Run ipmitool asynchron. Improved error handling.

collectors/ipmiMetric.go

@@ -1,51 +1,58 @@
 package collectors
 
 import (
+	"bufio"
+	"bytes"
 	"encoding/json"
 	"errors"
+	"fmt"
+	"io"
 	"log"
-	"os"
 	"os/exec"
 	"strconv"
 	"strings"
 	"time"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
-const IPMITOOL_PATH = `ipmitool`
 const IPMISENSORS_PATH = `ipmi-sensors`
 
-type IpmiCollectorConfig struct {
+type IpmiCollector struct {
+	metricCollector
+	config struct {
 		ExcludeDevices  []string `json:"exclude_devices"`
 		IpmitoolPath    string   `json:"ipmitool_path"`
 		IpmisensorsPath string   `json:"ipmisensors_path"`
 	}
-
-type IpmiCollector struct {
-	metricCollector
-	//tags        map[string]string
-	//matches     map[string]string
-	config      IpmiCollectorConfig
 	ipmitool    string
 	ipmisensors string
 }
 
 func (m *IpmiCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
 	m.name = "IpmiCollector"
 	m.setup()
 	m.parallel = true
-	m.meta = map[string]string{"source": m.name, "group": "IPMI"}
-	m.config.IpmitoolPath = string(IPMITOOL_PATH)
-	m.config.IpmisensorsPath = string(IPMISENSORS_PATH)
-	m.ipmitool = ""
-	m.ipmisensors = ""
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "IPMI",
+	}
+	// default path to IPMI tools
+	m.config.IpmitoolPath = "ipmitool"
+	m.config.IpmisensorsPath = "ipmi-sensors"
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
+	// Check if executables ipmitool or ipmisensors are found
 	p, err := exec.LookPath(m.config.IpmitoolPath)
 	if err == nil {
 		m.ipmitool = p
@@ -62,25 +69,33 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
 }
 
 func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
+
+	// Setup ipmitool command
 	command := exec.Command(cmd, "sensor")
-	command.Wait()
-	stdout, err := command.Output()
-	if err != nil {
-		log.Print(err)
+	stdout, _ := command.StdoutPipe()
+	errBuf := new(bytes.Buffer)
+	command.Stderr = errBuf
+
+	// start command
+	if err := command.Start(); err != nil {
+		cclog.ComponentError(
+			m.name,
+			fmt.Sprintf("readIpmiTool(): Failed to start command \"%s\": %v", command.String(), err),
+		)
 		return
 	}
 
-	ll := strings.Split(string(stdout), "\n")
-
-	for _, line := range ll {
-		lv := strings.Split(line, "|")
+	// Read command output
+	scanner := bufio.NewScanner(stdout)
+	for scanner.Scan() {
+		lv := strings.Split(scanner.Text(), "|")
 		if len(lv) < 3 {
 			continue
 		}
-		v, err := strconv.ParseFloat(strings.Trim(lv[1], " "), 64)
+		v, err := strconv.ParseFloat(strings.TrimSpace(lv[1]), 64)
 		if err == nil {
-			name := strings.ToLower(strings.Replace(strings.Trim(lv[0], " "), " ", "_", -1))
-			unit := strings.Trim(lv[2], " ")
+			name := strings.ToLower(strings.Replace(strings.TrimSpace(lv[0]), " ", "_", -1))
+			unit := strings.TrimSpace(lv[2])
 			if unit == "Volts" {
 				unit = "Volts"
 			} else if unit == "degrees C" {
@@ -98,6 +113,17 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
 			}
 		}
 	}
+
+	// Wait for command end
+	if err := command.Wait(); err != nil {
+		errMsg, _ := io.ReadAll(errBuf)
+		cclog.ComponentError(
+			m.name,
+			fmt.Sprintf("readIpmiTool(): Failed to wait for the end of command \"%s\": %v\n", command.String(), err),
+			fmt.Sprintf("readIpmiTool(): command stderr: \"%s\"\n", string(errMsg)),
+		)
+		return
+	}
 }
 
 func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
@@ -131,18 +157,18 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
 }
 
 func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+
+	// Check if already initialized
+	if !m.init {
+		return
+	}
+
 	if len(m.config.IpmitoolPath) > 0 {
-		_, err := os.Stat(m.config.IpmitoolPath)
-		if err == nil {
 		m.readIpmiTool(m.config.IpmitoolPath, output)
-		}
 	} else if len(m.config.IpmisensorsPath) > 0 {
-		_, err := os.Stat(m.config.IpmisensorsPath)
-		if err == nil {
 		m.readIpmiSensors(m.config.IpmisensorsPath, output)
 	}
 }
-}
 
 func (m *IpmiCollector) Close() {
 	m.init = false