ClusterCockpit/cc-backend
1
0
Fork 0
mirror of https://github.com/ClusterCockpit/cc-backend synced 2024-12-24 04:29:04 +01:00
Code Issues Packages Releases Activity

Merge branch 'fix-import-flag' into update-web-frontend-env

Browse Source
This commit is contained in:
Jan Eitzinger 2023-05-04 09:20:16 +02:00
commit 4ae763ee1b
9 changed files with 40 additions and 485 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

410
test/integration_test.go → internal/api/api_test.go
View File

@ -2,7 +2,7 @@
// All rights reserved.
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.
package test
package api_test
import (
"bytes"
@ -48,16 +48,7 @@ func setup(t *testing.T) *api.RestApi {
"duration": { "from": 0, "to": 86400 },
"startTime": { "from": "2022-01-01T00:00:00Z", "to": null }
}
},
{
"name": "taurus",
"metricDataRepository": {"kind": "test", "url": "bla:8081"},
"filterRanges": {
"numNodes": { "from": 1, "to": 4000 },
"duration": { "from": 0, "to": 604800 },
"startTime": { "from": "2010-01-01T00:00:00Z", "to": null }
}
}
}
]
}`
const testclusterJson = `{
@ -115,215 +106,6 @@ func setup(t *testing.T) *api.RestApi {
}
]
}`
const taurusclusterJson = `{
"name": "taurus",
"subClusters": [
{
"name": "haswell",
"processorType": "Intel Haswell",
"socketsPerNode": 2,
"coresPerSocket": 12,
"threadsPerCore": 1,
"flopRateScalar": {
"unit": {
"prefix": "G",
"base": "F/s"
},
"value": 14
},
"flopRateSimd": {
"unit": {
"prefix": "G",
"base": "F/s"
},
"value": 112
},
"memoryBandwidth": {
"unit": {
"prefix": "G",
"base": "B/s"
},
"value": 24
},
"numberOfNodes": 70,
"nodes": "w11[27-45,49-63,69-72]",
"topology": {
"node": [ 0, 1 ],
"socket": [
[ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ],
[ 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23 ]
],
"memoryDomain": [
[ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ],
[ 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23 ]
],
"core": [ [ 0 ], [ 1 ], [ 2 ], [ 3 ], [ 4 ], [ 5 ], [ 6 ], [ 7 ], [ 8 ], [ 9 ], [ 10 ], [ 11 ], [ 12 ], [ 13 ], [ 14 ], [ 15 ], [ 16 ], [ 17 ], [ 18 ], [ 19 ], [ 20 ], [ 21 ], [ 22 ], [ 23 ] ]
}
}
],
"metricConfig": [
{
"name": "cpu_used",
"scope": "core",
"unit": {"base": ""},
"aggregation": "avg",
"timestep": 30,
"peak": 1,
"normal": 0.5,
"caution": 2e-07,
"alert": 1e-07,
"subClusters": [
{
"name": "haswell",
"peak": 1,
"normal": 0.5,
"caution": 2e-07,
"alert": 1e-07
}
]
},
{
"name": "ipc",
"scope": "core",
"unit": { "base": "IPC"},
"aggregation": "avg",
"timestep": 60,
"peak": 2,
"normal": 1,
"caution": 0.1,
"alert": 0.5,
"subClusters": [
{
"name": "haswell",
"peak": 2,
"normal": 1,
"caution": 0.1,
"alert": 0.5
}
]
},
{
"name": "flops_any",
"scope": "core",
"unit": { "base": "F/s"},
"aggregation": "sum",
