feat: slurm support (#98)

This change adds a dispatcher resource manager, which gives Determined the ability to run on top of Slurm.

Co-authored-by: rcorujo <90728398+rcorujo@users.noreply.github.com>
Co-authored-by: Phillip Gaisford <phillip.gaisford@hpe.com>
Co-authored-by: phillip-gaisford <98362331+phillip-gaisford@users.noreply.github.com>
Co-authored-by: Jerry J. Harrow <84593277+jerryharrow@users.noreply.github.com>
Co-authored-by: Jagadeesh Madagundi <jagadeesh545@gmail.com>
Co-authored-by: Philip Norman <philipnrmn@users.noreply.github.com>

agent/go.mod

@@ -0,0 +1,188 @@
+module github.com/determined-ai/determined/agent
+
+go 1.21
+
+require (
+	github.com/determined-ai/determined/master v0.0.0
+	github.com/docker/distribution v2.8.2+incompatible
+	github.com/docker/docker v20.10.24+incompatible
+	github.com/docker/docker-credential-helpers v0.6.4
+	github.com/docker/go-connections v0.4.0 // indirect
+	github.com/ghodss/yaml v1.0.1-0.20190212211648-25d852aebe32
+	github.com/go-ole/go-ole v1.2.6 // indirect
+	github.com/google/uuid v1.3.0
+	github.com/gorilla/websocket v1.5.0
+	github.com/labstack/echo/v4 v4.9.1
+	github.com/pkg/errors v0.9.1
+	github.com/shirou/gopsutil v3.21.11+incompatible
+	github.com/sirupsen/logrus v1.8.1
+	github.com/spf13/cobra v1.6.1
+	github.com/spf13/pflag v1.0.5
+	golang.org/x/sys v0.10.0
+	gotest.tools v2.2.0+incompatible
+)
+
+require (
+	github.com/davecgh/go-spew v1.1.1
+	github.com/stretchr/testify v1.8.1
+	go.opentelemetry.io/contrib/instrumentation/github.com/labstack/echo/otelecho v0.29.0
+	golang.org/x/exp v0.0.0-20220328175248-053ad81199eb
+)
+
+require (
+	cloud.google.com/go v0.94.0 // indirect
+	cloud.google.com/go/storage v1.10.0 // indirect
+	github.com/Azure/go-ansiterm v0.0.0-20210617225240-d185dfc1b5a1 // indirect
+	github.com/Azure/go-autorest v14.2.0+incompatible // indirect
+	github.com/Azure/go-autorest/autorest v0.11.20 // indirect
+	github.com/Azure/go-autorest/autorest/adal v0.9.15 // indirect
+	github.com/Azure/go-autorest/autorest/date v0.3.0 // indirect
+	github.com/Azure/go-autorest/logger v0.2.1 // indirect
+	github.com/Azure/go-autorest/tracing v0.6.0 // indirect
+	github.com/Microsoft/go-winio v0.5.0 // indirect
+	github.com/aead/chacha20 v0.0.0-20180709150244-8b13a72661da // indirect
+	github.com/aead/chacha20poly1305 v0.0.0-20170617001512-233f39982aeb // indirect
+	github.com/aead/poly1305 v0.0.0-20180717145839-3fee0db0b635 // indirect
+	github.com/aws/aws-sdk-go v1.40.34 // indirect
+	github.com/beorn7/perks v1.0.1 // indirect
+	github.com/cenkalti/backoff/v4 v4.1.3 // indirect
+	github.com/cespare/xxhash/v2 v2.1.1 // indirect
+	github.com/coreos/go-systemd v0.0.0-20190719114852-fd7a80b32e1f // indirect
+	github.com/determined-ai/determined/proto v0.0.0-00010101000000-000000000000 // indirect
+	github.com/docker/go-metrics v0.0.1 // indirect
+	github.com/docker/go-units v0.4.0 // indirect
+	github.com/docker/libtrust v0.0.0-20150114040149-fa567046d9b1 // indirect
+	github.com/dustinkirkland/golang-petname v0.0.0-20191129215211-8e5a1ed0cff0 // indirect
+	github.com/elastic/go-elasticsearch/v7 v7.9.0 // indirect
+	github.com/emirpasic/gods v1.18.1 // indirect
+	github.com/fatih/color v1.15.0 // indirect
+	github.com/go-logr/logr v1.2.3 // indirect
+	github.com/go-logr/stdr v1.2.2 // indirect
+	github.com/go-pg/migrations/v8 v8.1.0 // indirect
+	github.com/go-pg/pg/v10 v10.10.6 // indirect
+	github.com/go-pg/zerochecker v0.2.0 // indirect
+	github.com/gogo/protobuf v1.3.2 // indirect
+	github.com/golang-jwt/jwt v3.2.2+incompatible // indirect
+	github.com/golang-jwt/jwt/v4 v4.4.3 // indirect
+	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
+	github.com/golang/protobuf v1.5.2 // indirect
+	github.com/google/go-cmp v0.5.8 // indirect
+	github.com/google/gofuzz v1.1.0 // indirect
+	github.com/googleapis/gax-go/v2 v2.1.0 // indirect
+	github.com/googleapis/gnostic v0.5.5 // indirect
+	github.com/gorilla/mux v1.8.0 // indirect
+	github.com/grpc-ecosystem/go-grpc-middleware v1.3.0 // indirect
+	github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0 // indirect
+	github.com/grpc-ecosystem/grpc-gateway v1.16.0 // indirect
+	github.com/grpc-ecosystem/grpc-gateway/v2 v2.7.0 // indirect
+	github.com/hashicorp/errwrap v1.0.0 // indirect
+	github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
+	github.com/hashicorp/go-multierror v1.1.1 // indirect
+	github.com/hashicorp/golang-lru v0.5.1 // indirect
+	github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
+	github.com/inconshreveable/mousetrap v1.0.1 // indirect
+	github.com/jackc/chunkreader/v2 v2.0.1 // indirect
+	github.com/jackc/pgconn v1.9.0 // indirect
+	github.com/jackc/pgio v1.0.0 // indirect
+	github.com/jackc/pgpassfile v1.0.0 // indirect
+	github.com/jackc/pgproto3/v2 v2.1.1 // indirect
+	github.com/jackc/pgservicefile v0.0.0-20200714003250-2b9c44734f2b // indirect
+	github.com/jackc/pgtype v1.8.0 // indirect
