ClusterCockpit/cc-backend
1
0
Fork 0
mirror of https://github.com/ClusterCockpit/cc-backend synced 2025-07-23 12:51:40 +02:00
Code Issues Packages Releases Activity

Merge branch 'dev' into add_editmeta_byrequest

Browse Source
This commit is contained in:
Christoph Kluge
2025-07-03 14:02:54 +02:00
parent 8dfaa78a83 60ec7e54f5
commit d35d00a18e
242 changed files with 15413 additions and 15625 deletions
Download Patch File Download Diff File Expand all files Collapse all files

441
api/schema.graphqls
View File

@@ -4,61 +4,78 @@ scalar Any
scalar NullableFloat
scalar MetricScope
scalar JobState
scalar NodeState
scalar MonitoringState
type Node {
id: ID!
hostname: String!
cluster: String!
subCluster: String!
nodeState: NodeState!
HealthState: MonitoringState!
metaData: Any
}
type NodeStats {
state: String!
count: Int!
}
type Job {
id: ID!
jobId: Int!
user: String!
project: String!
cluster: String!
subCluster: String!
startTime: Time!
duration: Int!
walltime: Int!
numNodes: Int!
numHWThreads: Int!
numAcc: Int!
energy: Float!
SMT: Int!
exclusive: Int!
partition: String!
arrayJobId: Int!
id: ID!
jobId: Int!
user: String!
project: String!
cluster: String!
subCluster: String!
startTime: Time!
duration: Int!
walltime: Int!
numNodes: Int!
numHWThreads: Int!
numAcc: Int!
energy: Float!
SMT: Int!
exclusive: Int!
partition: String!
arrayJobId: Int!
monitoringStatus: Int!
state: JobState!
tags: [Tag!]!
resources: [Resource!]!
concurrentJobs: JobLinkResultList
footprint: [FootprintValue]
energyFootprint: [EnergyFootprintValue]
metaData: Any
userData: User
state: JobState!
tags: [Tag!]!
resources: [Resource!]!
concurrentJobs: JobLinkResultList
footprint: [FootprintValue]
energyFootprint: [EnergyFootprintValue]
metaData: Any
userData: User
}
type JobLink {
id: ID!
jobId: Int!
id: ID!
jobId: Int!
}
type Cluster {
name: String!
partitions: [String!]! # Slurm partitions
subClusters: [SubCluster!]! # Hardware partitions/subclusters
name: String!
partitions: [String!]! # Slurm partitions
subClusters: [SubCluster!]! # Hardware partitions/subclusters
}
type SubCluster {
name: String!
nodes: String!
numberOfNodes: Int!
processorType: String!
socketsPerNode: Int!
coresPerSocket: Int!
threadsPerCore: Int!
flopRateScalar: MetricValue!
flopRateSimd: MetricValue!
name: String!
nodes: String!
numberOfNodes: Int!
processorType: String!
socketsPerNode: Int!
coresPerSocket: Int!
threadsPerCore: Int!
flopRateScalar: MetricValue!
flopRateSimd: MetricValue!
memoryBandwidth: MetricValue!
topology: Topology!
metricConfig: [MetricConfig!]!
footprint: [String!]!
topology: Topology!
metricConfig: [MetricConfig!]!
footprint: [String!]!
}
type FootprintValue {
@@ -80,99 +97,112 @@ type MetricValue {
}
type Topology {
node: [Int!]
socket: [[Int!]!]
node: [Int!]
socket: [[Int!]!]
memoryDomain: [[Int!]!]
die: [[Int!]!]
core: [[Int!]!]
die: [[Int!]!]
core: [[Int!]!]
accelerators: [Accelerator!]
}
type Accelerator {
id: String!
type: String!
id: String!
type: String!
model: String!
