add podman support

Author: yongbinfeng

HeterogeneousCore/SonicTriton/README.md

@@ -132,7 +132,7 @@ The script has three operations (`start`, `stop`, `check`) and the following opt
 * `-c`: don't cleanup temporary dir (for debugging)
 * `-C [dir]`: directory containing Nvidia compatibility drivers (checks CMSSW_BASE by default if available)
 * `-D`: dry run: print container commands rather than executing them
-* `-d`: use Docker instead of Apptainer
+* `-d [exe]`: container choice: Apptainer, Docker, Podman (default: apptainer)
 * `-E [path]`: include extra path(s) for executables (default: /cvmfs/oasis.opensciencegrid.org/mis/apptainer/current/bin)
 * `-f`: force reuse of (possibly) existing container instance
 * `-g [device]`: device choice: auto (try to detect GPU), CPU, GPU (default: auto)
@@ -200,8 +200,8 @@ The fallback server has a separate set of options, mostly related to the invocat
 * `enable`: enable the fallback server
 * `debug`: enable debugging (equivalent to `-c` in `cmsTriton`)
 * `verbose`: enable verbose output in logs (equivalent to `-v` in `cmsTriton`)
-* `useDocker`: use Docker instead of Apptainer (equivalent to `-d` in `cmsTriton`)
-* `useGPU`: run on local GPU (equivalent to `-g` in `cmsTriton`)
+* `container`: container choice (equivalent to `-d` in `cmsTriton`)
+* `device`: device choice (equivalent to `-g` in `cmsTriton`)
 * `retries`: number of retries when starting container (passed to `-r [num]` in `cmsTriton` if >= 0; default: -1)
 * `wait`: maximum time to wait for server to start (passed to `-w time` in `cmsTriton` if >= 0; default: -1)
 * `instanceBaseName`: base name for server instance if random names are enabled (default: triton_server_instance)

HeterogeneousCore/SonicTriton/interface/TritonService.h

@@ -36,7 +36,7 @@ class TritonService {
         : enable(pset.getUntrackedParameter<bool>("enable")),
           debug(pset.getUntrackedParameter<bool>("debug")),
           verbose(pset.getUntrackedParameter<bool>("verbose")),
-          useDocker(pset.getUntrackedParameter<bool>("useDocker")),
+          container(pset.getUntrackedParameter<std::string>("container")),
           device(pset.getUntrackedParameter<std::string>("device")),
           retries(pset.getUntrackedParameter<int>("retries")),
           wait(pset.getUntrackedParameter<int>("wait")),
@@ -54,7 +54,7 @@ class TritonService {
     bool enable;
     bool debug;
     bool verbose;
-    bool useDocker;
+    std::string container;
     std::string device;
     int retries;
     int wait;

HeterogeneousCore/SonicTriton/scripts/cmsTriton

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # defaults
-USEDOCKER=""
+CONTAINER=apptainer
 VERBOSE=""
 VERBOSE_ARGS="--log-verbose=1 --log-error=1 --log-warning=1 --log-info=1"
 WTIME=600
@@ -42,7 +42,7 @@ usage() {
 	$ECHO "-c          \t don't cleanup temporary dir (for debugging)"
 	$ECHO "-C [dir]    \t directory containing Nvidia compatibility drivers (checks CMSSW_BASE by default if available)"
 	$ECHO "-D          \t dry run: print container commands rather than executing them"
-	$ECHO "-d          \t use Docker instead of Apptainer"
+	$ECHO "-d [exe]    \t container choice: Apptainer, Docker, Podman (default: ${CONTAINER})"
 	$ECHO "-E [path]   \t include extra path(s) for executables (default: ${EXTRAPATH})"
 	$ECHO "-f          \t force reuse of (possibly) existing container instance"
 	$ECHO "-g [device] \t device choice: auto (try to detect GPU), CPU, GPU (default: ${DEVICE})"
@@ -73,15 +73,15 @@ if [ -e /run/shm ]; then
 	SHM=/run/shm
 fi
 
-while getopts "cC:Ddfg:i:I:M:m:n:P:p:r:s:t:vw:h" opt; do
+while getopts "cC:Dd:fg:i:I:M:m:n:P:p:r:s:t:vw:h" opt; do
 	case "$opt" in
 		c) CLEANUP=""
 		;;
 		C) COMPAT_USR="$OPTARG"
 		;;
 		D) DRYRUN=echo
 		;;
-		d) USEDOCKER=true
+		d) CONTAINER="$OPTARG"
 		;;
 		f) FORCE=true
 		;;
@@ -130,6 +130,13 @@ if [[ ! " auto cpu gpu " =~ " $DEVICE " ]]; then
 	exit 1
 fi
 
