Merge latest development changes to main branch (#79)

* Cleanup: Remove unused code

* Use Golang duration parser for 'interval' and 'duration'
 in main config

* Update handling of LIKWID headers. Download only if not already present in the system. Fixes #73

* Units with cc-units (#64)

* Add option to normalize units with cc-unit

* Add unit conversion to router

* Add option to change unit prefix in the router

* Add to MetricRouter README

* Add order of operations in router to README

* Use second add_tags/del_tags only if metric gets renamed

* Skip disks in DiskstatCollector that have size=0

* Check readability of sensor files in TempCollector

* Fix for --once option

* Rename `cpu` type to `hwthread` (#69)

* Rename 'cpu' type to 'hwthread' to avoid naming clashes with MetricStore and CC-Webfrontend

* Collectors in parallel (#74)

* Provide info to CollectorManager whether the collector can be executed in parallel with others

* Split serial and parallel collectors. Read in parallel first

* Update NvidiaCollector with new metrics, MIG and NvLink support (#75)

* CC topology module update (#76)

* Rename CPU to hardware thread, write some comments

* Do renaming in other parts

* Remove CpuList and SocketList function from metricCollector. Available in ccTopology

* Option to use MIG UUID as subtype-id in NvidiaCollector

* Option to use MIG slice name as subtype-id in NvidiaCollector

* MetricRouter: Fix JSON in README

* Fix for Github Action to really use the selected version

* Remove Ganglia installation in runonce Action and add Go 1.18

* Fix daemon options in init script

* Add separate go.mod files to use it with deprecated 1.16

* Minor updates for Makefiles

* fix string comparison

* AMD ROCm SMI collector (#77)

* Add collector for AMD ROCm SMI metrics

* Fix import path

* Fix imports

* Remove Board Number

* store GPU index explicitly

* Remove board number from description

* Use http instead of ftp to download likwid

* Fix serial number in rocmCollector

* Improved http sink (#78)

* automatic flush in NatsSink

* tweak default options of HttpSink

* shorter cirt. section and retries for HttpSink

* fix error handling

* Remove file added by mistake.

* Use http instead of ftp to download likwid

* Fix serial number in rocmCollector

Co-authored-by: Thomas Roehl <thomas.roehl@fau.de>

Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
Co-authored-by: Lou <lou.knauer@gmx.de>

collectors/collectorManager.go

@@ -14,39 +14,43 @@ import (
 // Map of all available metric collectors
 var AvailableCollectors = map[string]MetricCollector{
 
-	"likwid":           new(LikwidCollector),
-	"loadavg":          new(LoadavgCollector),
-	"memstat":          new(MemstatCollector),
-	"netstat":          new(NetstatCollector),
-	"ibstat":           new(InfinibandCollector),
-	"lustrestat":       new(LustreCollector),
-	"cpustat":          new(CpustatCollector),
-	"topprocs":         new(TopProcsCollector),
-	"nvidia":           new(NvidiaCollector),
-	"customcmd":        new(CustomCmdCollector),
-	"iostat":           new(IOstatCollector),
-	"diskstat":         new(DiskstatCollector),
-	"tempstat":         new(TempCollector),
-	"ipmistat":         new(IpmiCollector),
-	"gpfs":             new(GpfsCollector),
-	"cpufreq":          new(CPUFreqCollector),
-	"cpufreq_cpuinfo":  new(CPUFreqCpuInfoCollector),
-	"nfs3stat":         new(Nfs3Collector),
-	"nfs4stat":         new(Nfs4Collector),
-	"numastats":        new(NUMAStatsCollector),
-	"beegfs_meta":      new(BeegfsMetaCollector),
-	"beegfs_storage":   new(BeegfsStorageCollector),
+	"likwid":          new(LikwidCollector),
+	"loadavg":         new(LoadavgCollector),
+	"memstat":         new(MemstatCollector),
+	"netstat":         new(NetstatCollector),
+	"ibstat":          new(InfinibandCollector),
+	"lustrestat":      new(LustreCollector),
+	"cpustat":         new(CpustatCollector),
+	"topprocs":        new(TopProcsCollector),
+	"nvidia":          new(NvidiaCollector),
+	"customcmd":       new(CustomCmdCollector),
+	"iostat":          new(IOstatCollector),
+	"diskstat":        new(DiskstatCollector),
+	"tempstat":        new(TempCollector),
+	"ipmistat":        new(IpmiCollector),
+	"gpfs":            new(GpfsCollector),
+	"cpufreq":         new(CPUFreqCollector),
+	"cpufreq_cpuinfo": new(CPUFreqCpuInfoCollector),
+	"nfs3stat":        new(Nfs3Collector),
+	"nfs4stat":        new(Nfs4Collector),
+	"numastats":       new(NUMAStatsCollector),
+	"beegfs_meta":     new(BeegfsMetaCollector),
+	"beegfs_storage":  new(BeegfsStorageCollector),
+	"rocm_smi":        new(RocmSmiCollector),
 }
 