}
type SubClusterConfig {
name: String!
peak: Float
normal: Float
name: String!
peak: Float
normal: Float
caution: Float
alert: Float
remove: Boolean
alert: Float
remove: Boolean
}
type MetricConfig {
name: String!
unit: Unit!
scope: MetricScope!
name: String!
unit: Unit!
scope: MetricScope!
aggregation: String!
timestep: Int!
peak: Float!
normal: Float
timestep: Int!
peak: Float!
normal: Float
caution: Float!
alert: Float!
alert: Float!
lowerIsBetter: Boolean
subClusters: [SubClusterConfig!]!
}
type Tag {
id: ID!
id: ID!
type: String!
name: String!
scope: String!
}
type Resource {
hostname: String!
hwthreads: [Int!]
accelerators: [String!]
hostname: String!
hwthreads: [Int!]
accelerators: [String!]
configuration: String
}
type JobMetricWithName {
name: String!
scope: MetricScope!
name: String!
scope: MetricScope!
metric: JobMetric!
}
type JobMetric {
unit: Unit
timestep: Int!
series: [Series!]
unit: Unit
timestep: Int!
series: [Series!]
statisticsSeries: StatsSeries
}
type Series {
hostname: String!
id: String
hostname: String!
id: String
statistics: MetricStatistics
data: [NullableFloat!]!
data: [NullableFloat!]!
}
type StatsSeries {
mean: [NullableFloat!]!
mean: [NullableFloat!]!
median: [NullableFloat!]!
min: [NullableFloat!]!
max: [NullableFloat!]!
min: [NullableFloat!]!
max: [NullableFloat!]!
}
type JobStatsWithScope {
name: String!
scope: MetricScope!
stats: [ScopedStats!]!
type NamedStatsWithScope {
name: String!
scope: MetricScope!
stats: [ScopedStats!]!
}
type ScopedStats {
hostname: String!
id: String
data: MetricStatistics!
hostname: String!
id: String
data: MetricStatistics!
}
type JobStats {
name: String!
stats: MetricStatistics!
id: Int!
jobId: String!
startTime: Int!
duration: Int!
cluster: String!
subCluster: String!
numNodes: Int!
numHWThreads: Int
numAccelerators: Int
stats: [NamedStats!]!
}
type NamedStats {
name: String!
data: MetricStatistics!
}
type Unit {
@@ -188,12 +218,12 @@ type MetricStatistics {
type MetricFootprints {
metric: String!
data: [NullableFloat!]!
data: [NullableFloat!]!
}
type Footprints {
timeWeights: TimeWeights!
metrics: [MetricFootprints!]!
metrics: [MetricFootprints!]!
}
type TimeWeights {
@@ -202,20 +232,33 @@ type TimeWeights {
coreHours: [NullableFloat!]!
}
enum Aggregate { USER, PROJECT, CLUSTER }
enum SortByAggregate { TOTALWALLTIME, TOTALJOBS, TOTALNODES, TOTALNODEHOURS, TOTALCORES, TOTALCOREHOURS, TOTALACCS, TOTALACCHOURS }
enum Aggregate {
USER
PROJECT
CLUSTER
}
enum SortByAggregate {
TOTALWALLTIME
TOTALJOBS
TOTALNODES
TOTALNODEHOURS
TOTALCORES
TOTALCOREHOURS
TOTALACCS
TOTALACCHOURS
}
type NodeMetrics {
host: String!
host: String!
subCluster: String!
metrics: [JobMetricWithName!]!
metrics: [JobMetricWithName!]!
}
type NodesResultList {
items: [NodeMetrics!]!
items: [NodeMetrics!]!
offset: Int
limit: Int
count: Int
limit: Int
count: Int
totalNodes: Int
hasNextPage: Boolean
}
@@ -234,14 +277,14 @@ type GlobalMetricListItem {
}
type Count {
name: String!
name: String!
count: Int!
}
type User {
username: String!
name: String!
email: String!
name: String!
email: String!