+# check acceptable values for container choice
+CONTAINER="${CONTAINER,,}"
+if [[ ! " apptainer docker podman " =~ " $CONTAINER " ]]; then
+	echo "Unsupported container value: $CONTAINER"
+	exit 1
+fi
+
 if [ "$RETRIES" -le 0 ]; then
 	RETRIES=1
 fi
@@ -147,9 +154,13 @@ if [ -n "$EXTRAPATH" ]; then
 fi
 
 # find executables
-if [ -n "$USEDOCKER" ]; then
+if [ "$CONTAINER" == "docker" ]; then
 	if [ -z "$DOCKER" ]; then
-		DOCKER="sudo docker"
+		DOCKER="docker"
+	fi
+elif [ "$CONTAINER" == "podman" ]; then
+	if [ -z "$PODMAN" ]; then
+		PODMAN="podman"
 	fi
 else
 	if [ -z "$APPTAINER" ]; then
@@ -246,6 +257,29 @@ start_docker(){
 		${IMAGE} tritonserver $PORTARGS $REPOARGS $VERBOSE
 }
 
+start_podman(){
+	# mount all model repositories
+	MOUNTARGS=""
+	REPOARGS=""
+	for REPO in ${REPOS[@]}; do
+		MOUNTARGS="$MOUNTARGS --volume $REPO:$REPO"
+		REPOARGS="$REPOARGS --model-repository=${REPO}"
+	done
+
+	# compatibility driver environment
+	if [ -n "$COMPAT" ]; then
+		MOUNTARGS="$MOUNTARGS --volume $COMPAT"
+		if [ -n "$COMPAT_SCRIPT_MOUNT" ]; then
+			MOUNTARGS="$MOUNTARGS --volume $COMPAT_SCRIPT_MOUNT"
+		fi
+	fi
+
+	$DRYRUN $PODMAN run -d --name ${SERVER} \
+		--shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 \
+		-p${HTTPPORT}:${HTTPPORT} -p${GRPCPORT}:${GRPCPORT} -p${METRPORT}:${METRPORT} $EXTRA $MOUNTARGS \
+		${IMAGE} tritonserver $PORTARGS $REPOARGS $VERBOSE
+}
+
 start_apptainer(){
 	# triton server image may need to modify contents of opt/tritonserver/lib/
 	# but cvmfs is read-only
@@ -305,6 +339,16 @@ stop_docker(){
 	$DRYRUN $DOCKER rm ${SERVER}
 }
 
+stop_podman(){
+	# keep log
+	if [ -z "$DRYRUN" ]; then
+		if [ -n "$VERBOSE" ]; then $PODMAN logs ${SERVER} >& "$LOG"; fi
+	fi
+
+	$DRYRUN $PODMAN stop ${SERVER}
+	$DRYRUN $PODMAN rm ${SERVER}
+}
+
 stop_apptainer(){
 	$DRYRUN $APPTAINER instance stop ${SERVER}
 }
@@ -314,6 +358,11 @@ test_docker(){
 	${DOCKER} logs ${SERVER} |& grep "$1"
 }
 
+test_podman(){
+	# podman logs print to stdout
+	${PODMAN} logs ${SERVER} | grep "$1"
+}
+
 test_apptainer(){
 	grep "$1" $LOG
 }
@@ -462,6 +511,10 @@ driver_docker(){
 	$DOCKER run --rm --entrypoint env ${IMAGE} | grep "CUDA_DRIVER_VERSION="
 }
 
+driver_podman(){
+	$PODMAN run --rm --entrypoint env ${IMAGE} | grep "CUDA_DRIVER_VERSION="
+}
+
 driver_apptainer(){
 	D2S=${SANDBOX}/.singularity.d/env/10-docker2singularity.sh
 	if [ -f "$D2S" ]; then
@@ -536,20 +589,33 @@ extra_docker(){
 		EXTRA="--gpus all"
 	fi
 }
+extra_podman(){
+	if [ "$DEVICE" == gpu ]; then
+		EXTRA="--device nvidia.com/gpu=all"
+	fi
+}
 extra_apptainer(){
 	if [ "$DEVICE" == gpu ]; then
 		EXTRA="--nv"
 	fi
 }
 