"timestep": 60,
"peak": 40000000000,
"normal": 20000000000,
"caution": 30000000000,
"alert": 35000000000,
"subClusters": [
{
"name": "haswell",
"peak": 40000000000,
"normal": 20000000000,
"caution": 30000000000,
"alert": 35000000000
}
]
},
{
"name": "mem_bw",
"scope": "socket",
"unit": { "base": "B/s"},
"aggregation": "sum",
"timestep": 60,
"peak": 58800000000,
"normal": 28800000000,
"caution": 38800000000,
"alert": 48800000000,
"subClusters": [
{
"name": "haswell",
"peak": 58800000000,
"normal": 28800000000,
"caution": 38800000000,
"alert": 48800000000
}
]
},
{
"name": "file_bw",
"scope": "node",
"unit": { "base": "B/s"},
"aggregation": "sum",
"timestep": 30,
"peak": 20000000000,
"normal": 5000000000,
"caution": 9000000000,
"alert": 19000000000,
"subClusters": [
{
"name": "haswell",
"peak": 20000000000,
"normal": 5000000000,
"caution": 9000000000,
"alert": 19000000000
}
]
},
{
"name": "net_bw",
"scope": "node",
"unit": { "base": "B/s"},
"timestep": 30,
"aggregation": "sum",
"peak": 7000000000,
"normal": 5000000000,
"caution": 6000000000,
"alert": 6500000000,
"subClusters": [
{
"name": "haswell",
"peak": 7000000000,
"normal": 5000000000,
"caution": 6000000000,
"alert": 6500000000
}
]
},
{
"name": "mem_used",
"scope": "node",
"unit": {"base": "B"},
"aggregation": "sum",
"timestep": 30,
"peak": 32000000000,
"normal": 2000000000,
"caution": 31000000000,
"alert": 30000000000,
"subClusters": [
{
"name": "haswell",
"peak": 32000000000,
"normal": 2000000000,
"caution": 31000000000,
"alert": 30000000000
}
]
},
{
"name": "cpu_power",
"scope": "socket",
"unit": {"base": "W"},
"aggregation": "sum",
"timestep": 60,
"peak": 100,
"normal": 80,
"caution": 90,
"alert": 90,
"subClusters": [
{
"name": "haswell",
"peak": 100,
"normal": 80,
"caution": 90,
"alert": 90
}
]
}
]
}`
log.Init("info", true)
tmpdir := t.TempDir()
@ -344,13 +126,6 @@ func setup(t *testing.T) *api.RestApi {
t.Fatal(err)
}
if err := os.Mkdir(filepath.Join(jobarchive, "taurus"), 0777); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(jobarchive, "taurus", "cluster.json"), []byte(taurusclusterJson), 0666); err != nil {
t.Fatal(err)
}
dbfilepath := filepath.Join(tmpdir, "test.db")
err := repository.MigrateDB("sqlite3", dbfilepath)
if err != nil {
@ -392,7 +167,7 @@ func cleanup() {
/*
* This function starts a job, stops it, and then reads its data from the job-archive.
* Do not run sub-tests in parallel! Tests should not be run in parallel at all, because
* at least `setup` modifies global state. Log-Output is redirected to /dev/null on purpose.
* at least `setup` modifies global state.
*/
func TestRestApi(t *testing.T) {
restapi := setup(t)
@ -477,15 +252,15 @@ func TestRestApi(t *testing.T) {
job.Project != "testproj" ||
job.Cluster != "testcluster" ||