}
input MetricStatItem {
@@ -250,26 +293,81 @@ input MetricStatItem {
}
type Query {
clusters: [Cluster!]! # List of all clusters
tags: [Tag!]! # List of all tags
globalMetrics: [GlobalMetricListItem!]!
clusters: [Cluster!]! # List of all clusters
tags: [Tag!]! # List of all tags
globalMetrics: [GlobalMetricListItem!]!
user(username: String!): User
allocatedNodes(cluster: String!): [Count!]!
node(id: ID!): Node
nodes(filter: [NodeFilter!], order: OrderByInput): NodeStateResultList!
nodeStats(filter: [NodeFilter!]): [NodeStats!]!
job(id: ID!): Job
jobMetrics(id: ID!, metrics: [String!], scopes: [MetricScope!], resolution: Int): [JobMetricWithName!]!
jobStats(id: ID!, metrics: [String!]): [JobStats!]!
scopedJobStats(id: ID!, metrics: [String!], scopes: [MetricScope!]): [JobStatsWithScope!]!
jobMetrics(
id: ID!
metrics: [String!]
scopes: [MetricScope!]
resolution: Int
): [JobMetricWithName!]!
jobStats(id: ID!, metrics: [String!]): [NamedStats!]!
scopedJobStats(
id: ID!
metrics: [String!]
scopes: [MetricScope!]
): [NamedStatsWithScope!]!
jobs(
filter: [JobFilter!]
page: PageRequest
order: OrderByInput
): JobResultList!
jobsStatistics(
filter: [JobFilter!]
metrics: [String!]
page: PageRequest
sortBy: SortByAggregate
groupBy: Aggregate
numDurationBins: String
numMetricBins: Int
): [JobsStatistics!]!
jobsMetricStats(filter: [JobFilter!], metrics: [String!]): [JobStats!]!
jobsFootprints(filter: [JobFilter!], metrics: [String!]!): Footprints
jobs(filter: [JobFilter!], page: PageRequest, order: OrderByInput): JobResultList!
jobsStatistics(filter: [JobFilter!], metrics: [String!], page: PageRequest, sortBy: SortByAggregate, groupBy: Aggregate, numDurationBins: String, numMetricBins: Int): [JobsStatistics!]!
rooflineHeatmap(
filter: [JobFilter!]!
rows: Int!
cols: Int!
minX: Float!
minY: Float!
maxX: Float!
maxY: Float!
): [[Float!]!]!
rooflineHeatmap(filter: [JobFilter!]!, rows: Int!, cols: Int!, minX: Float!, minY: Float!, maxX: Float!, maxY: Float!): [[Float!]!]!
nodeMetrics(cluster: String!, nodes: [String!], scopes: [MetricScope!], metrics: [String!], from: Time!, to: Time!): [NodeMetrics!]!
nodeMetricsList(cluster: String!, subCluster: String!, nodeFilter: String!, scopes: [MetricScope!], metrics: [String!], from: Time!, to: Time!, page: PageRequest, resolution: Int): NodesResultList!
nodeMetrics(
cluster: String!
nodes: [String!]
scopes: [MetricScope!]
metrics: [String!]
from: Time!
to: Time!
): [NodeMetrics!]!
nodeMetricsList(
cluster: String!
subCluster: String!
nodeFilter: String!
scopes: [MetricScope!]
metrics: [String!]
from: Time!
to: Time!
page: PageRequest
resolution: Int
): NodesResultList!
}
type Mutation {
@@ -282,37 +380,52 @@ type Mutation {
updateConfiguration(name: String!, value: String!): String
}
type IntRangeOutput { from: Int!, to: Int! }
type TimeRangeOutput { range: String, from: Time!, to: Time! }
type IntRangeOutput {
from: Int!
to: Int!
}
type TimeRangeOutput {
range: String
from: Time!
to: Time!
