Merge pull request #39 from intel/prep2120

changes for 2.12.0

RELEASE_NOTES

@@ -6,6 +6,13 @@ Fully Supported Platforms
 - Operating Systems: Ubuntu 18.04, 20.04, 22.04, 24.04, CentOS 7, Amazon Linux 2, Debian 11, RHEL 9, Rocky Linux 8
   Note: svr-info may work on other micro-architectures and Linux distributions, but has not been thoroughly tested
 
+2.12.0
+Features Added/Changed
+- Gaudi devices enumerated
+- GNR-D vRAN accelerators enumerated
+- Minor modification to Excel 'brief' report's System Summary field
+- Show ELC thresholds for Compute Die(s)
+
 2.11.1
 Bugs Fixed
 - Fix frequency benchmark on GNR

cmd/orchestrator/resources/collector_reports.yaml.tmpl

@@ -290,11 +290,7 @@ commands:
 
           # Print metrics
           echo -n "$socket_id,$die,$die_type,$min_ratio,$max_ratio,$eff_latency_ctrl_ratio,"
-          if [ $die_type == "IO" ] ; then
-              echo "$eff_latency_ctrl_low_threshold,$eff_latency_ctrl_high_threshold,$eff_latency_ctrl_high_threshold_enable"
-          else
-              echo ",,"
-          fi
+          echo "$eff_latency_ctrl_low_threshold,$eff_latency_ctrl_high_threshold,$eff_latency_ctrl_high_threshold_enable"
       }
 
       # Print CSV header
@@ -383,8 +379,20 @@ commands:
         done
     superuser: true
     parallel: true
+  - label: gaudi info
+    command: hl-smi -Q module_id,serial,bus_id,driver_version -f csv
+    superuser: true
+    parallel: true
+  - label: gaudi firmware
+    command: hl-smi --fw-version
+    superuser: true
+    parallel: true
+  - label: gaudi numa
+    command: hl-smi topo -N
+    superuser: true
+    parallel: true
   - label: lspci bits
-    command: lspci -s $(lspci | grep 325b | awk 'NR==1{{print $1}}') -xxx |  awk '$1 ~ /^90/{{print $9 $8 $7 $6; exit}}'
+    command: lspci -s $(lspci | grep 325b | awk 'NR==1{print $1}') -xxx |  awk '$1 ~ /^90/{print $9 $8 $7 $6; exit}'
     superuser: true
     parallel: true
   - label: lspci devices

cmd/reporter/report.go

@@ -65,6 +65,7 @@ func NewConfigurationReport(sources []*Source, CPUdb cpudb.CPUDB) (report *Repor
 			newFilesystemTable(sources, Storage),
 
 			newGPUTable(sources, GPU),
+			newGaudiTable(sources, GPU),
 
 			newCXLDeviceTable(sources, CXL),
 
@@ -112,7 +113,7 @@ func NewBriefReport(sources []*Source, fullReport *Report, CPUdb cpudb.CPUDB) (r
 			fullReport.findTable("Power"),
 			tableEfficiencyLatencyControlSummary,
 			newVulnerabilitySummaryTable(fullReport.findTable("Vulnerability"), Security),
-			newMarketingClaimTable(fullReport, tableNicSummary, tableDiskSummary, tableAcceleratorSummary, NoCategory),
+			newMarketingClaimTable(fullReport, tableNicSummary, tableDiskSummary, NoCategory),
 		}...,
 	)
 	// TODO: remove check when code is stable

cmd/reporter/report_tables.go

@@ -34,15 +34,15 @@ import (
  *   nicSummaryTable() - has info derived from the full table, but is presented in summary format
  */
 
