initial SLURM sidecar code upload

Signed-off-by: Surax98 <giacomo.surace@gmail.com>

Author: Surax98

.gitignore

@@ -0,0 +1,2 @@
+envs.sh
+bin

Makefile

@@ -0,0 +1,4 @@
+all: sidecar
+
+sidecar:
+	CGO_ENABLED=0 GOOS=linux go build -o bin/slurm-sd cmd/main.go

Readme.md

@@ -0,0 +1,25 @@
+![Interlink logo](./docs/static/img/interlink_logo.png)
+
+## :information_source: Overview
+
+### Introduction
+InterLink aims to provide an abstraction for the execution of a Kubernetes pod on any remote resource capable of managing a Container execution lifecycle.
+We target to facilitate the development of provider specific plugins, so the resource providers can leverage the power of virtual kubelet without a black belt in kubernetes internals.
+
+The project consists of two main components:
+
+- __A Kubernetes Virtual Node:__ based on the [VirtualKubelet](https://virtual-kubelet.io/) technology. Translating request for a kubernetes pod execution into a remote call to the interLink API server.
+- __The interLink API server:__ a modular and pluggable REST server where you can create your own Container manager plugin (called sidecars), or use the existing ones: remote docker execution on a remote host, singularity Container on a remote SLURM batch system. This repo aims to maintain the SLURM sidecar as a standalone plugin.
+
+The project got inspired by the [KNoC](https://github.com/CARV-ICS-FORTH/knoc) and [Liqo](https://github.com/liqotech/liqo/tree/master) projects, enhancing that with the implemention a generic API layer b/w the virtual kubelet component and the provider logic for the container lifecycle management.
+
+## :information_source: Usage
+
+### Requirements
+- __[Our Kubernetes Virtual Node and the interLink API server](https://github.com/interTwin-eu/interLink)__
+- __[The Go programming language](https://go.dev/doc/install)__ (to build binaries)
+- __[Docker Engine](https://docs.docker.com/engine/)__ (optional)
+
+Note: if you want a quick start setup (using a Docker container), Go is not necessary
+
+### Quick Start

cmd/main.go

@@ -0,0 +1,58 @@
+package main
+
+import (
+	"context"
+	"net/http"
+	"strconv"
+
+	"github.com/sirupsen/logrus"
+	"github.com/virtual-kubelet/virtual-kubelet/log"
+	logruslogger "github.com/virtual-kubelet/virtual-kubelet/log/logrus"
+
+	commonIL "github.com/intertwin-eu/interlink/pkg/common"
+	slurm "github.com/intertwin-eu/interlink/pkg/slurm"
+)
+
+func main() {
+	logger := logrus.StandardLogger()
+
+	interLinkConfig, err := commonIL.NewInterLinkConfig()
+	if err != nil {
+		panic(err)
+	}
+
+	if interLinkConfig.VerboseLogging {
+		logger.SetLevel(logrus.DebugLevel)
+	} else if interLinkConfig.ErrorsOnlyLogging {
+		logger.SetLevel(logrus.ErrorLevel)
+	} else {
+		logger.SetLevel(logrus.InfoLevel)
+	}
+
+	log.L = logruslogger.FromLogrus(logrus.NewEntry(logger))
+
+	JobIDs := make(map[string]*slurm.JidStruct)
+	Ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	log.G(Ctx).Debug("Debug level: " + strconv.FormatBool(interLinkConfig.VerboseLogging))
+
+	SidecarAPIs := slurm.SidecarHandler{
+		Config: interLinkConfig,
+		JIDs:   &JobIDs,
+		Ctx:    Ctx,
+	}
+
+	mutex := http.NewServeMux()
+	mutex.HandleFunc("/status", SidecarAPIs.StatusHandler)
+	mutex.HandleFunc("/create", SidecarAPIs.SubmitHandler)
+	mutex.HandleFunc("/delete", SidecarAPIs.StopHandler)
+	mutex.HandleFunc("/getLogs", SidecarAPIs.GetLogsHandler)
+
+	slurm.CreateDirectories(interLinkConfig)
+	slurm.LoadJIDs(Ctx, interLinkConfig, &JobIDs)
+
+	err = http.ListenAndServe(":"+interLinkConfig.Sidecarport, mutex)
+	if err != nil {
+		log.G(Ctx).Fatal(err)
+	}
+}

docker/Dockerfile

@@ -0,0 +1,57 @@
+FROM golang:1.21 as build-stage
+
+WORKDIR /app
+
+COPY . .
+RUN CGO_ENABLED=0 GOOS=linux go build -o bin/slurm-sidecar cmd/main.go
+
+
+# Deploy the application binary into a lean image
+#FROM ubuntu:latest AS build-release-stage
+FROM ubuntu:22.04 
+
+# Settings for all images
+ENV TIMEZONE=America/New_York
+
+# Run system updates
+RUN apt update && apt -y upgrade
+
+# Set time zone
+RUN ln -sn /usr/share/zoneinfo/${TIMEZONE} /etc/localtime \
+    && echo ${TIMEZONE} > /etc/timezone \
+    && apt -y install tzdata
+
+# Set locale
+RUN apt -y install locales \
+    && locale-gen en_US.UTF-8 \
+    && update-locale LANG=en_US.UTF-8 LC_MESSAGES=POSIX
+
+# Install system packages
+RUN DEBIAN_FRONTEND=noninteractive \
+    apt -y install munge \
+                   slurm-wlm
+
+# Slurm configuration
+COPY docker/slurm.conf /etc/slurm/slurm.conf
+RUN mkdir -p /var/spool/slurmctld \
+    && chown slurm:slurm /var/spool/slurmctld
+
+# Startup configuration
+COPY docker/startup.sh /etc/startup.sh
+RUN chmod 555 /etc/startup.sh
+
+WORKDIR /root
+
+COPY --from=build-stage /app/bin/slurm-sidecar /sidecar/slurm-sidecar
+
+ENV INTERLINKCONFIGPATH=/root/InterLinkConfig.yaml
+
+COPY docker/InterLinkConfig.yaml .
+
+RUN apt update && apt install -y software-properties-common \
+ && add-apt-repository -y ppa:apptainer/ppa \
+ && apt install -y apptainer
+
+RUN mkdir -p /cvmfs/grid.cern.ch/etc/grid-security
+
+CMD ["/bin/sh", "-c", "/etc/startup.sh && /sidecar/slurm-sidecar"]

docker/Dockerfile.slurm

@@ -0,0 +1,39 @@
+FROM ubuntu:22.04 
+
+# Settings for all images
+ENV TIMEZONE=America/New_York
+
+# Run system updates
+RUN apt update && apt -y upgrade
+
+# Set time zone
+RUN ln -sn /usr/share/zoneinfo/${TIMEZONE} /etc/localtime \
+    && echo ${TIMEZONE} > /etc/timezone \
+    && apt -y install tzdata
+
+# Set locale
+RUN apt -y install locales \
+    && locale-gen en_US.UTF-8 \
+    && update-locale LANG=en_US.UTF-8 LC_MESSAGES=POSIX
+
+# Install system packages
+RUN DEBIAN_FRONTEND=noninteractive \
+    apt -y install munge \
+                   slurm-wlm
+
+# Slurm configuration
+COPY docker/slurm.conf /etc/slurm/slurm.conf
+RUN mkdir -p /var/spool/slurmctld \
+    && chown slurm:slurm /var/spool/slurmctld
+
+# Startup configuration
+COPY docker/startup.sh /etc/startup.sh
+RUN chmod 555 /etc/startup.sh
+
+WORKDIR /root
+
+RUN apt install -y software-properties-common \
+ && add-apt-repository -y ppa:apptainer/ppa \
+ && apt install -y apptainer
+
+CMD ["/bin/sh", "-c", "/etc/startup.sh && bash"]

docker/InterLinkConfig.yaml

@@ -0,0 +1,19 @@
+VKTokenFile: "$HOME/interLink/token"
+InterlinkURL: "http://interlink-api"
+SidecarURL: "http://docker-sidecar"
+InterlinkPort: "3000"
+SidecarPort: "4000"
+SbatchPath: "/usr/bin/sbatch"
+ScancelPath: "/usr/bin/scancel"
+SqueuePath: "/usr/bin/squeue"
+ExportPodData: true
+DataRootFolder: ".local/interlink/jobs/"
+ServiceAccount: "interlink"
+Namespace: "vk"
+Tsocks: false
+TsocksPath: "$WORK/tsocks-1.8beta5+ds1/libtsocks.so"
+TsocksLoginNode: "login01"
+BashPath: /bin/bash
+VerboseLogging: true
+ErrorsOnlyLogging: false
+Pod_IP: "172.16.9.11"

docker/docker-compose.yaml

@@ -0,0 +1,24 @@
+version: '3.7'
+services:
+  slurm-sidecar:
+    container_name: slurm-sidecar
+    build:
+      context: ../
+      dockerfile: docker/Dockerfile
+    restart: always
+    privileged: true
+    cap_add:
+    - SYS_ADMIN
+    #network_mode: "host"
+    ports:
+    - 4000:4000
+    volumes:
+    - type: bind
+      source: ../examples/config
+      target: /etc/interlink
+    # healthcheck:
+    #   test: ["CMD", "/check.sh"]
+    #   interval: 10s
+    #   timeout: 10s
+    #   retries: 3
+    #   start_period: 5s

docker/slurm.conf

@@ -0,0 +1,50 @@
+# slurm.conf file generated by configurator easy.html.
+# Put this file on all nodes of your cluster.
+# See the slurm.conf man page for more information.
+#
+ClusterName=cluster
+SlurmctldHost=<<HOSTNAME>>
+#
+#MailProg=/bin/mail
+MpiDefault=none
+#MpiParams=ports=#-#
+ProctrackType=proctrack/linuxproc
+ReturnToService=1
+SlurmctldPidFile=/var/run/slurmctld.pid
+#SlurmctldPort=6817
+SlurmdPidFile=/var/run/slurmd.pid
+#SlurmdPort=6818
+SlurmdSpoolDir=/var/spool/slurmd
+SlurmUser=slurm
+#SlurmdUser=root
+StateSaveLocation=/var/spool/slurmctld
+SwitchType=switch/none
+TaskPlugin=task/none
+#
+#
+# TIMERS
+#KillWait=30
+#MinJobAge=300
+#SlurmctldTimeout=120
+#SlurmdTimeout=300
+#
+#
+# SCHEDULING
+SchedulerType=sched/backfill
+SelectType=select/cons_tres
+SelectTypeParameters=CR_Core
+#
+#
+# LOGGING AND ACCOUNTING
+AccountingStorageType=accounting_storage/none
+#JobAcctGatherFrequency=30
+JobAcctGatherType=jobacct_gather/none
+#SlurmctldDebug=info
+SlurmctldLogFile=/var/log/slurmctld.log
+#SlurmdDebug=info
+SlurmdLogFile=/var/log/slurmd.log
+#
+#
+# COMPUTE NODES
+NodeName=<<HOSTNAME>> CPUs=<<CPU>> RealMemory=<<MEMORY>> State=UNKNOWN
+PartitionName=debug Nodes=ALL Default=YES MaxTime=INFINITE State=UP

docker/startup.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+# Determine whether script is running as root
+sudo_cmd=""
+if [ "$(id -u)" != "0" ]; then
+    sudo_cmd="sudo"
+    sudo -k
+fi
+
+# Configure Slurm to use maximum available processors and memory
+# and start required services
+${sudo_cmd} bash <<SCRIPT
+sed -i "s/<<HOSTNAME>>/$(hostname)/" /etc/slurm/slurm.conf
+sed -i "s/<<CPU>>/$(nproc)/" /etc/slurm/slurm.conf
+sed -i "s/<<MEMORY>>/$(if [[ "$(slurmd -C)" =~ RealMemory=([0-9]+) ]]; then echo "${BASH_REMATCH[1]}"; else exit 100; fi)/" /etc/slurm/slurm.conf
+service munge start
+service slurmd start
+service slurmctld start
+SCRIPT
+
+# Revoke sudo permissions
+if [[ ${sudo_cmd} ]]; then
+    sudo -k
+fi