}
input NodeFilter {
hostname: StringInput
cluster: StringInput
nodeState: NodeState
healthState: MonitoringState
}
input JobFilter {
tags: [ID!]
jobId: StringInput
arrayJobId: Int
user: StringInput
project: StringInput
jobName: StringInput
cluster: StringInput
partition: StringInput
duration: IntRange
energy: FloatRange
tags: [ID!]
dbId: [ID!]
jobId: StringInput
arrayJobId: Int
user: StringInput
project: StringInput
jobName: StringInput
cluster: StringInput
partition: StringInput
duration: IntRange
energy: FloatRange
minRunningFor: Int
numNodes: IntRange
numNodes: IntRange
numAccelerators: IntRange
numHWThreads: IntRange
numHWThreads: IntRange
startTime: TimeRange
state: [JobState!]
startTime: TimeRange
state: [JobState!]
metricStats: [MetricStatItem!]
exclusive: Int
node: StringInput
exclusive: Int
node: StringInput
}
input OrderByInput {
field: String!
type: String!,
type: String!
order: SortDirectionEnum! = ASC
}
@@ -322,34 +435,46 @@ enum SortDirectionEnum {
}
input StringInput {
eq: String
neq: String
contains: String
eq: String
neq: String
contains: String
startsWith: String
endsWith: String
in: [String!]
endsWith: String
in: [String!]
}
input IntRange { from: Int!, to: Int! }
input TimeRange { range: String, from: Time, to: Time }
input IntRange {
from: Int!
to: Int!
}
input TimeRange {
range: String
from: Time
to: Time
}
input FloatRange {
from: Float!
to: Float!
}
type NodeStateResultList {
items: [Node!]!
count: Int
}
type JobResultList {
items: [Job!]!
items: [Job!]!
offset: Int
limit: Int
count: Int
limit: Int
count: Int
hasNextPage: Boolean
}
type JobLinkResultList {
listQuery: String
items: [JobLink!]!
count: Int
items: [JobLink!]!
count: Int
}
type HistoPoint {
@@ -371,27 +496,27 @@ type MetricHistoPoint {
max: Int
}
type JobsStatistics {
id: ID! # If `groupBy` was used, ID of the user/project/cluster
name: String! # if User-Statistics: Given Name of Account (ID) Owner
totalJobs: Int! # Number of jobs
runningJobs: Int! # Number of running jobs
shortJobs: Int! # Number of jobs with a duration of less than duration
totalWalltime: Int! # Sum of the duration of all matched jobs in hours
totalNodes: Int! # Sum of the nodes of all matched jobs
totalNodeHours: Int! # Sum of the node hours of all matched jobs
totalCores: Int! # Sum of the cores of all matched jobs
totalCoreHours: Int! # Sum of the core hours of all matched jobs
totalAccs: Int! # Sum of the accs of all matched jobs
totalAccHours: Int! # Sum of the gpu hours of all matched jobs
histDuration: [HistoPoint!]! # value: hour, count: number of jobs with a rounded duration of value
histNumNodes: [HistoPoint!]! # value: number of nodes, count: number of jobs with that number of nodes
histNumCores: [HistoPoint!]! # value: number of cores, count: number of jobs with that number of cores
histNumAccs: [HistoPoint!]! # value: number of accs, count: number of jobs with that number of accs
histMetrics: [MetricHistoPoints!]! # metric: metricname, data array of histopoints: value: metric average bin, count: number of jobs with that metric average
type JobsStatistics {
id: ID! # If `groupBy` was used, ID of the user/project/cluster
name: String! # if User-Statistics: Given Name of Account (ID) Owner
totalJobs: Int! # Number of jobs
runningJobs: Int! # Number of running jobs
shortJobs: Int! # Number of jobs with a duration of less than duration
totalWalltime: Int! # Sum of the duration of all matched jobs in hours
totalNodes: Int! # Sum of the nodes of all matched jobs
totalNodeHours: Int! # Sum of the node hours of all matched jobs
totalCores: Int! # Sum of the cores of all matched jobs
totalCoreHours: Int! # Sum of the core hours of all matched jobs
totalAccs: Int! # Sum of the accs of all matched jobs
totalAccHours: Int! # Sum of the gpu hours of all matched jobs
histDuration: [HistoPoint!]! # value: hour, count: number of jobs with a rounded duration of value
histNumNodes: [HistoPoint!]! # value: number of nodes, count: number of jobs with that number of nodes
histNumCores: [HistoPoint!]! # value: number of cores, count: number of jobs with that number of cores
histNumAccs: [HistoPoint!]! # value: number of accs, count: number of jobs with that number of accs
histMetrics: [MetricHistoPoints!]! # metric: metricname, data array of histopoints: value: metric average bin, count: number of jobs with that metric average
}
input PageRequest {
itemsPerPage: Int!
page: Int!
page: Int!
}

273
api/swagger.json
View File

@@ -201,7 +201,7 @@
"200": {
"description": "Success message",
"schema": {
"$ref": "#/definitions/api.DefaultJobApiResponse"
"$ref": "#/definitions/api.DefaultApiResponse"
}
},
"400": {
@@ -271,7 +271,7 @@
"200": {
"description": "Success message",
"schema": {
"$ref": "#/definitions/api.DefaultJobApiResponse"
"$ref": "#/definitions/api.DefaultApiResponse"
}
},
"400": {
@@ -341,7 +341,7 @@
"200": {
"description": "Success message",
"schema": {
"$ref": "#/definitions/api.DefaultJobApiResponse"
"$ref": "#/definitions/api.DefaultApiResponse"
}
},
"400": {
@@ -523,7 +523,7 @@
"ApiKeyAuth": []
}
],
"description": "Job specified in request body will be saved to database as \"running\" with new DB ID.\nJob specifications follow the 'JobMeta' scheme, API will fail to execute if requirements are not met.",
"description": "Job specified in request body will be saved to database as \"running\" with new DB ID.\nJob specifications follow the 'Job' scheme, API will fail to execute if requirements are not met.",
"consumes": [
"application/json"
],
@@ -541,7 +541,7 @@
"in": "body",
"required": true,
"schema": {
"$ref": "#/definitions/schema.JobMeta"
"$ref": "#/definitions/schema.Job"
}
}
],
@@ -549,7 +549,7 @@
"201": {
"description": "Job added successfully",
"schema": {
"$ref": "#/definitions/api.DefaultJobApiResponse"
"$ref": "#/definitions/api.DefaultApiResponse"
}
},
"400": {
@@ -592,7 +592,7 @@
"ApiKeyAuth": []
}
],
"description": "Job to stop is specified by request body. All fields are required in this case.\nReturns full job resource information according to 'JobMeta' scheme.",
"description": "Job to stop is specified by request body. All fields are required in this case.\nReturns full job resource information according to 'Job' scheme.",
"produces": [
"application/json"
],
@@ -615,7 +615,7 @@
"200": {
"description": "Success message",
"schema": {
"$ref": "#/definitions/schema.JobMeta"
"$ref": "#/definitions/schema.Job"
}
},
"400": {
@@ -737,7 +737,7 @@
"ApiKeyAuth": []
}
],
"description": "Job to get is specified by database ID\nReturns full job resource information according to 'JobMeta' scheme and all metrics according to 'JobData'.",
"description": "Job to get is specified by database ID\nReturns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.",
"produces": [
"application/json"
],
@@ -811,7 +811,7 @@
"ApiKeyAuth": []
}
],
"description": "Job to get is specified by database ID\nReturns full job resource information according to 'JobMeta' scheme and all metrics according to 'JobData'.",
"description": "Job to get is specified by database ID\nReturns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.",
"consumes": [
"application/json"
],
@@ -889,6 +889,66 @@
}
}
},
"/api/nodestats/": {
"post": {
"security": [
{
"ApiKeyAuth": []
}
],
"description": "Returns a JSON-encoded list of users.\nRequired query-parameter defines if all users or only users with additional special roles are returned.",
"produces": [
"application/json"
],
"tags": [
"Nodestates"
],
"summary": "Deliver updated Slurm node states",
"parameters": [
{
"description": "Request body containing nodes and their states",
"name": "request",
"in": "body",
"required": true,
"schema": {
"$ref": "#/definitions/api.UpdateNodeStatesRequest"
}
}
],
"responses": {
"200": {
"description": "Success message",
"schema": {
"$ref": "#/definitions/api.DefaultApiResponse"
}
},
"400": {
"description": "Bad Request",
"schema": {
"$ref": "#/definitions/api.ErrorResponse"
}
},
"401": {
"description": "Unauthorized",