-func newMarketingClaimTable(fullReport *Report, tableNicSummary *Table, tableDiskSummary *Table, tableAcceleratorSummary *Table, category TableCategory) (table *Table) {
+func newMarketingClaimTable(fullReport *Report, tableNicSummary *Table, tableDiskSummary *Table, category TableCategory) (table *Table) {
 	table = &Table{
 		Name:          "Marketing Claim",
 		Category:      category,
 		AllHostValues: []HostValues{},
 	}
-	// BASELINE: 1-node, 2x Intel® Xeon® <SKU, processor>, xx cores, 100W TDP, HT On/Off?, Turbo On/Off?, NUMA xxx,  Integrated Accelerators Available [used]: xxx, Total Memory xxx GB (xx slots/ xx GB/ xxxx MHz [run @ xxxx MHz] ), <BIOS version>, <ucode version>, <OS Version>, <kernel version>. Software: WORKLOAD+VERSION, COMPILER, LIBRARIES, OTHER_SW. Test by Intel as of <mm/dd/yy>.
-	template := "1-node, %sx %s, %s cores, %s TDP, HT %s, Turbo %s, NUMA %s, Integrated Accelerators Available [used]: %s, Total Memory %s, BIOS %s, microcode %s, %s, %s, %s, %s. Software: WORKLOAD+VERSION, COMPILER, LIBRARIES, OTHER_SW. Test by Intel as of %s."
-	var date, socketCount, cpuModel, coreCount, tdp, htOnOff, turboOnOff, numaNodes, installedMem, biosVersion, uCodeVersion, nics, disks, operatingSystem, kernelVersion string
+	// BASELINE: 1-node, 2x Intel® Xeon® <SKU, processor>, xx cores, 100W TDP, HT On/Off?, Turbo On/Off?, Total Memory xxx GB (xx slots/ xx GB/ xxxx MHz [run @ xxxx MHz] ), <BIOS version>, <ucode version>, <OS Version>, <kernel version>. Test by Intel as of <mm/dd/yy>.
+	template := "1-node, %sx %s, %s cores, %s TDP, HT %s, Turbo %s, Total Memory %s, BIOS %s, microcode %s, %s, %s, %s, %s. Test by Intel as of %s."
+	var date, socketCount, cpuModel, coreCount, tdp, htOnOff, turboOnOff, installedMem, biosVersion, uCodeVersion, nics, disks, operatingSystem, kernelVersion string
 
 	for sourceIdx, source := range fullReport.Sources {
 		var hostValues = HostValues{
@@ -78,16 +78,14 @@ func newMarketingClaimTable(fullReport *Report, tableNicSummary *Table, tableDis
 		} else {
 			turboOnOff = "?"
 		}
-		numaNodes, _ = fullReport.findTable("CPU").getValue(sourceIdx, "NUMA Nodes")
-		accelerators, _ := tableAcceleratorSummary.getValue(sourceIdx, "Accelerators Available [used]")
 		installedMem, _ = fullReport.findTable("Memory").getValue(sourceIdx, "Installed Memory")
 		biosVersion, _ = fullReport.findTable("BIOS").getValue(sourceIdx, "Version")
 		uCodeVersion, _ = fullReport.findTable("Operating System").getValue(sourceIdx, "Microcode")
 		nics, _ = tableNicSummary.getValue(sourceIdx, "NIC")
 		disks, _ = tableDiskSummary.getValue(sourceIdx, "Disk")
 		operatingSystem, _ = fullReport.findTable("Operating System").getValue(sourceIdx, "OS")
 		kernelVersion, _ = fullReport.findTable("Operating System").getValue(sourceIdx, "Kernel")
-		claim := fmt.Sprintf(template, socketCount, cpuModel, coreCount, tdp, htOnOff, turboOnOff, numaNodes, accelerators, installedMem, biosVersion, uCodeVersion, nics, disks, operatingSystem, kernelVersion, date)
+		claim := fmt.Sprintf(template, socketCount, cpuModel, coreCount, tdp, htOnOff, turboOnOff, installedMem, biosVersion, uCodeVersion, nics, disks, operatingSystem, kernelVersion, date)
 		hostValues.Values = append(hostValues.Values, []string{claim})
 		table.AllHostValues = append(table.AllHostValues, hostValues)
 	}
@@ -1131,6 +1129,133 @@ func newGPUTable(sources []*Source, category TableCategory) (table *Table) {
 	return
 }
 