job.SubCluster != "sc1" ||
*job.Partition != "default" ||
*job.Walltime != 3600 ||
*job.ArrayJobId != 0 ||
job.Partition != "default" ||
job.Walltime != 3600 ||
job.ArrayJobId != 0 ||
job.NumNodes != 1 ||
*job.NumHWThreads != 8 ||
*job.NumAcc != 0 ||
job.NumHWThreads != 8 ||
job.NumAcc != 0 ||
job.Exclusive != 1 ||
job.MonitoringStatus != 1 ||
*job.SMT != 1 ||
job.SMT != 1 ||
!reflect.DeepEqual(job.Resources, []*schema.Resource{{Hostname: "host123", HWThreads: []int{0, 1, 2, 3, 4, 5, 6, 7}}}) ||
job.StartTime.Unix() != 123456789 {
t.Fatalf("unexpected job properties: %#v", job)
@ -573,8 +348,7 @@ func TestRestApi(t *testing.T) {
}
})
t.Run("FailedJob", func(t *testing.T) {
const startJobBody string = `{
const startJobBodyFailed string = `{
"jobId": 12345,
"user": "testuser",
"project": "testproj",
@ -593,120 +367,8 @@ func TestRestApi(t *testing.T) {
"startTime": 12345678
}`
ok := t.Run("StartJob", func(t *testing.T) {
req := httptest.NewRequest(http.MethodPost, "/api/jobs/start_job/", bytes.NewBuffer([]byte(startJobBody)))
recorder := httptest.NewRecorder()
r.ServeHTTP(recorder, req)
response := recorder.Result()
if response.StatusCode != http.StatusCreated {
t.Fatal(response.Status, recorder.Body.String())
}
})
if !ok {
t.Fatal("subtest failed")
}
const stopJobBody string = `{
"jobId": 12345,
"cluster": "testcluster",
"jobState": "failed",
"stopTime": 12355678
}`
ok = t.Run("StopJob", func(t *testing.T) {
req := httptest.NewRequest(http.MethodPost, "/api/jobs/stop_job/", bytes.NewBuffer([]byte(stopJobBody)))
recorder := httptest.NewRecorder()
r.ServeHTTP(recorder, req)
response := recorder.Result()
if response.StatusCode != http.StatusOK {
t.Fatal(response.Status, recorder.Body.String())
}
restapi.JobRepository.WaitForArchiving()
jobid, cluster := int64(12345), "testcluster"
job, err := restapi.JobRepository.Find(&jobid, &cluster, nil)
if err != nil {
t.Fatal(err)
}
if job.State != schema.JobStateFailed {
t.Fatal("expected job to be failed")
}
})
if !ok {
t.Fatal("subtest failed")
}
})
t.Run("ImportJob", func(t *testing.T) {
if err := repository.HandleImportFlag("meta.json:data.json"); err != nil {
t.Fatal(err)
}
repo := repository.GetJobRepository()
jobId := int64(20639587)
cluster := "taurus"
startTime := int64(1635856524)
job, err := repo.Find(&jobId, &cluster, &startTime)
if err != nil {
t.Fatal(err)
}
if job.NumNodes != 2 {
t.Errorf("NumNode: Received %d, expected 2", job.NumNodes)
}
ar := archive.GetHandle()
data, err := ar.LoadJobData(job)
if err != nil {
t.Fatal(err)
}
if len(data) != 8 {
t.Errorf("Job data length: Got %d, want 8", len(data))
}
r := map[string]string{"mem_used": "GB", "net_bw": "KB/s",
"cpu_power": "W", "cpu_used": "",
"file_bw": "KB/s", "flops_any": "F/s",