"schema": {
"$ref": "#/definitions/api.ErrorResponse"
}
},
"403": {
"description": "Forbidden",
"schema": {
"$ref": "#/definitions/api.ErrorResponse"
}
},
"500": {
"description": "Internal Server Error",
"schema": {
"$ref": "#/definitions/api.ErrorResponse"
}
}
}
}
},
"/api/users/": {
"get": {
"security": [
@@ -1137,7 +1197,7 @@
}
}
},
"api.DefaultJobApiResponse": {
"api.DefaultApiResponse": {
"type": "object",
"properties": {
"msg": {
@@ -1231,7 +1291,7 @@
"description": "Array of jobs",
"type": "array",
"items": {
"$ref": "#/definitions/schema.JobMeta"
"$ref": "#/definitions/schema.Job"
}
},
"page": {
@@ -1285,6 +1345,20 @@
}
}
},
"api.Node": {
"type": "object",
"properties": {
"hostname": {
"type": "string"
},
"states": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"api.StopJobApiRequest": {
"type": "object",
"required": [
@@ -1318,6 +1392,21 @@
}
}
},
"api.UpdateNodeStatesRequest": {
"type": "object",
"properties": {
"cluster": {
"type": "string",
"example": "fritz"
},
"nodes": {
"type": "array",
"items": {
"$ref": "#/definitions/api.Node"
}
}
}
},
"schema.Accelerator": {
"type": "object",
"properties": {
@@ -1353,7 +1442,6 @@
}
},
"schema.Job": {
"description": "Information of a HPC job.",
"type": "object",
"properties": {
"arrayJobId": {
@@ -1451,6 +1539,12 @@
"type": "string",
"example": "abcd200"
},
"requestedMemory": {
"description": "in MB",
"type": "integer",
"minimum": 1,
"example": 128000
},
"resources": {
"type": "array",
"items": {
@@ -1462,7 +1556,14 @@
"example": 4
},
"startTime": {
"type": "string"
"type": "integer",
"example": 1649723812
},
"statistics": {
"type": "object",
"additionalProperties": {
"$ref": "#/definitions/schema.JobStatistics"
}
},
"subCluster": {
"type": "string",
@@ -1510,147 +1611,6 @@
}
}
},
"schema.JobMeta": {
"description": "Meta data information of a HPC job.",
"type": "object",
"properties": {
"arrayJobId": {
"type": "integer",
"example": 123000
},
"cluster": {
"type": "string",
"example": "fritz"
},
"concurrentJobs": {
"$ref": "#/definitions/schema.JobLinkResultList"
},
"duration": {
"type": "integer",
"minimum": 1,
"example": 43200
},
"energy": {
"type": "number"
},
"energyFootprint": {
"type": "object",
"additionalProperties": {
"type": "number"
}
},
"exclusive": {
"type": "integer",
"maximum": 2,
"minimum": 0,
"example": 1
},
"footprint": {
"type": "object",
"additionalProperties": {
"type": "number"
}
},
"id": {
"type": "integer"
},
"jobId": {
"type": "integer",
"example": 123000
},
"jobState": {
"enum": [
"completed",
"failed",
"cancelled",
"stopped",
"timeout",
"out_of_memory"
],
"allOf": [
{
"$ref": "#/definitions/schema.JobState"
}
],
"example": "completed"
},
"metaData": {
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"monitoringStatus": {
"type": "integer",
"maximum": 3,
"minimum": 0,
"example": 1
},
"numAcc": {
"type": "integer",
"minimum": 1,
"example": 2
},
"numHwthreads": {
"type": "integer",
"minimum": 1,
"example": 20
},
"numNodes": {
"type": "integer",
"minimum": 1,
"example": 2
},
"partition": {
"type": "string",
"example": "main"
},
"project": {
"type": "string",
"example": "abcd200"
},
"resources": {
"type": "array",
"items": {
"$ref": "#/definitions/schema.Resource"
}
},
"smt": {
"type": "integer",
"example": 4
},
"startTime": {
"type": "integer",
"minimum": 1,
"example": 1649723812
},
"statistics": {
"type": "object",
"additionalProperties": {
"$ref": "#/definitions/schema.JobStatistics"
}
},
"subCluster": {
"type": "string",
"example": "main"
},
"tags": {
"type": "array",
"items": {
"$ref": "#/definitions/schema.Tag"