+	github.com/jackc/pgx/v4 v4.12.0 // indirect
+	github.com/jinzhu/copier v0.3.5 // indirect
+	github.com/jinzhu/inflection v1.0.0 // indirect
+	github.com/jmespath/go-jmespath v0.4.0 // indirect
+	github.com/jmoiron/sqlx v1.2.1-0.20190826204134-d7d95172beb5 // indirect
+	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/labstack/echo-contrib v0.11.0 // indirect
+	github.com/labstack/gommon v0.4.0 // indirect
+	github.com/mattn/go-colorable v0.1.13 // indirect
+	github.com/mattn/go-isatty v0.0.19 // indirect
+	github.com/matttproud/golang_protobuf_extensions v1.0.2-0.20181231171920-c182affec369 // indirect
+	github.com/moby/term v0.0.0-20210619224110-3f7ff695adc6 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/morikuni/aec v1.0.0 // indirect
+	github.com/o1egl/paseto v1.0.0 // indirect
+	github.com/opencontainers/go-digest v1.0.0 // indirect
+	github.com/opencontainers/image-spec v1.0.2 // indirect
+	github.com/opentracing/opentracing-go v1.2.0 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/prometheus/client_golang v1.11.1 // indirect
+	github.com/prometheus/client_model v0.2.0 // indirect
+	github.com/prometheus/common v0.26.0 // indirect
+	github.com/prometheus/procfs v0.6.0 // indirect
+	github.com/rogpeppe/go-internal v1.9.0 // indirect
+	github.com/santhosh-tekuri/jsonschema/v2 v2.2.0 // indirect
+	github.com/segmentio/backo-go v0.0.0-20200129164019-23eae7c10bd3 // indirect
+	github.com/shopspring/decimal v1.2.0 // indirect
+	github.com/soheilhy/cmux v0.1.4 // indirect
+	github.com/tklauser/go-sysconf v0.3.11 // indirect
+	github.com/tklauser/numcpus v0.6.0 // indirect
+	github.com/tmthrgd/go-hex v0.0.0-20190904060850-447a3041c3bc // indirect
+	github.com/uber/jaeger-client-go v2.25.0+incompatible // indirect
+	github.com/uber/jaeger-lib v2.4.0+incompatible // indirect
+	github.com/uptrace/bun v1.1.14 // indirect
+	github.com/uptrace/bun/dialect/pgdialect v1.1.14 // indirect
+	github.com/uptrace/bun/extra/bundebug v1.1.14 // indirect
+	github.com/valyala/bytebufferpool v1.0.0 // indirect
+	github.com/valyala/fasttemplate v1.2.1 // indirect
+	github.com/vmihailenco/bufpool v0.1.11 // indirect
+	github.com/vmihailenco/msgpack/v5 v5.3.5 // indirect
+	github.com/vmihailenco/tagparser v0.1.2 // indirect
+	github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
+	github.com/xtgo/uuid v0.0.0-20140804021211-a0b114877d4c // indirect
+	github.com/yusufpapurcu/wmi v1.2.2 // indirect
+	go.opencensus.io v0.23.0 // indirect
+	go.opentelemetry.io/otel v1.6.1 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/internal/retry v1.6.1 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.6.1 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.6.1 // indirect
+	go.opentelemetry.io/otel/sdk v1.6.1 // indirect
+	go.opentelemetry.io/otel/trace v1.6.1 // indirect
+	go.opentelemetry.io/proto/otlp v0.12.1 // indirect
+	go.uber.org/atomic v1.10.0 // indirect
+	golang.org/x/crypto v0.0.0-20220829220503-c86fa9a7ed90 // indirect
+	golang.org/x/net v0.7.0 // indirect
+	golang.org/x/oauth2 v0.0.0-20211104180415-d3ed0bb246c8 // indirect
+	golang.org/x/sync v0.1.0 // indirect
+	golang.org/x/term v0.5.0 // indirect
+	golang.org/x/text v0.7.0 // indirect
+	golang.org/x/time v0.0.0-20210723032227-1f47c861a9ac // indirect
+	google.golang.org/api v0.56.0 // indirect
+	google.golang.org/appengine v1.6.7 // indirect
+	google.golang.org/genproto v0.0.0-20211223182754-3ac035c7e7cb // indirect
+	google.golang.org/grpc v1.45.0 // indirect
+	google.golang.org/protobuf v1.28.0 // indirect
+	gopkg.in/guregu/null.v3 v3.4.0 // indirect
+	gopkg.in/inf.v0 v0.9.1 // indirect
+	gopkg.in/segmentio/analytics-go.v3 v3.1.0 // indirect
+	gopkg.in/yaml.v2 v2.4.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+	k8s.io/api v0.20.14 // indirect
+	k8s.io/apimachinery v0.20.14 // indirect
+	k8s.io/client-go v0.20.14 // indirect
+	k8s.io/klog/v2 v2.30.0 // indirect
+	k8s.io/kube-openapi v0.0.0-20211115234752-e816edb12b65 // indirect
+	k8s.io/utils v0.0.0-20210930125809-cb0fa318a74b // indirect
+	mellium.im/sasl v0.3.1 // indirect
+	sigs.k8s.io/structured-merge-diff/v4 v4.1.2 // indirect
+	sigs.k8s.io/yaml v1.2.0 // indirect
+)
+
+require (
+	github.com/coreos/go-oidc/v3 v3.1.0 // indirect
+	github.hpe.com/hpe/hpc-ard-launcher-go/launcher v0.1.2 // indirect
+	gopkg.in/oauth2.v3 v3.12.0 // indirect
+	gopkg.in/square/go-jose.v2 v2.5.1 // indirect
+)
+
+replace github.com/determined-ai/determined/master => ../master
+
+replace github.com/determined-ai/determined/proto => ../proto
+
+// Determined AI's CircleCI doesn't have access to "github.hpe.com/hpe/hpc-ard-launcher-go",
+// so the build will fail in CircleCI.  Therefore, we had to do a "git clone" of the
+// launcher repo to store a local copy.  We make use of the "replace" directive to use the
+// local copy and not try to pull it from GitHub.
+replace github.hpe.com/hpe/hpc-ard-launcher-go/launcher => ../hpc-ard-launcher-go/launcher