-if [ -n "$USEDOCKER" ]; then
+if [ "$CONTAINER" == "docker" ]; then
 	START_FN=start_docker
 	EXTRA_FN=extra_docker
 	TEST_FN=test_docker
 	STOP_FN=stop_docker
 	DRIVER_FN=driver_docker
 	COMPAT_FN=compat_docker
 	PROG_NAME=Docker
+elif [ "$CONTAINER" == "podman" ]; then
+	START_FN=start_podman
+	EXTRA_FN=extra_podman
+	TEST_FN=test_podman
+	STOP_FN=stop_podman
+	DRIVER_FN=driver_podman
+	COMPAT_FN=compat_podman
+	PROG_NAME=Podman
 else
 	START_FN=start_apptainer
 	EXTRA_FN=extra_apptainer

HeterogeneousCore/SonicTriton/src/TritonService.cc

@@ -273,12 +273,11 @@ void TritonService::preBeginJob(edm::PathsAndConsumesOfModulesBase const&, edm::
   //assemble server start command
   fallbackOpts_.command = "cmsTriton -P -1 -p " + pid_;
   fallbackOpts_.command += " -g " + fallbackOpts_.device;
+  fallbackOpts_.command += " -d " + fallbackOpts_.container;
   if (fallbackOpts_.debug)
     fallbackOpts_.command += " -c";
   if (fallbackOpts_.verbose)
     fallbackOpts_.command += " -v";
-  if (fallbackOpts_.useDocker)
-    fallbackOpts_.command += " -d";
   if (!fallbackOpts_.instanceName.empty())
     fallbackOpts_.command += " -n " + fallbackOpts_.instanceName;
   if (fallbackOpts_.retries >= 0)
@@ -434,7 +433,8 @@ void TritonService::fillDescriptions(edm::ConfigurationDescriptions& description
   fallbackDesc.addUntracked<bool>("enable", false);
   fallbackDesc.addUntracked<bool>("debug", false);
   fallbackDesc.addUntracked<bool>("verbose", false);
-  fallbackDesc.addUntracked<bool>("useDocker", false);
+  fallbackDesc.ifValue(edm::ParameterDescription<std::string>("container", "apptainer", false),
+                       edm::allowedValues<std::string>("apptainer", "docker", "podman"));
   fallbackDesc.ifValue(edm::ParameterDescription<std::string>("device", "auto", false),
                        edm::allowedValues<std::string>("auto", "cpu", "gpu"));
   fallbackDesc.addUntracked<int>("retries", -1);

HeterogeneousCore/SonicTriton/test/tritonTest_cfg.py

@@ -15,6 +15,7 @@
 allowed_modes = ["Async","PseudoAsync","Sync"]
 allowed_compression = ["none","deflate","gzip"]
 allowed_devices = ["auto","cpu","gpu"]
+allowed_containers = ["apptainer","docker","podman"]
 
 parser = ArgumentParser(formatter_class=ArgumentDefaultsHelpFormatter)
 parser.add_argument("--maxEvents", default=-1, type=int, help="Number of events to process (-1 for all)")
@@ -42,7 +43,7 @@
 parser.add_argument("--compression", default="", type=str, choices=allowed_compression, help="enable I/O compression")
 parser.add_argument("--ssl", default=False, action="store_true", help="enable SSL authentication for server communication")
 parser.add_argument("--device", default="auto", type=str.lower, choices=allowed_devices, help="specify device for fallback server")
-parser.add_argument("--docker", default=False, action="store_true", help="use Docker for fallback server")
+parser.add_argument("--container", default="apptainer", type=str.lower, choices=allowed_containers, help="specify container for fallback server")
 parser.add_argument("--tries", default=0, type=int, help="number of retries for failed request")
 options = parser.parse_args()
 
@@ -74,7 +75,7 @@
 
 process.TritonService.verbose = options.verbose or options.verboseService or options.verboseDiscovery
 process.TritonService.fallback.verbose = options.verbose or options.verboseServer
-process.TritonService.fallback.useDocker = options.docker
+process.TritonService.fallback.container = options.container
 process.TritonService.fallback.device = options.device
 if len(options.fallbackName)>0:
     process.TritonService.fallback.instanceBaseName = options.fallbackName