}
},
"user": {
"type": "string",
"example": "abcd100h"
},
"walltime": {
"type": "integer",
"minimum": 1,
"example": 86400
}
}
},
"schema.JobMetric": {
"type": "object",
"properties": {
@@ -1978,6 +1938,9 @@
},
"remove": {
"type": "boolean"
},
"unit": {
"$ref": "#/definitions/schema.Unit"
}
}
},

201
api/swagger.yaml
View File

@@ -31,7 +31,7 @@ definitions:
example: Debug
type: string
type: object
api.DefaultJobApiResponse:
api.DefaultApiResponse:
properties:
msg:
type: string
@@ -96,7 +96,7 @@ definitions:
jobs:
description: Array of jobs
items:
$ref: '#/definitions/schema.JobMeta'
$ref: '#/definitions/schema.Job'
type: array
page:
description: Page id returned
@@ -132,6 +132,15 @@ definitions:
scope:
$ref: '#/definitions/schema.MetricScope'
type: object
api.Node:
properties:
hostname:
type: string
states:
items:
type: string
type: array
type: object
api.StopJobApiRequest:
properties:
cluster:
@@ -154,6 +163,16 @@ definitions:
- jobState
- stopTime
type: object
api.UpdateNodeStatesRequest:
properties:
cluster:
example: fritz
type: string
nodes:
items:
$ref: '#/definitions/api.Node'
type: array
type: object
schema.Accelerator:
properties:
id:
@@ -177,7 +196,6 @@ definitions:
type: array
type: object
schema.Job:
description: Information of a HPC job.
properties:
arrayJobId:
example: 123000
@@ -249,6 +267,11 @@ definitions:
project:
example: abcd200
type: string
requestedMemory:
description: in MB
example: 128000
minimum: 1
type: integer
resources:
items:
$ref: '#/definitions/schema.Resource'
@@ -257,7 +280,12 @@ definitions:
example: 4
type: integer
startTime:
type: string
example: 1649723812
type: integer
statistics:
additionalProperties:
$ref: '#/definitions/schema.JobStatistics'
type: object
subCluster:
example: main
type: string
@@ -289,109 +317,6 @@ definitions:
$ref: '#/definitions/schema.JobLink'
type: array
type: object
schema.JobMeta:
description: Meta data information of a HPC job.
properties:
arrayJobId:
example: 123000
type: integer
cluster:
example: fritz
type: string
concurrentJobs:
$ref: '#/definitions/schema.JobLinkResultList'
duration:
example: 43200
minimum: 1
type: integer
energy:
type: number
energyFootprint:
additionalProperties:
type: number
type: object
exclusive:
example: 1
maximum: 2
minimum: 0
type: integer
footprint:
additionalProperties:
type: number
type: object
id:
type: integer
jobId:
example: 123000
type: integer
jobState:
allOf:
- $ref: '#/definitions/schema.JobState'
enum:
- completed
- failed
- cancelled
- stopped
- timeout
- out_of_memory
example: completed
metaData:
additionalProperties:
type: string
type: object
monitoringStatus:
example: 1
maximum: 3
minimum: 0
type: integer
numAcc:
example: 2
minimum: 1
type: integer
numHwthreads:
example: 20
minimum: 1
type: integer
numNodes:
example: 2
minimum: 1
type: integer
partition:
example: main
type: string
project:
example: abcd200
type: string
resources:
items:
$ref: '#/definitions/schema.Resource'
type: array
smt:
example: 4
type: integer
startTime:
example: 1649723812
minimum: 1
type: integer
statistics:
additionalProperties:
$ref: '#/definitions/schema.JobStatistics'
type: object
subCluster:
example: main
type: string
tags:
items:
$ref: '#/definitions/schema.Tag'
type: array
user:
example: abcd100h
type: string
walltime:
example: 86400
minimum: 1
type: integer
type: object
schema.JobMetric:
properties:
series:
@@ -620,6 +545,8 @@ definitions:
type: number
remove:
type: boolean
unit:
$ref: '#/definitions/schema.Unit'
type: object
schema.Tag:
description: Defines a tag using name and type.
@@ -797,7 +724,7 @@ paths:
get:
description: |-
Job to get is specified by database ID
Returns full job resource information according to 'JobMeta' scheme and all metrics according to 'JobData'.
Returns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.
parameters:
- description: Database ID of Job
in: path
@@ -850,7 +777,7 @@ paths:
- application/json
description: |-
Job to get is specified by database ID
Returns full job resource information according to 'JobMeta' scheme and all metrics according to 'JobData'.
Returns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.
parameters:
- description: Database ID of Job
in: path
@@ -921,7 +848,7 @@ paths:
"200":
description: Success message
schema:
$ref: '#/definitions/api.DefaultJobApiResponse'
$ref: '#/definitions/api.DefaultApiResponse'
"400":
description: Bad Request
schema:
@@ -968,7 +895,7 @@ paths:
"200":
description: Success message
schema:
$ref: '#/definitions/api.DefaultJobApiResponse'
$ref: '#/definitions/api.DefaultApiResponse'
"400":
description: Bad Request
schema:
@@ -1015,7 +942,7 @@ paths:
"200":
description: Success message
schema:
$ref: '#/definitions/api.DefaultJobApiResponse'
$ref: '#/definitions/api.DefaultApiResponse'
"400":
description: Bad Request
schema:
@@ -1141,21 +1068,21 @@ paths:
- application/json
description: |-
Job specified in request body will be saved to database as "running" with new DB ID.
Job specifications follow the 'JobMeta' scheme, API will fail to execute if requirements are not met.
Job specifications follow the 'Job' scheme, API will fail to execute if requirements are not met.
parameters:
- description: Job to add
in: body
name: request
required: true
schema:
$ref: '#/definitions/schema.JobMeta'
$ref: '#/definitions/schema.Job'
produces:
- application/json
responses:
"201":
description: Job added successfully
schema:
$ref: '#/definitions/api.DefaultJobApiResponse'
$ref: '#/definitions/api.DefaultApiResponse'
"400":
description: Bad Request
schema:
@@ -1186,7 +1113,7 @@ paths:
post:
description: |-
Job to stop is specified by request body. All fields are required in this case.
Returns full job resource information according to 'JobMeta' scheme.
Returns full job resource information according to 'Job' scheme.
parameters:
- description: All fields required
in: body
@@ -1200,7 +1127,7 @@ paths:
"200":
description: Success message
schema:
$ref: '#/definitions/schema.JobMeta'
$ref: '#/definitions/schema.Job'
"400":
description: Bad Request
schema:
@@ -1280,6 +1207,46 @@ paths:
summary: Adds one or more tags to a job
tags:
- Job add and modify
/api/nodestats/:
post:
description: |-
Returns a JSON-encoded list of users.
Required query-parameter defines if all users or only users with additional special roles are returned.
parameters:
- description: Request body containing nodes and their states
in: body
name: request
required: true
schema:
$ref: '#/definitions/api.UpdateNodeStatesRequest'
produces:
- application/json
responses:
"200":
description: Success message
schema:
$ref: '#/definitions/api.DefaultApiResponse'
"400":
description: Bad Request
schema:
$ref: '#/definitions/api.ErrorResponse'
"401":
description: Unauthorized
schema:
$ref: '#/definitions/api.ErrorResponse'
"403":
description: Forbidden
schema:
$ref: '#/definitions/api.ErrorResponse'
"500":
description: Internal Server Error
schema:
$ref: '#/definitions/api.ErrorResponse'
security:
- ApiKeyAuth: []
summary: Deliver updated Slurm node states
tags:
- Nodestates
/api/users/:
get:
description: |-