hpc-ard-launcher-go/README.md

@@ -0,0 +1,29 @@
+# hpc-ard-launcher-go
+
+This repo is the home of the Capsules (hpc-ard-capsules-core) dispatch server Go client.
+
+The code found here is generated automatically using openapi tools from the Capsules REST API specification. It can be build wit the following command line executed in the hpc-ard-capsules-core project:
+
+```
+mvn -pl com.cray.analytics.capsules:capsules-dispatch-client clean generate-sources -P go-client
+```
+To install the package to your Go environment:
+
+If you use ssh to interact with github.hpe.com, add the following to your ~/.gitconfig:
+```
+[url "ssh://git@github.hpe.com/"]
+        insteadOf = https://github.hpe.com/
+```
+Then:
+```
+% export GOPRIVATE=github.hpe.com/hpe/hpc-ard-launcher-go
+% go get github.hpe.com/hpe/hpc-ard-launcher-go/launcher
+```
+Import the launcher package to your Go program thus:
+```
+import (
+	<other imports go here>
+
+	"github.hpe.com/hpe/hpc-ard-launcher-go/launcher"
+)
+```

hpc-ard-launcher-go/go.mod

@@ -0,0 +1,5 @@
+module github.hpe.com/hpe/hpc-ard-launcher-go
+
+go 1.13
+
+require golang.org/x/oauth2 v0.0.0-20210218202405-ba52d332ba99