+type Gaudi struct {
+	ModuleID      string
+	SerialNumber  string
+	BusID         string
+	DriverVersion string
+	EROM          string
+	CPLD          string
+	SPI           string
+	NUMA          string
+}
+
+func newGaudiTable(sources []*Source, category TableCategory) (table *Table) {
+	table = &Table{
+		Name:          "Gaudi",
+		Category:      category,
+		AllHostValues: []HostValues{},
+	}
+	for _, source := range sources {
+		gaudis := []Gaudi{}
+		for i, line := range source.getCommandOutputLines("gaudi info") {
+			if line == "" || i == 0 { // skip blank lines and header
+				continue
+			}
+			fields := strings.Split(line, ", ")
+			if len(fields) != 4 {
+				log.Printf("unexpected number of fields in gaudi info output")
+				continue
+			}
+			gaudis = append(gaudis, Gaudi{ModuleID: fields[0], SerialNumber: fields[1], BusID: fields[2], DriverVersion: fields[3]})
+		}
+		// sort the gaudis by module ID
+		sort.Slice(gaudis, func(i, j int) bool {
+			return gaudis[i].ModuleID < gaudis[j].ModuleID
+		})
+		// get NUMA affinity
+		numaAffinities := source.valsArrayFromRegexSubmatch("gaudi numa", `^(\d+)\s+(\d+)$`)
+		if len(numaAffinities) != len(gaudis) {
+			log.Printf("number of gaudis in gaudi info and numa output do not match")
+			return nil
+		}
+		for i, numaAffinity := range numaAffinities {
+			gaudis[i].NUMA = numaAffinity[1]
+		}
+		// get firmware versions
+		reDevice := regexp.MustCompile(`^\[(\d+)] AIP \(accel\d+\) (.*)$`)
+		reErom := regexp.MustCompile(`^erom$`)
+		reCpld := regexp.MustCompile(`^cpld$`)
+		rePreboot := regexp.MustCompile(`^preboot$`)
+		reComponent := regexp.MustCompile(`^component\s+:\s+hl-gaudi\d-(.*)-sec-\d+`)
+		reCpldComponent := regexp.MustCompile(`^component\s+:\s+(0x[0-9a-fA-F]+\.[0-9a-fA-F]+)$`)
+		deviceIdx := -1
+		state := -1
+		for _, line := range source.getCommandOutputLines("gaudi firmware") {
+			if line == "" {
+				continue
+			}
+			match := reDevice.FindStringSubmatch(line)
+			if match != nil {
+				var err error
+				deviceIdx, err = strconv.Atoi(match[1])
+				if err != nil {
+					log.Printf("failed to parse device index")
+					return nil
+				}
+				if deviceIdx >= len(gaudis) {
+					log.Printf("device index out of range")
+					return nil
+				}
+				continue
+			}
+			if deviceIdx == -1 {
+				continue
+			}
+			if reErom.FindString(line) != "" {
+				state = 0
+				continue
+			}
+			if reCpld.FindString(line) != "" {
+				state = 1
+				continue
+			}
+			if rePreboot.FindString(line) != "" {
+				state = 2
+				continue
+			}
+			if state != -1 {
+				switch state {
+				case 0:
+					match := reComponent.FindStringSubmatch(line)
+					if match != nil {
+						gaudis[deviceIdx].EROM = match[1]
+					}
+				case 1:
+					match := reCpldComponent.FindStringSubmatch(line)
+					if match != nil {
+						gaudis[deviceIdx].CPLD = match[1]
+					}
+				case 2:
+					match := reComponent.FindStringSubmatch(line)
+					if match != nil {
+						gaudis[deviceIdx].SPI = match[1]
+					}
+				}
+				state = -1
+			}
+		}
+		var hostValues = HostValues{
+			Name: source.getHostname(),
+			ValueNames: []string{
+				"Module ID",
+				"Serial Number",
+				"Bus ID",
+				"Driver Version",
+				"EROM",
+				"CPLD",
+				"SPI",
+				"NUMA Node",
+			},
+		}
+		for _, gaudi := range gaudis {
+			hostValues.Values = append(hostValues.Values, []string{gaudi.ModuleID, gaudi.SerialNumber, gaudi.BusID, gaudi.DriverVersion, gaudi.EROM, gaudi.CPLD, gaudi.SPI, gaudi.NUMA})
+		}
+		table.AllHostValues = append(table.AllHostValues, hostValues)
+	}
+	return
+}
+
 func newNICTable(sources []*Source, category TableCategory) (table *Table) {
 	table = &Table{
 		Name:          "NIC",
@@ -1140,7 +1265,7 @@ func newNICTable(sources []*Source, category TableCategory) (table *Table) {
 	idxNicName := 0
 	idxNicModel := 1
 	for _, source := range sources {
-		nicsInfo := source.valsArrayFromRegexSubmatch("lshw", `^pci.*? (\S+)\s+network\s+(\S.*?)\s+\[\w+:\w+]$`)
+		nicsInfo := source.valsArrayFromRegexSubmatch("lshw", `^\S+\s+(\S+)\s+network\s+([^\[]+?)(?:\s+\[.*\])?$`)
 		nicsInfo = append(nicsInfo, source.valsArrayFromRegexSubmatch("lshw", `^usb.*? (\S+)\s+network\s+(\S.*?)$`)...)
 		var nics [][]string
 		for _, nic := range nicsInfo {

cmd/reporter/resources/accelerators.yaml

@@ -32,3 +32,9 @@
   devid: 37C8
   full_name: Intel Quick Assist Technology
   description: accelerates data encryption and compression for applications from networking to enterprise, cloud to storage, and content delivery to database
+
+- name: vRAN Boost
+  mfgid: 8086
+  devid: 57C2
+  full_name: Intel vRAN Boost Accelerator
+  description: accelerates vRAN workloads

