Fix regex matching rules // add logs if spmix_appdir is not mounted

Author: gwangmu

src/pmix/PMIxHook.cpp

@@ -160,8 +160,8 @@ void PMIxHook::derivePathsFromScontrol() {
     auto ss = std::stringstream{output};
     auto line = std::string{};
     auto matches = boost::smatch{};
-    auto reSlurmdSpoolDir = boost::regex{"^SlurmdSpoolDir *= (.*)$"};
-    auto reTmpFS = boost::regex{"^TmpFS *= (.*)$"};
+    auto reSlurmdSpoolDir = boost::regex{"^SlurmdSpoolDir *= *([^ ]*).*"};
+    auto reTmpFS = boost::regex{"^TmpFS *= *([^ ]*).*"};
 
     while (std::getline(ss, line)) {
         if (boost::regex_match(line, matches, reSlurmdSpoolDir)) {
@@ -178,10 +178,15 @@ void PMIxHook::derivePathsFromScontrol() {
     // Check the sanity of the derived paths.
     boost::system::error_code ec;
 
-    if (!boost::filesystem::is_directory(pathSlurmdSpoolDir, ec)) 
-        SARUS_THROW_ERROR("SlurmdSpoolDir is not a directory");
-    if (!boost::filesystem::is_directory(pathTmpFS, ec)) 
-        SARUS_THROW_ERROR("TmpFS is not a directory");
+    if (!boost::filesystem::is_directory(pathSlurmdSpoolDir, ec)) {
+        auto msg = boost::format("SlurmdSpoolDir is not a directory (%s)") % pathSlurmdSpoolDir;
+        SARUS_THROW_ERROR(msg.str());
+    }
+
+    if (!boost::filesystem::is_directory(pathTmpFS, ec)) {
+        auto msg = boost::format("TmpFS is not a directory (%s)") % pathTmpFS;
+        SARUS_THROW_ERROR(msg.str());
+    }
 
     log("Derived paths from 'scontrol'", libsarus::LogLevel::INFO);
 }
@@ -201,16 +206,22 @@ void PMIxHook::mountPMIxDirectories() {
     pathAppdirJobStep += ("_" + envSlurmJobID);
     pathAppdirJobStep += ("." + envSlurmStepID);
 
-    try {
-        if (!envSlurmJobUID.empty() && boost::filesystem::is_directory(pathAppdirUIDJobStep)) {
+    if (!envSlurmJobUID.empty() && boost::filesystem::is_directory(pathAppdirUIDJobStep)) {
+        try {
             libsarus::mount::validatedBindMount(pathAppdirUIDJobStep, pathAppdirUIDJobStep, userIdentity, pathRootFS, mount_flags);
-            log(boost::format("Mounted: %s") % pathAppdirUIDJobStep, libsarus::LogLevel::INFO);
-        } else {
+            log(boost::format("Mounted spmix_appdir: %s") % pathAppdirUIDJobStep, libsarus::LogLevel::INFO);
+        } catch (...) {
+            // Respecfully ignore. ("nofail")
+            log(boost::format("Cannot mount spmix_appdir: %s") % pathAppdirUIDJobStep, libsarus::LogLevel::INFO);
+        }
+    } else {
+        try {
             libsarus::mount::validatedBindMount(pathAppdirJobStep, pathAppdirJobStep, userIdentity, pathRootFS, mount_flags);
-            log(boost::format("Mounted: %s") % pathAppdirJobStep, libsarus::LogLevel::INFO);
+            log(boost::format("Mounted spmix_appdir: %s") % pathAppdirJobStep, libsarus::LogLevel::INFO);
+        } catch (...) {
+            // Respecfully ignore. ("nofail")
+            log(boost::format("Cannot mount spmix_appdir: %s") % pathAppdirJobStep, libsarus::LogLevel::INFO);
         }
-    } catch (...) {
-        // Respecfully ignore. ("nofail")
     }
 
     // Mount "pmix".

tests/assets/scontrol-mock

@@ -3,239 +3,8 @@
 if [[ "$1" == "show" ]] && [[ "$2" == "config" ]]; then
   cat <<EOF
 Configuration data as of 2025-09-16T10:59:04
-AccountingStorageBackupHost = (null)
-AccountingStorageEnforce = associations,limits,qos
-AccountingStorageHost   = zinal-slurmdbd.tds.cscs.ch
-AccountingStorageExternalHost = (null)
-AccountingStorageParameters = (null)
-AccountingStoragePort   = 6819
-AccountingStorageTRES   = cpu,mem,energy,node,billing,fs/disk,vmem,pages,gres/gpu,gres/gpumem,gres/gpuutil
-AccountingStorageType   = accounting_storage/slurmdbd
-AccountingStorageUser   = N/A
-AccountingStoreFlags    = (null)
-AcctGatherEnergyType    = acct_gather_energy/pm_counters
-AcctGatherFilesystemType = (null)
-AcctGatherInterconnectType = (null)
-AcctGatherNodeFreq      = 0 sec
-AcctGatherProfileType   = (null)
-AllowSpecResourcesUsage = No
-AuthAltTypes            = auth/jwt
-AuthAltParameters       = jwks=/etc/slurm_extra/jwks.json,userclaimfield=preferred_username
-AuthInfo                = (null)
-AuthType                = auth/munge
-BatchStartTimeout       = 10 sec
-BcastExclude            = /lib,/usr/lib,/lib64,/usr/lib64
-BcastParameters         = (null)
-BOOT_TIME               = 2025-09-01T14:17:43
-BurstBufferType         = (null)
-CliFilterPlugins        = (null)
-ClusterName             = zinal
-CommunicationParameters = (null)
-CompleteWait            = 0 sec
-CpuFreqDef              = Unknown
-CpuFreqGovernors        = OnDemand,Performance,UserSpace
-CredType                = cred/munge
-DebugFlags              = (null)
-DefMemPerNode           = UNLIMITED
-DependencyParameters    = (null)
-DisableRootJobs         = No
-EioTimeout              = 60
-EnforcePartLimits       = NO
-EpilogMsgTime           = 2000 usec
-FairShareDampeningFactor = 1
-FederationParameters    = (null)
-FirstJobId              = 1
-GetEnvTimeout           = 2 sec
-GresTypes               = (null)
-GpuFreqDef              = (null)
-GroupUpdateForce        = 1
-GroupUpdateTime         = 600 sec
-HASH_VAL                = Different Ours=0xe7c32fa3 Slurmctld=0xf73d113
-HashPlugin              = hash/k12
-HealthCheckInterval     = 0 sec
-HealthCheckNodeState    = ANY
-HealthCheckProgram      = (null)
-InactiveLimit           = 0 sec
-InteractiveStepOptions  = --interactive --preserve-env --pty $SHELL
-JobAcctGatherFrequency  = task=30,energy=30,filesystem=30
-JobAcctGatherType       = jobacct_gather/linux
-JobAcctGatherParams     = (null)
-JobCompHost             = localhost
-JobCompLoc              = /etc/slurm/rdkafka.conf
-JobCompParams           = flush_timeout=200,poll_interval=3,requeue_on_msg_timeout,topic=raw.slurm.jobcomp.zinal
-JobCompPort             = 0
-JobCompType             = jobcomp/kafka
-JobCompUser             = root
-JobContainerType        = (null)
-JobDefaults             = (null)
-JobFileAppend           = 0
-JobRequeue              = 1
-JobSubmitPlugins        = (null)
-KillOnBadExit           = 0
-KillWait                = 30 sec
-LaunchParameters        = (null)
-Licenses                = (null)
-LogTimeFormat           = iso8601_ms
-MailDomain              = (null)
-MailProg                = /bin/mail
-MaxArraySize            = 1001
-MaxBatchRequeue         = 5
-MaxDBDMsgs              = 20096
-MaxJobCount             = 10000
-MaxJobId                = 67043328
-MaxMemPerNode           = UNLIMITED
-MaxNodeCount            = 24
-MaxStepCount            = 40000
-MaxTasksPerNode         = 512
-MCSPlugin               = (null)
-MCSParameters           = (null)
-MessageTimeout          = 30 sec
-MinJobAge               = 300 sec
-MpiDefault              = (null)
-MpiParams               = (null)
-NEXT_JOB_ID             = 243
-NodeFeaturesPlugins     = (null)
-OverTimeLimit           = 0 min
-PluginDir               = /usr/lib64/slurm
-PlugStackConfig         = (null)
-PreemptMode             = OFF
-PreemptParameters       = (null)
-PreemptType             = (null)
-PreemptExemptTime       = 00:00:00
-PrEpParameters          = (null)
-PrEpPlugins             = prep/script
-PriorityParameters      = (null)
-PrioritySiteFactorParameters = (null)
-PrioritySiteFactorPlugin = (null)
-PriorityDecayHalfLife   = 40-00:00:00
-PriorityCalcPeriod      = 00:05:00
-PriorityFavorSmall      = No
-PriorityFlags           = NO_NORMAL_ALL
-PriorityMaxAge          = 14-00:00:00
-PriorityUsageResetPeriod = QUARTERLY
-PriorityType            = priority/multifactor
-PriorityWeightAge       = 172800
-PriorityWeightAssoc     = 100000
-PriorityWeightFairShare = 259200
-PriorityWeightJobSize   = 0
-PriorityWeightPartition = 172800
-PriorityWeightQOS       = 500000
-PriorityWeightTRES      = (null)
-PrivateData             = none
-ProctrackType           = proctrack/cgroup
-Prolog[0]               = /etc/slurm/node_prolog.d/*
-PrologEpilogTimeout     = 65534
-PrologFlags             = Alloc,Contain,X11
-PropagatePrioProcess    = 0
-PropagateResourceLimits = ALL
-PropagateResourceLimitsExcept = (null)
-RebootProgram           = (null)
-ReconfigFlags           = (null)
-RequeueExit             = (null)
-RequeueExitHold         = (null)
-ResumeFailProgram       = (null)
-ResumeProgram           = (null)
-ResumeRate              = 300 nodes/min
-ResumeTimeout           = 60 sec
-ResvEpilog              = (null)
-ResvOverRun             = 0 min
-ResvProlog              = (null)
-ReturnToService         = 1
-SchedulerParameters     = (null)
-SchedulerTimeSlice      = 30 sec
-SchedulerType           = sched/backfill
-ScronParameters         = (null)
-SelectType              = select/cons_tres
-SelectTypeParameters    = CR_CORE_MEMORY
-SlurmUser               = root(0)
-SlurmctldAddr           = (null)
-SlurmctldDebug          = verbose
-SlurmctldHost[0]        = zinal-slurmctl(zinal-slurmctl.tds.cscs.ch)
-SlurmctldLogFile        = /var/log/slurmctld.log
-SlurmctldPort           = 6817
-SlurmctldSyslogDebug    = (null)
-SlurmctldPrimaryOffProg = (null)
-SlurmctldPrimaryOnProg  = (null)
-SlurmctldTimeout        = 120 sec
-SlurmctldParameters     = enable_configless,enable_stepmgr
-SlurmdDebug             = debug
-SlurmdLogFile           = /var/log/slurmd.log
-SlurmdParameters        = (null)
-SlurmdPidFile           = /var/run/slurmd.pid
-SlurmdPort              = 6818
-SlurmdSpoolDir          = /tmp/spool/slurmd
-SlurmdSyslogDebug       = (null)
-SlurmdTimeout           = 300 sec
-SlurmdUser              = root(0)
-SlurmSchedLogFile       = (null)
-SlurmSchedLogLevel      = 0
-SlurmctldPidFile        = /var/run/slurmctld.pid
-SLURM_CONF              = /etc/slurm/slurm.conf
-SLURM_VERSION           = 24.05.8
-SrunEpilog              = (null)
-SrunPortRange           = 0-0
-SrunProlog              = (null)
-StateSaveLocation       = /var/spool/slurmctld
-SuspendExcNodes         = (null)
-SuspendExcParts         = (null)
-SuspendExcStates        = (null)
-SuspendProgram          = (null)
-SuspendRate             = 60 nodes/min
-SuspendTime             = INFINITE
-SuspendTimeout          = 30 sec
-SwitchParameters        = (null)
-SwitchType              = (null)
-TaskEpilog              = (null)
-TaskPlugin              = task/affinity
-TaskPluginParam         = (null type)
-TaskProlog              = (null)
-TCPTimeout              = 2 sec
-TLSParameters           = (null)
-TLSType                 = tls/none
-TmpFS                   = /tmp
-TopologyParam           = (null)
-TopologyPlugin          = topology/default
-TrackWCKey              = No
-TreeWidth               = 65533
-UsePam                  = No
-UnkillableStepProgram   = (null)
-UnkillableStepTimeout   = 150 sec
-VSizeFactor             = 0 percent
-WaitTime                = 0 sec
-X11Parameters           = (null)
-
-Cgroup Support Configuration:
-AllowedRAMSpace         = 100.0%
-AllowedSwapSpace        = 0.0%
-CgroupMountpoint        = /sys/fs/cgroup
-CgroupPlugin            = autodetect
-ConstrainCores          = yes
-ConstrainDevices        = no
-ConstrainRAMSpace       = yes
-ConstrainSwapSpace      = no
-EnableControllers       = no
-IgnoreSystemd           = no
-IgnoreSystemdOnFailure  = no
-MaxRAMPercent           = 100.0%
-MaxSwapPercent          = 100.0%
-MemorySwappiness        = (null)
-MinRAMSpace             = 30MB
-SystemdTimeout          = 1000 ms
-
-MPI Plugins Configuration:
-PMIxCliTmpDirBase       = (null)
-PMIxCollFence           = (null)
-PMIxDebug               = 0
-PMIxDirectConn          = yes
-PMIxDirectConnEarly     = no
-PMIxDirectConnUCX       = no
-PMIxDirectSameArch      = no
-PMIxEnv                 = (null)
-PMIxFenceBarrier        = no
-PMIxNetDevicesUCX       = (null)
-PMIxTimeout             = 300
-PMIxTlsUCX              = (null)
-
+SlurmdSpoolDir          = /tmp/spool/slurmd (default)
+TmpFS                   = /tmp (default)
 Slurmctld(primary) at zinal-slurmctl is UP
 EOF
 fi