"mem_bw": "GB/s", "ipc": "IPC"}
for name, scopes := range data {
for _, metric := range scopes {
if metric.Unit.Base != r[name] {
t.Errorf("Metric %s unit: Got %s, want %s", name, metric.Unit.Base, r[name])
}
}
}
})
}
func subtestLetJobFail(t *testing.T, restapi *api.RestApi, r *mux.Router) {
const startJobBody string = `{
"jobId": 12345,
"user": "testuser",
"project": "testproj",
"cluster": "testcluster",
"partition": "default",
"walltime": 3600,
"numNodes": 1,
"exclusive": 1,
"monitoringStatus": 1,
"smt": 1,
"resources": [
{
"hostname": "host123"
}
],
"startTime": 12345678
}`
ok := t.Run("StartJob", func(t *testing.T) {
req := httptest.NewRequest(http.MethodPost, "/api/jobs/start_job/", bytes.NewBuffer([]byte(startJobBody)))
ok := t.Run("StartJobFailed", func(t *testing.T) {
req := httptest.NewRequest(http.MethodPost, "/api/jobs/start_job/", bytes.NewBuffer([]byte(startJobBodyFailed)))
recorder := httptest.NewRecorder()
r.ServeHTTP(recorder, req)
@ -719,7 +381,7 @@ func subtestLetJobFail(t *testing.T, restapi *api.RestApi, r *mux.Router) {
t.Fatal("subtest failed")
}
const stopJobBody string = `{
const stopJobBodyFailed string = `{
"jobId": 12345,
"cluster": "testcluster",
@ -727,8 +389,8 @@ func subtestLetJobFail(t *testing.T, restapi *api.RestApi, r *mux.Router) {
"stopTime": 12355678
}`
ok = t.Run("StopJob", func(t *testing.T) {
req := httptest.NewRequest(http.MethodPost, "/api/jobs/stop_job/", bytes.NewBuffer([]byte(stopJobBody)))
ok = t.Run("StopJobFailed", func(t *testing.T) {
req := httptest.NewRequest(http.MethodPost, "/api/jobs/stop_job/", bytes.NewBuffer([]byte(stopJobBodyFailed)))
recorder := httptest.NewRecorder()
r.ServeHTTP(recorder, req)
@ -752,45 +414,3 @@ func subtestLetJobFail(t *testing.T, restapi *api.RestApi, r *mux.Router) {
t.Fatal("subtest failed")
}
}
func testImportFlag(t *testing.T) {
if err := repository.HandleImportFlag("meta.json:data.json"); err != nil {
t.Fatal(err)
}
repo := repository.GetJobRepository()
jobId := int64(20639587)
cluster := "taurus"
startTime := int64(1635856524)
job, err := repo.Find(&jobId, &cluster, &startTime)
if err != nil {
t.Fatal(err)
}
if job.NumNodes != 2 {
t.Errorf("NumNode: Received %d, expected 2", job.NumNodes)
}
ar := archive.GetHandle()
data, err := ar.LoadJobData(job)
if err != nil {
t.Fatal(err)
}
if len(data) != 8 {
t.Errorf("Job data length: Got %d, want 8", len(data))
}
r := map[string]string{"mem_used": "GB", "net_bw": "KB/s",
"cpu_power": "W", "cpu_used": "",
"file_bw": "KB/s", "flops_any": "F/s",
"mem_bw": "GB/s", "ipc": "IPC"}
for name, scopes := range data {
for _, metric := range scopes {
if metric.Unit.Base != r[name] {
t.Errorf("Metric %s unit: Got %s, want %s", name, metric.Unit.Base, r[name])
}
}
}
}

2
internal/api/rest.go
View File

@ -253,7 +253,7 @@ func (api *RestApi) getJobs(rw http.ResponseWriter, r *http.Request) {
results := make([]*schema.JobMeta, 0, len(jobs))
for _, job := range jobs {
if withMetadata {
if _, err := api.JobRepository.FetchMetadata(job); err != nil {
if _, err = api.JobRepository.FetchMetadata(job); err != nil {
handleError(err, http.StatusInternalServerError, rw)
return
}

16
internal/importer/handleImport.go
View File

@ -37,14 +37,14 @@ func HandleImportFlag(flag string) error {
}
if config.Keys.Validate {
if err := schema.Validate(schema.Meta, bytes.NewReader(raw)); err != nil {
if err = schema.Validate(schema.Meta, bytes.NewReader(raw)); err != nil {
return fmt.Errorf("REPOSITORY/INIT > validate job meta: %v", err)
}
}
dec := json.NewDecoder(bytes.NewReader(raw))
dec.DisallowUnknownFields()
jobMeta := schema.JobMeta{BaseJob: schema.JobDefaults}
if err := dec.Decode(&jobMeta); err != nil {
if err = dec.Decode(&jobMeta); err != nil {
log.Warn("Error while decoding raw json metadata for import")
return err
}
@ -56,14 +56,14 @@ func HandleImportFlag(flag string) error {
}
if config.Keys.Validate {
if err := schema.Validate(schema.Data, bytes.NewReader(raw)); err != nil {
if err = schema.Validate(schema.Data, bytes.NewReader(raw)); err != nil {
return fmt.Errorf("REPOSITORY/INIT > validate job data: %v", err)
}
}
dec = json.NewDecoder(bytes.NewReader(raw))
dec.DisallowUnknownFields()
jobData := schema.JobData{}
if err := dec.Decode(&jobData); err != nil {
if err = dec.Decode(&jobData); err != nil {
log.Warn("Error while decoding raw json jobdata for import")
return err
}
@ -71,13 +71,13 @@ func HandleImportFlag(flag string) error {
//checkJobData(&jobData)
// SanityChecks(&jobMeta.BaseJob)
jobMeta.MonitoringStatus = schema.MonitoringStatusArchivingSuccessful
if job, err := r.Find(&jobMeta.JobID, &jobMeta.Cluster, &jobMeta.StartTime); err != sql.ErrNoRows {
if _, err = r.Find(&jobMeta.JobID, &jobMeta.Cluster, &jobMeta.StartTime); err != sql.ErrNoRows {
if err != nil {
log.Warn("Error while finding job in jobRepository")
return err
}
return fmt.Errorf("REPOSITORY/INIT > a job with that jobId, cluster and startTime does already exist (dbid: %d)", job.ID)
return fmt.Errorf("REPOSITORY/INIT > a job with that jobId, cluster and startTime does already exist")
}
job := schema.Job{
@ -102,12 +102,12 @@ func HandleImportFlag(flag string) error {
return err
}
if err := SanityChecks(&job.BaseJob); err != nil {
if err = SanityChecks(&job.BaseJob); err != nil {
log.Warn("BaseJob SanityChecks failed")
return err
}
if err := archive.GetHandle().ImportJob(&jobMeta, &jobData); err != nil {
if err = archive.GetHandle().ImportJob(&jobMeta, &jobData); err != nil {
log.Error("Error while importing job")
return err
}

5
internal/importer/importer_test.go
View File

@ -34,7 +34,7 @@ func copyFile(s string, d string) error {
return nil
}
func setupRepo(t *testing.T) *repository.JobRepository {
func setup(t *testing.T) *repository.JobRepository {
const testconfig = `{
"addr": "0.0.0.0:8080",
"validate": false,
@ -138,7 +138,7 @@ func readResult(t *testing.T, testname string) Result {
}
func TestHandleImportFlag(t *testing.T) {
r := setupRepo(t)
r := setup(t)
tests, err := filepath.Glob(filepath.Join("testdata", "*.input"))
if err != nil {
@ -167,7 +167,6 @@ func TestHandleImportFlag(t *testing.T) {
if job.Duration != result.Duration {
t.Errorf("wrong duration for job\ngot: %d \nwant: %d", job.Duration, result.Duration)
}
})
}
}

2
internal/importer/initDB.go
View File

@ -136,7 +136,7 @@ func SanityChecks(job *schema.BaseJob) error {
if len(job.Resources) == 0 || len(job.User) == 0 {
return fmt.Errorf("'resources' and 'user' should not be empty")
}
if *job.NumAcc < 0 || *job.NumHWThreads < 0 || job.NumNodes < 1 {
if job.NumAcc < 0 || job.NumHWThreads < 0 || job.NumNodes < 1 {
return fmt.Errorf("'numNodes', 'numAcc' or 'numHWThreads' invalid")
}
if len(job.Resources) != int(job.NumNodes) {

2
internal/metricdata/cc-metric-store.go
View File

@ -293,7 +293,7 @@ func (ccms *CCMetricStore) buildQueries(
scopesLoop:
for _, requestedScope := range scopes {
nativeScope := mc.Scope
if nativeScope == schema.MetricScopeAccelerator && job.NumAcc == nil {
if nativeScope == schema.MetricScopeAccelerator && job.NumAcc == 0 {
continue
}

64
internal/repository/init_test.go
View File

@ -1,64 +0,0 @@
// Copyright (C) 2022 NHR@FAU, University Erlangen-Nuremberg.
// All rights reserved.
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.
package repository
import (
"fmt"
"testing"
"github.com/ClusterCockpit/cc-backend/pkg/units"
)
func TestNormalizeFactor(t *testing.T) {
// var us string
s := []float64{2890031237, 23998994567, 389734042344, 390349424345}
// r := []float64{3, 24, 390, 391}
total := 0.0
for _, number := range s {
total += number
}
avg := total / float64(len(s))
fmt.Printf("AVG: %e\n", avg)
f, e := getNormalizationFactor(avg)
fmt.Printf("Factor %e Count %d\n", f, e)
np := units.NewPrefix("")
fmt.Printf("Prefix %e Short %s\n", float64(np), np.Prefix())
p := units.NewPrefixFromFactor(np, e)
if p.Prefix() != "G" {
t.Errorf("Failed Prefix or unit: Want G, Got %s", p.Prefix())
}
}
func TestNormalizeKeep(t *testing.T) {
s := []float64{3.0, 24.0, 390.0, 391.0}
total := 0.0
for _, number := range s {
total += number
}
avg := total / float64(len(s))
fmt.Printf("AVG: %e\n", avg)
f, e := getNormalizationFactor(avg)
fmt.Printf("Factor %e Count %d\n", f, e)
np := units.NewPrefix("G")
fmt.Printf("Prefix %e Short %s\n", float64(np), np.Prefix())
p := units.NewPrefixFromFactor(np, e)
if p.Prefix() != "G" {
t.Errorf("Failed Prefix or unit: Want G, Got %s", p.Prefix())
}
}

12
pkg/schema/job.go
View File

@ -22,17 +22,17 @@ type BaseJob struct {
Project string `json:"project" db:"project" example:"abcd200"` // The unique identifier of a project
Cluster string `json:"cluster" db:"cluster" example:"fritz"` // The unique identifier of a cluster
SubCluster string `json:"subCluster" db:"subcluster" example:"main"` // The unique identifier of a sub cluster
Partition *string `json:"partition,omitempty" db:"partition" example:"main"` // The Slurm partition to which the job was submitted
ArrayJobId *int64 `json:"arrayJobId,omitempty" db:"array_job_id" example:"123000"` // The unique identifier of an array job
Partition string `json:"partition,omitempty" db:"partition" example:"main"` // The Slurm partition to which the job was submitted
ArrayJobId int64 `json:"arrayJobId,omitempty" db:"array_job_id" example:"123000"` // The unique identifier of an array job
NumNodes int32 `json:"numNodes" db:"num_nodes" example:"2" minimum:"1"` // Number of nodes used (Min > 0)
NumHWThreads *int32 `json:"numHwthreads,omitempty" db:"num_hwthreads" example:"20" minimum:"1"` // Number of HWThreads used (Min > 0)
NumAcc *int32 `json:"numAcc,omitempty" db:"num_acc" example:"2" minimum:"1"` // Number of accelerators used (Min > 0)
NumHWThreads int32 `json:"numHwthreads,omitempty" db:"num_hwthreads" example:"20" minimum:"1"` // Number of HWThreads used (Min > 0)
NumAcc int32 `json:"numAcc,omitempty" db:"num_acc" example:"2" minimum:"1"` // Number of accelerators used (Min > 0)
Exclusive int32 `json:"exclusive" db:"exclusive" example:"1" minimum:"0" maximum:"2"` // Specifies how nodes are shared: 0 - Shared among multiple jobs of multiple users, 1 - Job exclusive (Default), 2 - Shared among multiple jobs of same user
MonitoringStatus int32 `json:"monitoringStatus,omitempty" db:"monitoring_status" example:"1" minimum:"0" maximum:"3"` // State of monitoring system during job run: 0 - Disabled, 1 - Running or Archiving (Default), 2 - Archiving Failed, 3 - Archiving Successfull
SMT *int32 `json:"smt,omitempty" db:"smt" example:"4"` // SMT threads used by job
SMT int32 `json:"smt,omitempty" db:"smt" example:"4"` // SMT threads used by job
State JobState `json:"jobState" db:"job_state" example:"completed" enums:"completed,failed,cancelled,stopped,timeout,out_of_memory"` // Final state of job
Duration int32 `json:"duration" db:"duration" example:"43200" minimum:"1"` // Duration of job in seconds (Min > 0)
Walltime *int64 `json:"walltime,omitempty" db:"walltime" example:"86400" minimum:"1"` // Requested walltime of job in seconds (Min > 0)
Walltime int64 `json:"walltime,omitempty" db:"walltime" example:"86400" minimum:"1"` // Requested walltime of job in seconds (Min > 0)
Tags []*Tag `json:"tags,omitempty"` // List of tags
RawResources []byte `json:"-" db:"resources"` // Resources used by job [As Bytes]
Resources []*Resource `json:"resources"` // Resources used by job

