diff --git a/go.mod b/go.mod index b87bb64..98dac3a 100644 --- a/go.mod +++ b/go.mod @@ -26,13 +26,14 @@ require ( github.com/swaggo/http-swagger v1.3.3 github.com/swaggo/swag v1.16.1 github.com/vektah/gqlparser/v2 v2.5.8 - golang.org/x/crypto v0.12.0 + golang.org/x/crypto v0.13.0 golang.org/x/exp v0.0.0-20230510235704-dd950f8aeaea ) require ( github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358 // indirect github.com/ClusterCockpit/slurm-rest-client-0_0_37 v0.0.0-20230901125459-dc653ac37420 // indirect + github.com/ClusterCockpit/slurm-rest-client-0_0_38 v0.0.0-20230906120742-0f15562ea666 // indirect github.com/KyleBanks/depth v1.2.1 // indirect github.com/agnivade/levenshtein v1.1.1 // indirect github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect @@ -40,6 +41,7 @@ require ( github.com/cespare/xxhash/v2 v2.2.0 // indirect github.com/containerd/containerd v1.6.18 // indirect github.com/cpuguy83/go-md2man/v2 v2.0.2 // indirect + github.com/davecgh/go-spew v1.1.1 // indirect github.com/deepmap/oapi-codegen v1.12.4 // indirect github.com/felixge/httpsnoop v1.0.3 // indirect github.com/go-asn1-ber/asn1-ber v1.5.4 // indirect @@ -72,19 +74,21 @@ require ( github.com/nats-io/nuid v1.0.1 // indirect github.com/opencontainers/image-spec v1.0.3-0.20211202183452-c5a74bcca799 // indirect github.com/pkg/errors v0.9.1 // indirect + github.com/pmezard/go-difflib v1.0.0 // indirect github.com/prometheus/client_model v0.3.0 // indirect github.com/prometheus/procfs v0.9.0 // indirect github.com/robfig/cron/v3 v3.0.1 // indirect github.com/russross/blackfriday/v2 v2.1.0 // indirect + github.com/stretchr/testify v1.8.4 // indirect github.com/swaggo/files v1.0.0 // indirect github.com/urfave/cli/v2 v2.25.7 // indirect github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673 // indirect go.uber.org/atomic v1.10.0 // indirect golang.org/x/mod v0.12.0 // indirect - golang.org/x/net v0.14.0 // indirect + golang.org/x/net v0.15.0 // indirect golang.org/x/oauth2 v0.5.0 // indirect - golang.org/x/sys v0.11.0 // indirect - golang.org/x/text v0.12.0 // indirect + golang.org/x/sys v0.12.0 // indirect + golang.org/x/text v0.13.0 // indirect golang.org/x/tools v0.12.0 // indirect google.golang.org/appengine v1.6.7 // indirect google.golang.org/protobuf v1.30.0 // indirect diff --git a/go.sum b/go.sum index 1dac910..6f22475 100644 --- a/go.sum +++ b/go.sum @@ -84,6 +84,8 @@ github.com/ClusterCockpit/cc-units v0.4.0 h1:zP5DOu99GmErW0tCDf0gcLrlWt42RQ9dpoO github.com/ClusterCockpit/cc-units v0.4.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw= github.com/ClusterCockpit/slurm-rest-client-0_0_37 v0.0.0-20230901125459-dc653ac37420 h1:AeQY40KrLQmSSyyHdbNdAqgln+0+p1dLag5yspE5M8A= github.com/ClusterCockpit/slurm-rest-client-0_0_37 v0.0.0-20230901125459-dc653ac37420/go.mod h1:oNgVG2puNj9cNw/KgqLbgE1pPOn8jXORX3ErP58LcAA= +github.com/ClusterCockpit/slurm-rest-client-0_0_38 v0.0.0-20230906120742-0f15562ea666 h1:8PofHcOwEMmeAFqJjvAEgnu7rbRHAwJhd2XJ9u/YxiU= +github.com/ClusterCockpit/slurm-rest-client-0_0_38 v0.0.0-20230906120742-0f15562ea666/go.mod h1:vxaj1my0GNoCXx4bYyOTA/IZP/IOZImtdOIn4T7pCa4= github.com/KyleBanks/depth v1.2.1 h1:5h8fQADFrWtarTdtDudMmGsC7GPbOAu6RVB3ffsVFHc= github.com/KyleBanks/depth v1.2.1/go.mod h1:jzSb9d0L43HxTQfT+oSA1EEp2q+ne2uh6XgeJcm8brE= github.com/Masterminds/squirrel v1.5.3 h1:YPpoceAcxuzIljlr5iWpNKaql7hLeG1KLSrhvdHpkZc= @@ -463,6 +465,7 @@ github.com/go-ldap/ldap/v3 v3.4.4/go.mod h1:fe1MsuN5eJJ1FeLT/LEBVdWfNWKh459R7aXg github.com/go-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9GBnD5lWE= github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk= github.com/go-logfmt/logfmt v0.5.0/go.mod h1:wCYkCAKZfumFQihp8CzCvQ3paCTfi41vtzG1KdI/P7A= +github.com/go-logfmt/logfmt