go.mod

@@ -1,6 +1,8 @@
 module github.com/intel/svr-info
 
-go 1.22
+go 1.22.0
+
+toolchain go1.23.0
 
 replace github.com/intel/svr-info/internal/core => ./internal/core
 
@@ -21,29 +23,29 @@ require (
 	github.com/deckarep/golang-set/v2 v2.6.0
 	github.com/google/go-cmp v0.6.0
 	github.com/hyperjumptech/grule-rule-engine v1.15.0
-	github.com/intel/svr-info/internal/commandfile v0.0.0-00010101000000-000000000000
-	github.com/intel/svr-info/internal/core v0.0.0-00010101000000-000000000000
-	github.com/intel/svr-info/internal/cpudb v0.0.0-20240202173944-01aa39f167b4
-	github.com/intel/svr-info/internal/msr v0.0.0-00010101000000-000000000000
-	github.com/intel/svr-info/internal/progress v0.0.0-00010101000000-000000000000
-	github.com/intel/svr-info/internal/target v0.0.0-00010101000000-000000000000
-	github.com/intel/svr-info/internal/util v0.0.0-00010101000000-000000000000
+	github.com/intel/svr-info/internal/commandfile v0.0.0-20240826225705-4df592082b12
+	github.com/intel/svr-info/internal/core v0.0.0-20240826225705-4df592082b12
+	github.com/intel/svr-info/internal/cpudb v0.0.0-20240826225705-4df592082b12
+	github.com/intel/svr-info/internal/msr v0.0.0-20240826225705-4df592082b12
+	github.com/intel/svr-info/internal/progress v0.0.0-20240826225705-4df592082b12
+	github.com/intel/svr-info/internal/target v0.0.0-20240826225705-4df592082b12
+	github.com/intel/svr-info/internal/util v0.0.0-20240826225705-4df592082b12
 	github.com/xuri/excelize/v2 v2.8.1
-	golang.org/x/exp v0.0.0-20240409090435-93d18d7e34b8
-	golang.org/x/term v0.23.0
-	golang.org/x/text v0.17.0
+	golang.org/x/exp v0.0.0-20241004190924-225e2abe05e6
+	golang.org/x/term v0.25.0
+	golang.org/x/text v0.19.0
 	gopkg.in/yaml.v2 v2.4.0
 )
 
 require (
-	dario.cat/mergo v1.0.0 // indirect
-	github.com/Microsoft/go-winio v0.6.1 // indirect
+	dario.cat/mergo v1.0.1 // indirect
+	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/ProtonMail/go-crypto v1.0.0 // indirect
 	github.com/antlr/antlr4/runtime/Go/antlr v1.4.10 // indirect
 	github.com/bmatcuk/doublestar v1.3.4 // indirect
-	github.com/cloudflare/circl v1.3.7 // indirect
+	github.com/cloudflare/circl v1.4.0 // indirect
 	github.com/creasty/defaults v1.8.0 // indirect
-	github.com/cyphar/filepath-securejoin v0.2.4 // indirect
+	github.com/cyphar/filepath-securejoin v0.3.3 // indirect
 	github.com/emirpasic/gods v1.18.1 // indirect
 	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
 	github.com/go-git/go-billy/v5 v5.5.0 // indirect
@@ -55,20 +57,17 @@ require (
 	github.com/mohae/deepcopy v0.0.0-20170929034955-c48cc78d4826 // indirect
 	github.com/pjbgf/sha1cd v0.3.0 // indirect
 	github.com/richardlehane/mscfb v1.0.4 // indirect
-	github.com/richardlehane/msoleps v1.0.3 // indirect
+	github.com/richardlehane/msoleps v1.0.4 // indirect
 	github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 // indirect
 	github.com/sirupsen/logrus v1.9.3 // indirect
-	github.com/skeema/knownhosts v1.2.2 // indirect
+	github.com/skeema/knownhosts v1.3.0 // indirect
 	github.com/xanzy/ssh-agent v0.3.3 // indirect
 	github.com/xuri/efp v0.0.0-20240408161823-9ad904a10d6d // indirect
 	github.com/xuri/nfp v0.0.0-20240318013403-ab9948c2c4a7 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0 // indirect
-	golang.org/x/crypto v0.23.0 // indirect
-	golang.org/x/mod v0.17.0 // indirect
-	golang.org/x/net v0.25.0 // indirect
-	golang.org/x/sync v0.8.0 // indirect
-	golang.org/x/sys v0.23.0 // indirect
-	golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d // indirect
+	golang.org/x/crypto v0.28.0 // indirect
+	golang.org/x/net v0.30.0 // indirect
+	golang.org/x/sys v0.26.0 // indirect
 	gopkg.in/warnings.v0 v0.1.2 // indirect
 )