12
tools/archive-migration/job.go
View File

@ -23,17 +23,17 @@ type BaseJob struct {
Project string `json:"project" db:"project" example:"abcd200"` // The unique identifier of a project
Cluster string `json:"cluster" db:"cluster" example:"fritz"` // The unique identifier of a cluster
SubCluster string `json:"subCluster" db:"subcluster" example:"main"` // The unique identifier of a sub cluster
Partition *string `json:"partition" db:"partition" example:"main"` // The Slurm partition to which the job was submitted
ArrayJobId *int64 `json:"arrayJobId" db:"array_job_id" example:"123000"` // The unique identifier of an array job
Partition string `json:"partition" db:"partition" example:"main"` // The Slurm partition to which the job was submitted
ArrayJobId int64 `json:"arrayJobId" db:"array_job_id" example:"123000"` // The unique identifier of an array job
NumNodes int32 `json:"numNodes" db:"num_nodes" example:"2" minimum:"1"` // Number of nodes used (Min > 0)
NumHWThreads *int32 `json:"numHwthreads" db:"num_hwthreads" example:"20" minimum:"1"` // Number of HWThreads used (Min > 0)
NumAcc *int32 `json:"numAcc" db:"num_acc" example:"2" minimum:"1"` // Number of accelerators used (Min > 0)
NumHWThreads int32 `json:"numHwthreads" db:"num_hwthreads" example:"20" minimum:"1"` // Number of HWThreads used (Min > 0)
NumAcc int32 `json:"numAcc" db:"num_acc" example:"2" minimum:"1"` // Number of accelerators used (Min > 0)
Exclusive int32 `json:"exclusive" db:"exclusive" example:"1" minimum:"0" maximum:"2"` // Specifies how nodes are shared: 0 - Shared among multiple jobs of multiple users, 1 - Job exclusive (Default), 2 - Shared among multiple jobs of same user
MonitoringStatus int32 `json:"monitoringStatus" db:"monitoring_status" example:"1" minimum:"0" maximum:"3"` // State of monitoring system during job run: 0 - Disabled, 1 - Running or Archiving (Default), 2 - Archiving Failed, 3 - Archiving Successfull
SMT *int32 `json:"smt" db:"smt" example:"4"` // SMT threads used by job
SMT int32 `json:"smt" db:"smt" example:"4"` // SMT threads used by job
State JobState `json:"jobState" db:"job_state" example:"completed" enums:"completed,failed,cancelled,stopped,timeout,out_of_memory"` // Final state of job
Duration int32 `json:"duration" db:"duration" example:"43200" minimum:"1"` // Duration of job in seconds (Min > 0)
Walltime *int64 `json:"walltime" db:"walltime" example:"86400" minimum:"1"` // Requested walltime of job in seconds (Min > 0)
Walltime int64 `json:"walltime" db:"walltime" example:"86400" minimum:"1"` // Requested walltime of job in seconds (Min > 0)
Tags []*schema.Tag `json:"tags"` // List of tags
RawResources []byte `json:"-" db:"resources"` // Resources used by job [As Bytes]
Resources []*Resource `json:"resources"` // Resources used by job