` +
`sum(node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"} + ` +
`node_memory_Cached_bytes{job="node-exporter"}) by (cluster, instance)`,
"node_hls_cpu_usage": `sum by (instance) (label_replace(` +
`pod_cpu_usage_by_colocation{type="HLS"}, "instance", "$1", "node", "(.*)"))`,
"node_hls_memory_usage": `sum by (instance) (label_replace(` +
`pod_memory_usage_by_colocation{type="HLS"}, "instance", "$1", "node", "(.*)"))`,
"node_ls_cpu_usage": `sum by (instance) (label_replace(` +
`pod_cpu_usage_by_colocation{type="LS"}, "instance", "$1", "node", "(.*)"))`,
"node_ls_memory_usage": `sum by (instance) (label_replace(` +
`pod_memory_usage_by_colocation{type="LS"}, "instance", "$1", "node", "(.*)"))`,
"node_be_cpu_usage": `sum by (instance) (label_replace(` +
`pod_cpu_usage_by_colocation{type="BE"}, "instance", "$1", "node", "(.*)"))`,
"node_be_memory_usage": `sum by (instance) (label_replace(` +
`pod_memory_usage_by_colocation{type="BE"}, "instance", "$1", "node", "(.*)"))`,
"node_noncolo_cpu_usage": `sum by (instance) (label_replace(` +
`pod_cpu_usage_by_colocation{type="None"}, "instance", "$1", "node", "(.*)"))`,
"node_noncolo_memory_usage": `sum by (instance) (label_replace(` +
`pod_memory_usage_by_colocation{type="None"}, "instance", "$1", "node", "(.*)"))`,
"node_be_cpu_allocatable": `sum(label_replace(node_overquota_cpu_allocatable, ` +
`"instance", "$1", "node_name", "(.*)")) by (instance) / 1000`,
"node_be_memory_allocatable": `sum(label_replace(node_overquota_memory_allocatable, ` +
`"instance", "$1", "node_name", "(.*)")) by (instance)`,
"node_be_cpu_request": `sum(label_replace(pod_overquota_cpu_request, "instance", ` +
`"$1", "node", "(.*)")) by (instance) / 1000`,
"node_be_memory_request": `sum(label_replace(pod_overquota_memory_request, "instance", ` +
`"$1", "node", "(.*)")) by (instance)`,
"node_hls_cpu_request": `sum by (instance) (
label_replace(
kube_pod_container_resource_requests{resource="cpu", unit="core"}
and on(pod, namespace)
label_replace(
label_replace(
pod_cpu_usage_by_colocation{type="HLS"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
),
"instance", "$1", "node", "(.*)"
)
)`,
"node_hls_memory_request": `sum by (instance) (
label_replace(
kube_pod_container_resource_requests{resource="memory", unit="byte"}
and on(pod, namespace)
label_replace(
label_replace(
pod_memory_usage_by_colocation{type="HLS"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
),
"instance", "$1", "node", "(.*)"
)
)`,
"node_ls_cpu_request": `sum by (instance) (
label_replace(
kube_pod_container_resource_requests{resource="cpu", unit="core"}
and on(pod, namespace)
label_replace(
label_replace(
pod_cpu_usage_by_colocation{type="LS"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
),
"instance", "$1", "node", "(.*)"
)
)`,
"node_ls_memory_request": `sum by (instance) (
label_replace(
kube_pod_container_resource_requests{resource="memory", unit="byte"}
and on(pod, namespace)
label_replace(
label_replace(
pod_memory_usage_by_colocation{type="LS"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
),
"instance", "$1", "node", "(.*)"
)
)`,
"node_noncolo_cpu_request": `sum by (instance) (
label_replace(
kube_pod_container_resource_requests{resource="cpu", unit="core"}
and on(pod, namespace)
label_replace(
label_replace(
pod_cpu_usage_by_colocation{type="None"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
),
"instance", "$1", "node", "(.*)"
)
)`,
"node_noncolo_memory_request": `sum by (instance) (
label_replace(
kube_pod_container_resource_requests{resource="memory", unit="byte"}
and on(pod, namespace)
label_replace(
label_replace(
pod_memory_usage_by_colocation{type="None"},
"namespace", "$1", "exported_namespace", "(.*)"
),
"pod", "$1", "pod_name", "(.*)"
),
"instance", "$1", "node", "(.*)"
)
)`,
}
