[Data] Additional Ray Data Dashboard Metrics (ray-project#43628)

- Adds remaining metrics from `OpRuntimeMetrics` class in new time series charts on the Grafana and Ray Data dashboards.
- Clean up the `OpRuntimeMetrics` and `StatsActor` code, grouping related metrics by area and consolidating descriptions and comments.
- Visually group each section of Ray Data metrics. See below for screenshots of each section.
~- Programmatically generate Grafana panels from `OpRuntimeMetrics` fields.~ this is currently not possible, since we would need to add ray data as a dependency for ray dashboards / serve.

- Overview:
![overview](https://github.com/ray-project/ray/assets/5122851/05f0b21a-09f4-4a56-ac80-22c7aeea997d)

- Inputs:
![inputs](https://github.com/ray-project/ray/assets/5122851/2f356207-97ca-43a6-a7d9-eeeb0477c392)

- Outputs:
![outputs](https://github.com/ray-project/ray/assets/5122851/cf9f1fc8-eae8-406a-ae64-88a868b9b98c)

- Tasks:
![tasks](https://github.com/ray-project/ray/assets/5122851/7213e86d-c327-4904-825f-4b06997a7a17)

- Object Store Memory:
![object_store_memory](https://github.com/ray-project/ray/assets/5122851/78f088fc-7885-44cb-9916-d59195c3d31c)

- Iteration:
![iteration](https://github.com/ray-project/ray/assets/5122851/5e570618-caff-4a61-8bfb-5e4f04b30d85)

---------

Signed-off-by: Scott Lee <[email protected]>

.vale/styles/Vocab/Data/accept.txt

@@ -1,4 +1,5 @@
 autoscaler
+[Bb]ackpressure
 Dask
 Data('s)?
 [Dd]atasource
@@ -7,10 +8,12 @@ dtype
 [Gg]roupby
 [Ii]ndexable
 [Ii]ngest
+[Ii]nqueue(s)?
 [Ll]ookup(s)?
 Modin
 [Mm]ultiget(s)?
 ndarray(s)?
+[Oo]utqueue(s)?
 Predibase('s)?
 [Pp]refetch
 [Pp]refetching

dashboard/client/src/pages/metrics/Metrics.tsx

@@ -174,7 +174,7 @@ const METRICS_CONFIG: MetricsSectionConfig[] = [
 
 const DATA_METRICS_CONFIG: MetricsSectionConfig[] = [
  {
- title: "Ray Data Metrics",
+ title: "Ray Data Metrics (Overview)",
  contents: [
  {
  title: "Bytes Spilled",
@@ -208,10 +208,127 @@ const DATA_METRICS_CONFIG: MetricsSectionConfig[] = [
  title: "Rows Outputted",
  pathParams: "orgId=1&theme=light&panelId=11",
  },
+ ],
+ },
+ {
+ title: "Ray Data Metrics (Inputs)",
+ contents: [
+ {
+ title: "Input Blocks Received by Operator",
+ pathParams: "orgId=1&theme=light&panelId=17",
+ },
+ {
+ title: "Input Blocks Processed by Tasks",
+ pathParams: "orgId=1&theme=light&panelId=19",
+ },
+ {
+ title: "Input Bytes Processed by Tasks",
+ pathParams: "orgId=1&theme=light&panelId=20",
+ },
+ {
+ title: "Input Bytes Submitted to Tasks",
+ pathParams: "orgId=1&theme=light&panelId=21",
+ },
+ ],
+ },
+ {
+ title: "Ray Data Metrics (Outputs)",
+ contents: [
+ {
+ title: "Blocks Generated by Tasks",
+ pathParams: "orgId=1&theme=light&panelId=22",
+ },
+ {
+ title: "Bytes Generated by Tasks",
+ pathParams: "orgId=1&theme=light&panelId=23",
+ },
+ {
+ title: "Rows Generated by Tasks",
+ pathParams: "orgId=1&theme=light&panelId=24",
+ },
+ {
+ title: "Output Blocks Taken by Downstream Operators",
+ pathParams: "orgId=1&theme=light&panelId=25",
+ },
+ {
+ title: "Output Bytes Taken by Downstream Operators",
+ pathParams: "orgId=1&theme=light&panelId=26",
+ },
+ ],
+ },
+ {
+ title: "Ray Data Metrics (Tasks)",
+ contents: [
+ {
+ title: "Submitted Tasks",
+ pathParams: "orgId=1&theme=light&panelId=29",
+ },
+ {
+ title: "Running Tasks",
+ pathParams: "orgId=1&theme=light&panelId=30",
+ },
+ {
+ title: "Tasks with output blocks",
+ pathParams: "orgId=1&theme=light&panelId=31",
+ },
+ {
+ title: "Finished Tasks",
+ pathParams: "orgId=1&theme=light&panelId=32",
+ },
+ {
+ title: "Failed Tasks",
+ pathParams: "orgId=1&theme=light&panelId=33",
+ },
  {
  title: "Block Generation Time",
  pathParams: "orgId=1&theme=light&panelId=8",
  },
+ {
+ title: "Task Submission Backpressure Time",
+ pathParams: "orgId=1&theme=light&panelId=37",
+ },
+ ],
+ },
+ {
+ title: "Ray Data Metrics (Object Store Memory)",
+ contents: [
+ {
+ title: "Operator Internal Inqueue Size (Blocks)",
+ pathParams: "orgId=1&theme=light&panelId=13",
+ },
+ {
+ title: "Operator Internal Inqueue Size (Bytes)",
+ pathParams: "orgId=1&theme=light&panelId=14",
+ },
+ {
+ title: "Operator Internal Outqueue Size (Blocks)",
+ pathParams: "orgId=1&theme=light&panelId=15",
+ },
+ {
+ title: "Operator Internal Outqueue Size (Bytes)",
+ pathParams: "orgId=1&theme=light&panelId=16",
+ },
+ {
+ title: "Size of Blocks used in Pending Tasks (Bytes)",
+ pathParams: "orgId=1&theme=light&panelId=34",
+ },
+ {
+ title: "Freed Memory in Object Store (Bytes)",
+ pathParams: "orgId=1&theme=light&panelId=35",
+ },
+ {
+ title: "Spilled Memory in Object Store (Bytes)",
+ pathParams: "orgId=1&theme=light&panelId=36",
+ },
+ ],
+ },
+ {
+ title: "Ray Data Metrics (Iteration)",
+ contents: [
+ {
+ title: "Iteration Initialization Time",
+ pathParams: "orgId=1&theme=light&panelId=12",
+ },
  {
  title: "Iteration Blocked Time",
  pathParams: "orgId=1&theme=light&panelId=9",
@@ -222,6 +339,11 @@ const DATA_METRICS_CONFIG: MetricsSectionConfig[] = [
  },
  ],
  },
+ // Add metrics with `metrics_group: "misc"` here.
+ // {
+ // title: "Ray Data Metrics (Miscellaneous)",
+ // contents: [],
+ // },
 ];
 
 export const Metrics = () => {