v0.5.1/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs= github.com/go-logr/logr v0.1.0/go.mod h1:ixOQHD9gLJUVQQ2ZOR7zLEifBX6tGkNJF4QyIY7sIas= github.com/go-logr/logr v0.2.0/go.mod h1:z6/tIYblkpsD+a4lm/fGIIU9mZ+XfAiaFtq7xTgseGU= github.com/go-logr/logr v0.4.0/go.mod h1:z6/tIYblkpsD+a4lm/fGIIU9mZ+XfAiaFtq7xTgseGU= @@ -595,6 +598,7 @@ github.com/golang/snappy v0.0.0-20170215233205-553a64147049/go.mod h1:/XxbfmMg8l github.com/golang/snappy v0.0.1/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q= github.com/golang/snappy v0.0.3/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q= github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q= +github.com/golangci/lint-1 v0.0.0-20181222135242-d2cdd8c08219/go.mod h1:/X8TswGSh1pIozq4ZwCfxS0WA5JGXguxk94ar/4c87Y= github.com/google/btree v0.0.0-20180813153112-4030bb1f1f0c/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ= github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ= github.com/google/btree v1.0.1/go.mod h1:xXMiIv4Fb/0kKde4SpL7qlzvu5cMJDRkFDxJfI9uaxA= @@ -1158,6 +1162,7 @@ github.com/stretchr/testify v1.7.2/go.mod h1:R6va5+xMeoiuVRoj+gSkQ7d3FALtqAAGI1F github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU= github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4= github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk= +github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo= github.com/subosito/gotenv v1.2.0/go.mod h1:N0PQaV/YGNqwC0u51sEeR/aUtSLEXKX9iv69rRypqCw= github.com/swaggo/files v1.0.0 h1:1gGXVIeUFCS/dta17rnP0iOpr6CXFwKD7EO5ID233e4= github.com/swaggo/files v1.0.0/go.mod h1:N59U6URJLyU1PQgFqPM7wXLMhJx7QAolnvfQkqO13kc= @@ -1181,6 +1186,7 @@ github.com/urfave/cli v1.22.1/go.mod h1:Gos4lmkARVdJ6EkW0WaNv/tZAAMe9V7XWyB60NtX github.com/urfave/cli v1.22.2/go.mod h1:Gos4lmkARVdJ6EkW0WaNv/tZAAMe9V7XWyB60NtXRu0= github.com/urfave/cli/v2 v2.25.7 h1:VAzn5oq403l5pHjc4OhD54+XGO9cdKVL/7lDjF+iKUs= github.com/urfave/cli/v2 v2.25.7/go.mod h1:8qnjx1vcq5s2/wpsqoZFndg2CE5tNFyrTvS6SinrnYQ= +github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc= github.com/vektah/gqlparser/v2 v2.5.8 h1:pm6WOnGdzFOCfcQo9L3+xzW51mKrlwTEg4Wr7AH1JW4= github.com/vektah/gqlparser/v2 v2.5.8/go.mod h1:z8xXUff237NntSuH8mLFijZ+1tjV1swDbpDqjJmk6ME= github.com/vishvananda/netlink v0.0.0-20181108222139-023a6dafdcdf/go.mod h1:+SR5DhBJrl6ZM7CoCKvpw5BKroDKQ+PJqOg65H/2ktk= @@ -1300,6 +1306,8 @@ golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5y golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4= golang.org/x/crypto v0.12.0 h1:tFM/ta59kqch6LlvYnPa0yx5a83cL2nHflFhYKvv9Yk= golang.org/x/crypto v0.12.0/go.mod h1:NF0Gs7EO5K4qLn+Ylc+fih8BSTeIjAP05siRnAh98yw= +golang.org/x/crypto v0.13.0 h1:mvySKfSWJ+UKUii46M40LOvyWfN0s2U+46/jDd0e6Ck= +golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc= golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA= golang.org/x/exp v0.0.0-20180807140117-3d87b88a115f/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA= golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA= @@ -1423,6 +1431,8 @@ golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug golang.org/x/net v0.2.0/go.mod h1:KqCZLdyyvdV855qA2rE3GC2aiw5xGR5TEjj8smXukLY= golang.org/x/net v0.14.0 h1:BONx9s002vGdD9umnlX1Po8vOZmrgH34qlHcD1MfK14= golang.org/x/net v0.14.0/go.mod h1:PpSgVXXLK0OxS0F31C1/tv6XNguvCrnXIDrFMspZIUI= +golang.org/x/net v0.15.0 h1:ugBLEUaxABaB5AJqW9enI0ACdci2RUd4eP51NTBvuJ8= +golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk= golang.org/x/oauth2 v0.0.0-20180227000427-d7d64896b5ff/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U= golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U= golang.org/x/oauth2 v0.0.0-20181106182150-f42d05182288/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U= @@ -1582,6 +1592,8 @@ golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBc golang.org/x/sys v0.2.