 // Metric collector manager data structure
 type collectorManager struct {
-	collectors []MetricCollector          // List of metric collectors to use
-	output     chan lp.CCMetric           // Output channels
-	done       chan bool                  // channel to finish / stop metric collector manager
-	ticker     mct.MultiChanTicker        // periodically ticking once each interval
-	duration   time.Duration              // duration (for metrics that measure over a given duration)
-	wg         *sync.WaitGroup            // wait group for all goroutines in cc-metric-collector
-	config     map[string]json.RawMessage // json encoded config for collector manager
+	collectors   []MetricCollector          // List of metric collectors to read in parallel
+	serial       []MetricCollector          // List of metric collectors to read serially
+	output       chan lp.CCMetric           // Output channels
+	done         chan bool                  // channel to finish / stop metric collector manager
+	ticker       mct.MultiChanTicker        // periodically ticking once each interval
+	duration     time.Duration              // duration (for metrics that measure over a given duration)
+	wg           *sync.WaitGroup            // wait group for all goroutines in cc-metric-collector
+	config       map[string]json.RawMessage // json encoded config for collector manager
+	collector_wg sync.WaitGroup             // internally used wait group for the parallel reading of collector
+	parallel_run bool                       // Flag whether the collectors are currently read in parallel
 }
 
 // Metric collector manager access functions
@@ -66,6 +70,7 @@ type CollectorManager interface {
 // Initialization is done for all configured collectors
 func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error {
 	cm.collectors = make([]MetricCollector, 0)
+	cm.serial = make([]MetricCollector, 0)
 	cm.output = nil
 	cm.done = make(chan bool)
 	cm.wg = wg
@@ -100,7 +105,11 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
 			continue
 		}
 		cclog.ComponentDebug("CollectorManager", "ADD COLLECTOR", collector.Name())
-		cm.collectors = append(cm.collectors, collector)
+		if collector.Parallel() {
+			cm.collectors = append(cm.collectors, collector)
+		} else {
+			cm.serial = append(cm.serial, collector)
+		}
 	}
 	return nil
 }
@@ -116,6 +125,10 @@ func (cm *collectorManager) Start() {
 		// Collector manager is done
 		done := func() {
 			// close all metric collectors
+			if cm.parallel_run {
+				cm.collector_wg.Wait()
+				cm.parallel_run = false
+			}
 			for _, c := range cm.collectors {
 				c.Close()
 			}
@@ -130,7 +143,26 @@ func (cm *collectorManager) Start() {
 				done()
 				return
 			case t := <-tick:
+				cm.parallel_run = true
 				for _, c := range cm.collectors {
+					// Wait for done signal or execute the collector
+					select {
+					case <-cm.done:
+						done()
+						return
+					default:
+						// Read metrics from collector c via goroutine
+						cclog.ComponentDebug("CollectorManager", c.Name(), t)
+						cm.collector_wg.Add(1)
+						go func(myc MetricCollector) {
+							myc.Read(cm.duration, cm.output)
+							cm.collector_wg.Done()
+						}(c)
+					}
+				}
+				cm.collector_wg.Wait()
+				cm.parallel_run = false
+				for _, c := range cm.serial {
 					// Wait for done signal or execute the collector
 					select {
 					case <-cm.done: