全部产品
Search
文档中心

服务网格 ASM:使用QuotaSchedulingPolicy实现请求调用配额管理

更新时间:Oct 25, 2024

ASM流量调度套件支持通过QuotaSchedulingPolicy实现指定请求调用配额下的请求优先级调度。当系统中正在处理的请求速率超过指定的配额时,后续的请求将会被排队,同时优先级高的请求能够被更快处理。本文介绍如何使用流量调度套件提供的QuotaSchedulingPolicy来实现请求调用配额管理。

背景信息

QuotaSchedulingPolicy通过令牌桶算法来控制调用指定服务的请求速率,并在速率超过指定配额时对请求进行排队处理。大致工作流程如下:

  1. 使用限流器对请求进行速率限制:使用令牌桶算法对请求进行限流,有关限流器的算法实现,可详细参考使用RateLimitingPolicy实现分用户限流场景的背景信息。

  2. 请求调度:请求速率超过配额限制后,后续请求将会被排队,等待先前请求处理完成后再发送给服务,以保证请求速率始终保持在给定数值。同时,高优先级的请求有更大的机会被从队列中取出发送给服务。

和限流的场景不同,使用QuotaSchedulingPolicy时,若请求速率超过限制,此时请求不会被直接拒绝,而是进入一个优先级队列,在保证请求速率始终在限制内的同时对请求进行优先级调度。

前提条件

步骤一:创建QuotaSchedulingPolicy配额管理规则

  1. 使用kubectl连接到ASM实例,具体操作,请参见通过控制面kubectl访问Istio资源

  2. 使用以下内容创建quotaschedulingpolicy.yaml文件

    apiVersion: istio.alibabacloud.com/v1
    kind: QuotaSchedulingPolicy
    metadata:
      name: quotascheduling
      namespace: istio-system
    spec:
      quota_scheduler:
        bucket_capacity: 10
        fill_amount: 10
        rate_limiter:
          interval: 1s
        scheduler:
          workloads:
            - label_matcher:
                match_labels:
                  http.request.header.user_type: guest
              parameters:
                priority: 50.0
              name: guest
            - label_matcher:
                match_labels:
                  http.request.header.user_type: subscriber
              parameters:
                priority: 200.0
              name: subscriber
        selectors:
        - service: httpbin.default.svc.cluster.local

    部分配置项说明如下。关于配置项的更多信息,请参见QuotaSchedulingPolicy CRD说明

    配置项

    说明

    fill_amount

    在interval指定的时间间隔内填充令牌的数量。示例中指定为10,即每过interval指定的时间间隔后便向令牌桶填充10个令牌。

    interval

    向令牌桶中填充令牌的时间间隔。示例中指定为1s,即每过1秒后便向令牌桶填充10个令牌。

    bucket_capacity

    令牌桶内的令牌数量上限。当请求速率小于令牌桶填充速率时,令牌桶内的令牌数量会持续增加,最大将达到bucket_capacity。使用bucket_capacity可以容许一定程度的突发流量。示例中设置为10,和fill_amount相同,即不允许任何突发流量。

    workloads

    根据请求header中的user_type定义了两类请求,分别是guestsubscriberguest类型的请求优先级是50,subscriber类型的请求优先级是200。

    selectors

    指定应用限流策略的多个服务。示例中使用httpbin.default.svc.cluster.local 服务进行并行度限制。

  3. 执行以下命令,创建配额管理规则

kubectl apply -f quotaschedulingpolicy.yaml

步骤二:测试请求配额管理效果

本步骤使用压测工具fortio进行测试,安装方式请参见安装fortio

  1. 同时打开两个终端,并分别运行下面两个压测命令(尽可能同时开始这两个测试),整个测试期间,请确保不要关闭对应的终端。两个测试都使用10并发、10000预期QPS的设定对服务发起调用,远远超过了服务的预期并发度限制。

    fortio load -c 10 -qps 10000  -H "user_type:guest" -t 30s -timeout 60s -a http://${ASM网关IP}/status/201
    fortio load -c 10 -qps 10000  -H "user_type:subscriber" -t 30s -timeout 60s -a http://${ASM网关IP}/status/202
    说明