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.11.0 h1:eG7RXZHdqOJ1i+0lgLgCpSXAp6M3LYlAo6osgSi0xOM= golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.12.0 h1:CM0HF96J0hcLAwsHPJZjfdNzs0gftsLfgKt57wWHJ0o= +golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw= golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= golang.org/x/term v0.0.0-20210220032956-6a3ed077a48d/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= @@ -1600,6 +1612,8 @@ golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= golang.org/x/text v0.4.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8= golang.org/x/text v0.12.0 h1:k+n5B8goJNdU7hSvEtMUz3d1Q6D/XW4COJSJR6fN0mc= golang.org/x/text v0.12.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE= +golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k= +golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE= golang.org/x/time v0.0.0-20180412165947-fbb02b2291d2/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ= golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ= golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ= diff --git a/internal/scheduler/slurmRest.go b/internal/scheduler/slurmRest.go index 5dc0459..5e30a7d 100644 --- a/internal/scheduler/slurmRest.go +++ b/internal/scheduler/slurmRest.go @@ -14,11 +14,13 @@ import ( "os" "os/exec" "strconv" - "sync" "time" + "github.com/ClusterCockpit/cc-backend/internal/repository" "github.com/ClusterCockpit/cc-backend/pkg/log" "github.com/ClusterCockpit/cc-backend/pkg/schema" + + openapi "github.com/ClusterCockpit/slurm-rest-client-0_0_38" ) // A Response struct to map the Entire Response @@ -33,6 +35,8 @@ type SlurmRestSchedulerConfig struct { type SlurmRestScheduler struct { url string + + JobRepository *repository.JobRepository } var client *http.Client @@ -247,72 +251,85 @@ func (sd *SlurmRestScheduler) Init(rawConfig json.RawMessage) error { return err } -func (sd *SlurmRestScheduler) Sync() { - // for _, job := range jobs.GetJobs() { - // fmt.Printf("Job %s - %s\n", job.GetJobId(), job.GetJobState()) - // } - - jobsResponse, err := queryAllJobs() - if err != nil { - log.Fatal(err.Error()) - } - - // Fetch an example instance of V0037JobsResponse - // jobsResponse := V0037JobsResponse{} +func (sd *SlurmRestScheduler) HandleJobsResponse(jobsResponse openapi.V0038JobsResponse) { // Iterate over the Jobs slice for _, job := range jobsResponse.Jobs { // Process each job - fmt.Printf("Job ID: %s\n", job.JobID) + fmt.Printf("Job ID: %s\n", job.JobId) fmt.Printf("Job Name: %s\n", *job.Name) fmt.Printf("Job State: %s\n", *job.JobState) fmt.Println("Job StartTime:", *job.StartTime) - // is aquire lock to avoid race condition between API calls needed? - // aquire lock to avoid race condition between API calls - var unlockOnce sync.Once - sd.RepositoryMutex.Lock() - defer unlockOnce.Do(sd.RepositoryMutex.Unlock) + // var unlockOnce sync.Once + // sd.RepositoryMutex.Lock() + // defer unlockOnce.Do(sd.RepositoryMutex.Unlock) // is "running" one of JSON state? if *job.JobState == "running" { // Check if combination of (job_id, cluster_id, start_time) already exists: - jobs, err := sd.JobRepository.FindAll(job.JobID, &job.Cluster, job.StartTime) + // jobs, err := sd.JobRepository.FindRunningJobs(job.Cluster, job.StartTime) + + jobs, err := sd.FindRunningJobs(job.Cluster) + if err != nil { + log.Fatalf("Failed to find running jobs: %v", err) + } + + for id, job := range jobs { + fmt.Printf("Job ID: %d, Job: %+v\n", id, job) + } if err != nil || err != sql.ErrNoRows { log.Errorf("checking for duplicate failed: %s", err.Error()) return } else if err == nil { if len(jobs) == 0 { + var exclusive int32 + if job.Shared == nil { + exclusive = 1 + } else { + exclusive = 0 + } + + jobResourcesInBytes, err := json.Marshal(*job.JobResources) + if err != nil { + log.Fatalf("JSON marshaling failed: %s", err) + } + var defaultJob schema.BaseJob = schema.BaseJob{ - JobID: job.JobID, - User: job.User, - Project: job.Project, - Cluster: job.Cluster, - SubCluster: job.SubCluster, - Partition: job.Partition, - ArrayJobId: job.ArrayJobId, - NumNodes: job.NumNodes, - NumHWThreads: job.NumHWThreads, - NumAcc: job.NumAcc, - Exclusive: job.Exclusive, - MonitoringStatus: job.MonitoringStatus, - SMT: job.SMT, - State: job.State, - Duration: job.Duration, - Walltime: job.Walltime, - Tags: job.Tags, - RawResources: job.RawResources, - Resources: job.Resources, - RawMetaData: job.RawMetaData, - MetaData: job.MetaData, - ConcurrentJobs: job.ConcurrentJobs, + JobID: int64(*job.JobId), + User: *job.UserName, + Project: *job.Account, + Cluster: *job.Cluster, + Partition: *job.Partition, + // check nil + ArrayJobId: int64(*job.ArrayJobId), + NumNodes: *job.NodeCount, + NumHWThreads: *job.Cpus, + // NumAcc: job.NumAcc, + Exclusive: exclusive, + // MonitoringStatus: job.MonitoringStatus, + // SMT: *job.TasksPerCore, + State: schema.JobState(*job.JobState), + // ignore this for start job + // Duration: int32(time.Now().Unix() - *job.StartTime), // or SubmitTime? + Walltime: time.Now().Unix(), // max duration requested by the job + // Tags: job.Tags, + // ignore this! + RawResources: jobResourcesInBytes, + // "job_resources": "allocated_nodes" "sockets": + // very important; has to be right + Resources: job.JobResources, + // RawMetaData: job.RawMetaData, + // optional metadata with'jobScript 'jobName': 'slurmInfo': + // MetaData: job.MetaData, + // ConcurrentJobs: job.ConcurrentJobs, } req := &schema.JobMeta{ BaseJob: defaultJob, - StartTime: job.StartTime, + StartTime: *job.StartTime, Statistics: make(map[string]schema.JobStatistics), } // req := new(schema.JobMeta) @@ -328,15 +345,17 @@ func (sd *SlurmRestScheduler) Sync() { existingJob, err := sd.JobRepository.Find(job.JobID, &job.Cluster, job.StartTime) if err == nil { - existingJob.BaseJob.Duration = job.EndTime - job.StartTime - existingJob.BaseJob.State = job.State + existingJob.BaseJob.Duration = *job.EndTime - *job.StartTime + existingJob.BaseJob.State = schema.JobState(*job.JobState) existingJob.BaseJob.Walltime = job.StartTime + var jobID int64 + jobID = int64(*job.JobId) req := &StopJobRequest{ Cluster: job.Cluster, - JobId: job.JobId, - State: job.State, + JobId: &jobID, + State: schema.JobState(*job.JobState), StartTime: existingJob.StartTime, - StopTime: job.StartTime, + StopTime: *job.EndTime, } // req := new(schema.JobMeta) id, err := sd.JobRepository.checkAndHandleStopJob(job, req) @@ -344,5 +363,22 @@ func (sd *SlurmRestScheduler) Sync() { } } +} + +func (sd *SlurmRestScheduler) Sync() { + // for _, job := range jobs.GetJobs() { + // fmt.Printf("Job %s - %s\n", job.GetJobId(), job.GetJobState()) + // } + + response, err := queryAllJobs() + if err != nil { + log.Fatal(err.Error()) + } + + // Fetch an example instance of V0037JobsResponse + // jobsResponse := openapi.V0038JobsResponse{} + + var jobsResponse openapi.V0038JobsResponse + sd.HandleJobsResponse(jobsResponse) } diff --git a/tools/nats-manager/main.go b/tools/nats-manager/main.go index ddf1c43..90d0d04 100644 --- a/tools/nats-manager/main.go +++ b/tools/nats-manager/main.go @@ -7,7 +7,6 @@ package main import ( "flag" "fmt" - "io/ioutil" "log" "net/http" "os" @@ -76,8 +75,8 @@ func setupPublisher() { func injectPayload() { // Read the JSON file - jobsData, err := ioutil.ReadFile("slurm_0038.json") - dbData, err := ioutil.ReadFile("slurmdb_0038-large.json") + jobsData, err := os.ReadFile("slurm_0038.json") + dbData, err := os.ReadFile("slurmdb_0038-large.json") if err != nil { fmt.Println("Error reading JSON file:", err)