    请将上述指令中的${ASM网关IP}替换为ASM网关的IP地址。有关获取ASM网关IP地址的具体操作,请参见使用Istio资源实现版本流量路由

    测试1的预期输出:

    ...
    # target 50% 4.83333
    # target 75% 5.20763
    # target 90% 5.38203
    # target 99% 5.48668
    # target 99.9% 5.49714
    Sockets used: 10 (for perfect keepalive, would be 10)
    Uniform: false, Jitter: false
    Code 201 : 70 (100.0 %)
    Response Header Sizes : count 70 avg 249.94286 +/- 0.2871 min 248 max 250 sum 17496
    Response Body/Total Sizes : count 70 avg 249.94286 +/- 0.2871 min 248 max 250 sum 17496
    All done 70 calls (plus 10 warmup) 4566.839 ms avg, 2.1 qps
    Successfully wrote 4693 bytes of Json data to 2024-07-26-232250_114_55_5_155_status_201_iZbp1cz9ur77robaiv085tZ.json

    测试2的预期输出:

    fortio load -c 10 -qps 10000  -H "user_type:subscriber" -t 30s -timeout 60s -a http://114.55.xx.xx/status/202
    ...
    # target 50% 0.253333
    # target 75% 1.875
    # target 90% 4.26635
    # target 99% 4.47301
    # target 99.9% 4.49367
    Sockets used: 10 (for perfect keepalive, would be 10)
    Uniform: false, Jitter: false
    Code 202 : 250 (100.0 %)
    Response Header Sizes : count 250 avg 250.264 +/- 0.4408 min 250 max 251 sum 62566
    Response Body/Total Sizes : count 250 avg 250.264 +/- 0.4408 min 250 max 251 sum 62566
    All done 250 calls (plus 10 warmup) 1226.657 ms avg, 8.0 qps
    Successfully wrote 4509 bytes of Json data to 2024-07-26-232250_114_55_5_155_status_202_iZbp1cz9ur77robaiv085tZ.json

    可以看到,测试2的平均请求延迟约为测试1的四分之一,QPS约为测试1的四倍。这是由于先前定义的策略中,subscriber类型的请求优先级是guest类型的请求的四倍。同时,两个测试在30秒内总共完成了320个请求,除去最开始预热使用的20个请求,服务收到的请求速率正好是1秒钟10个请求,证明服务收到的请求始终在给定限额之内。

相关操作

您可以通过Grafana大盘来观测QuotaSchedulingPolicy策略的执行效果。请确保Grafana使用的数据源Prometheus实例已经完成配置采集ASM流量调度套件相关指标

将以下内容导入到Grafana,创建QuotaSchedulingPolicy策略的大盘。

展开查看JSON内容

{
  "annotations": {
    "list": [
      {
        "builtIn": 1,
        "datasource": {
          "type": "grafana",
          "uid": "-- Grafana --"
        },
        "enable": true,
        "hide": true,
        "iconColor": "rgba(0, 211, 255, 1)",
        "name": "Annotations & Alerts",
        "type": "dashboard"
      }
    ]
  },
  "editable": true,
  "fiscalYearStartMonth": 0,
  "graphTooltip": 0,
  "id": 44,
  "links": [],
  "liveNow": false,
  "panels": [
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "description": "Signal derived from periodic execution of query: (sum(rate(workload_requests_total{policy_name=\"quotascheduling\",component_id=\"root.0\",decision_type=\"DECISION_TYPE_ACCEPTED\"}[30s])) / sum(rate(workload_requests_total{policy_name=\"quotascheduling\",component_id=\"root.0\"}[30s]))) * 100",
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": ""
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 24,
        "x": 0,
        "y": 0
      },
      "id": 1,
      "interval": "10s",
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "(sum by (policy_name)(rate(workload_requests_total{component_id=\"root.0\",decision_type=\"DECISION_TYPE_ACCEPTED\"}[30s])) / sum by (policy_name)(rate(workload_requests_total{component_id=\"root.0\"}[30s]))) * 100",
          "intervalFactor": 1,
          "legendFormat": "policy={{policy_name}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "ACCEPT_PERCENTAGE - runs every 10s, metrics: workload_requests_total",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "description": "",
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "Decisions",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 24,
        "x": 0,
        "y": 10
      },
      "id": 2,
      "interval": "10s",
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "expr": "sum by(decision_type) (rate(workload_requests_total{component_id=\"root.0\",policy_name=\"quotascheduling\"}[$__rate_interval]))",
          "intervalFactor": 1,
          "refId": "A"
        }
      ],
      "title": "Workload Decisions",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "description": "",
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "Decisions",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 24,
        "x": 0,
        "y": 20
      },
      "id": 3,
      "interval": "10s",
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "expr": "sum by(workload_index, decision_type) (rate(workload_requests_total{component_id=\"root.0\",policy_name=\"quotascheduling\",decision_type=\"DECISION_TYPE_ACCEPTED\"}[$__rate_interval]))",
          "intervalFactor": 1,
          "refId": "A"
        }
      ],
      "title": "Workload Decisions (accepted)",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "description": "",
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "Decisions",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 24,
        "x": 0,
        "y": 30
      },
      "id": 4,
      "interval": "10s",
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by(workload_index, decision_type, policy_name) (rate(workload_requests_total{component_id=\"root.0\",decision_type=\"DECISION_TYPE_REJECTED\"}[$__rate_interval]))",
          "intervalFactor": 1,
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Workload Decisions (rejected)",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "noValue": "No data",
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "blue",
                "value": null
              }
            ]
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 8,
        "x": 0,
        "y": 40
      },
      "id": 5,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "center",
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.0.9",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(increase(workload_requests_total{component_id=\"root.0\"}[$__range]))",
          "instant": false,
          "intervalFactor": 1,
          "legendFormat": "{{ policy_name }}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Total Requests",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "noValue": "No data",
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 8,
        "x": 8,
        "y": 40
      },
      "id": 6,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "center",
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.0.9",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(increase(workload_requests_total{component_id=\"root.0\",decision_type=\"DECISION_TYPE_ACCEPTED\"}[$__range]))",
          "instant": false,
          "intervalFactor": 1,
          "legendFormat": "{{ policy_name }}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Total Accepted Requests",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "noValue": "No rejected requests",
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "red",
                "value": null
              }
            ]
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 8,
        "x": 16,
        "y": 40
      },
      "id": 7,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "center",
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.0.9",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(increase(workload_requests_total{component_id=\"root.0\",decision_type=\"DECISION_TYPE_REJECTED\"}[$__range]))",
          "instant": false,
          "intervalFactor": 1,
          "legendFormat": "{{ policy_name }}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Total Rejected Requests",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "description": "",
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "Latency",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": "ms"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 24,
        "x": 0,
        "y": 50
      },
      "id": 8,
      "interval": "10s",
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "(sum by (workload_index, policy_name) (increase(workload_latency_ms_sum{component_id=\"root.0\"}[$__rate_interval])))/(sum by (workload_index, policy_name) (increase(workload_latency_ms_count{component_id=\"root.0\"}[$__rate_interval])))",
          "intervalFactor": 1,
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Workload Latency",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "description": "",
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "Wait Time",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": "ms"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 12,
        "x": 0,
        "y": 60
      },
      "id": 9,
      "interval": "10s",
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "(sum by (workload_index, policy_name) (increase(request_in_queue_duration_ms_sum{component_id=\"root.0\"}[$__rate_interval])))/ ((sum by (workload_index, policy_name) (increase(request_in_queue_duration_ms_count{component_id=\"root.0\"}[$__rate_interval]))) != 0)",
          "intervalFactor": 1,
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Request in Queue Duration",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisGridShow": true,
            "axisLabel": "",
            "axisPlacement": "hidden",
            "fillOpacity": 80,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineWidth": 1,
            "scaleDistribution": {
              "type": "linear"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": "ms"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 12,
        "x": 12,
        "y": 60
      },
      "id": 10,
      "options": {
        "barRadius": 0,
        "barWidth": 0.97,
        "colorByField": "",
        "fullHighlight": false,
        "groupWidth": 0.7,
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "orientation": "horizontal",
        "showValue": "auto",
        "stacking": "none",
        "tooltip": {
          "mode": "single",
          "sort": "sort"
        },
        "xTickLabelRotation": 0,
        "xTickLabelSpacing": 0
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "topk(10, (sum by(workload_index, policy_name) (increase(request_in_queue_duration_ms_sum{component_id=\"root.0\"}[$__range])) ) / ((sum by(workload_index, policy_name) (increase(request_in_queue_duration_ms_count{component_id=\"root.0\"}[$__range])) )) != 0)",
          "format": "time_series",
          "instant": true,
          "intervalFactor": 1,
          "legendFormat": "",
          "range": false,
          "refId": "A"
        }
      ],
      "title": "Request in Queue Duration",
      "type": "barchart"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "description": "",
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "Token Rate",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": ""
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 70
      },
      "id": 13,
      "interval": "10s",
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(rate(incoming_tokens_total{component_id=\"root.0\"}[$__rate_interval]))",
          "intervalFactor": 1,
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Incoming Token Rate",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "description": "",
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "Token Rate",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 80
              }
            ]
          },
          "unit": ""
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 70
      },
      "id": 14,
      "interval": "10s",
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "pluginVersion": "v10.1.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(rate(accepted_tokens_total{component_id=\"root.0\"}[$__rate_interval]))",
          "intervalFactor": 1,
          "legendFormat": "Accepted Token Rate",
          "range": true,
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(rate(rejected_tokens_total{component_id=\"root.0\"}[$__rate_interval]))",
          "intervalFactor": 1,
          "legendFormat": "Rejected Token Rate",
          "range": true,
          "refId": "B"
        }
      ],
      "title": "Accepted Token Rate vs Rejected Token Rate",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "noValue": "No data",
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "blue",
                "value": null
              }
            ]
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 8,
        "x": 0,
        "y": 78
      },
      "id": 15,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "center",
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.0.9",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(increase(incoming_tokens_total{component_id=\"root.0\"}[$__range]))",
          "instant": false,
          "intervalFactor": 1,
          "legendFormat": "{{ instance }} - {{ policy_name }}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Total Incoming Tokens",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "noValue": "No data",
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 8,
        "x": 8,
        "y": 78
      },
      "id": 16,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "center",
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.0.9",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(increase(accepted_tokens_total{component_id=\"root.0\"}[$__range]))",
          "instant": false,
          "intervalFactor": 1,
          "legendFormat": "{{ instance }} - {{ policy_name }}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Total Accepted Tokens",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "noValue": "No data",
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "red",
                "value": null
              }
            ]
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 10,
        "w": 8,
        "x": 16,
        "y": 78
      },
      "id": 17,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "center",
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.0.9",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (policy_name)(increase(rejected_tokens_total{component_id=\"root.0\"}[$__range]))",
          "instant": false,
          "intervalFactor": 1,
          "legendFormat": "{{ instance }} - {{ policy_name }}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Total Rejected Tokens",
      "type": "stat"
    }
  ],
  "refresh": false,
  "schemaVersion": 38,
  "style": "dark",
  "tags": [],
  "templating": {
    "list": [
      {
        "hide": 0,
        "includeAll": false,
        "label": "Data Source",
        "multi": false,
        "name": "datasource",
        "options": [],
        "query": "prometheus",
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "type": "datasource"
      }
    ]
  },
  "time": {
    "from": "now-5m",
    "to": "now"
  },
  "timepicker": {},
  "timezone": "browser",
  "title": "Policy Summary - quotascheduling",
  "version": 1,
  "weekStart": ""
}

大盘效果如下。

image