cc-metric-collector/collectors/lustreMetric.go

432 lines
10 KiB
Go
Raw Normal View History

2021-03-25 16:52:28 +01:00
package collectors
import (
2021-11-25 15:11:39 +01:00
"encoding/json"
"errors"
"fmt"
"os/exec"
"os/user"
2021-03-25 16:52:28 +01:00
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
2021-03-25 16:52:28 +01:00
)
const LUSTRE_SYSFS = `/sys/fs/lustre`
const LCTL_CMD = `lctl`
const LCTL_OPTION = `get_param`
2021-03-25 16:52:28 +01:00
type LustreCollectorConfig struct {
LCtlCommand string `json:"lctl_command,omitempty"`
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
Sudo bool `json:"use_sudo,omitempty"`
SendAbsoluteValues bool `json:"send_abs_values,omitempty"`
SendDerivedValues bool `json:"send_derived_values,omitempty"`
SendDiffValues bool `json:"send_diff_values,omitempty"`
}
type LustreMetricDefinition struct {
name string
lineprefix string
lineoffset int
unit string
calc string
}
2021-03-25 16:52:28 +01:00
type LustreCollector struct {
Modularize the whole thing (#16) * Use channels, add a metric router, split up configuration and use extended version of Influx line protocol internally * Use central timer for collectors and router. Add expressions to router * Add expression to router config * Update entry points * Start with README * Update README for CCMetric * Formatting * Update README.md * Add README for MultiChanTicker * Add README for MultiChanTicker * Update README.md * Add README to metric router * Update main README * Remove SinkEntity type * Update README for sinks * Update go files * Update README for receivers * Update collectors README * Update collectors README * Use seperate page per collector * Fix for tempstat page * Add docs for customcmd collector * Add docs for ipmistat collector * Add docs for topprocs collector * Update customCmdMetric.md * Use seconds when calculating LIKWID metrics * Add IB metrics ib_recv_pkts and ib_xmit_pkts * Drop domain part of host name * Updated to latest stable version of likwid * Define source code dependencies in Makefile * Add GPFS / IBM Spectrum Scale collector * Add vet and staticcheck make targets * Add vet and staticcheck make targets * Avoid go vet warning: struct field tag `json:"..., omitempty"` not compatible with reflect.StructTag.Get: suspicious space in struct tag value struct field tag `json:"...", omitempty` not compatible with reflect.StructTag.Get: key:"value" pairs not separated by spaces * Add sample collector to README.md * Add CPU frequency collector * Avoid staticcheck warning: redundant return statement * Avoid staticcheck warning: unnecessary assignment to the blank identifier * Simplified code * Add CPUFreqCollectorCpuinfo a metric collector to measure the current frequency of the CPUs as obtained from /proc/cpuinfo Only measure on the first hyperthread * Add collector for NFS clients * Move publication of metrics into Flush() for NatsSink * Update GitHub actions * Refactoring * Avoid vet warning: Println arg list ends with redundant newline * Avoid vet warning struct field commands has json tag but is not exported * Avoid vet warning: return copies lock value. * Corrected typo * Refactoring * Add go sources in internal/... * Bad separator in Makefile * Fix Infiniband collector Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
2022-01-25 15:37:43 +01:00
metricCollector
tags map[string]string
config LustreCollectorConfig
lctl string
sudoCmd string
lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
definitions []LustreMetricDefinition // Combined list without excluded metrics
stats map[string]map[string]int64 // Data for last value per device and metric
}
func (m *LustreCollector) getDeviceDataCommand(device string) []string {
var command *exec.Cmd
statsfile := fmt.Sprintf("llite.%s.stats", device)
if m.config.Sudo {
command = exec.Command(m.sudoCmd, m.lctl, LCTL_OPTION, statsfile)
} else {
command = exec.Command(m.lctl, LCTL_OPTION, statsfile)
}
command.Wait()
stdout, _ := command.Output()
return strings.Split(string(stdout), "\n")
}
func (m *LustreCollector) getDevices() []string {
devices := make([]string, 0)
// //Version reading devices from sysfs
// globPattern := filepath.Join(LUSTRE_SYSFS, "llite/*/stats")
// files, err := filepath.Glob(globPattern)
// if err != nil {
// return devices
// }
// for _, f := range files {
// pathlist := strings.Split(f, "/")
// devices = append(devices, pathlist[4])
// }
data := m.getDeviceDataCommand("*")
for _, line := range data {
if strings.HasPrefix(line, "llite") {
linefields := strings.Split(line, ".")
if len(linefields) > 2 {
devices = append(devices, linefields[1])
}
}
}
return devices
}
func getMetricData(lines []string, prefix string, offset int) (int64, error) {
for _, line := range lines {
if strings.HasPrefix(line, prefix) {
lf := strings.Fields(line)
return strconv.ParseInt(lf[offset], 0, 64)
}
}
return 0, errors.New("no such line in data")
}
// //Version reading the stats data of a device from sysfs
// func (m *LustreCollector) getDeviceDataSysfs(device string) []string {
// llitedir := filepath.Join(LUSTRE_SYSFS, "llite")
// devdir := filepath.Join(llitedir, device)
// statsfile := filepath.Join(devdir, "stats")
Merge develop into main (#109) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update to line-protocol/v2 * Update runonce.yml with Golang 1.20 * Update fsnotify in LIKWID Collector * Use not a pointer to line-protocol.Encoder * Simplify Makefile * Use only as many arguments as required * Allow sum function to handle non float types * Allow values to be a slice of type float64, float32, int, int64, int32, bool * Use generic function to simplify code * Add missing case for type []int32 * Use generic function to compute minimum * Use generic function to compute maximum * Use generic function to compute average * Add error value to sumAnyType * Use generic function to compute median * For older versions of go slices is not part of the installation * Remove old entries from go.sum * Use simpler sort function * Compute metrics ib_total and ib_total_pkts * Add aggregated metrics. Add missing units * Update likwidMetric.go Fixes a potential bug when `fsnotify.NewWatcher()` fails with an error * Completly avoid memory allocations in infinibandMetric read() * Fixed initialization: Initalization and measurements should run in the same thread * Add safe.directory to Release action * Fix path after installation to /usr/bin after installation * ioutil.ReadFile is deprecated: As of Go 1.16, this function simply calls os.ReadFile * Switch to package slices from the golang 1.21 default library * Read file line by line * Read file line by line * Read file line by line * Use CamelCase * Use CamelCase * Fix function getNumaDomain, it always returned 0 * Avoid type conversion by using Atoi Avoid copying structs by using pointer access Increase readability with CamelCase variable names * Add caching * Cache CpuData * Cleanup * Use init function to initalize cache structure to avoid multi threading problems * Reuse information from /proc/cpuinfo * Avoid slice cloning. Directly use the cache * Add DieList * Add NumaDomainList and SMTList * Cleanup * Add comment * Lookup core ID from /sys/devices/system/cpu, /proc/cpuinfo is not portable * Lookup all information from /sys/devices/system/cpu, /proc/cpuinfo is not portable * Correctly handle lists from /sys * Add Simultaneous Multithreading siblings * Replace deprecated thread_siblings_list by core_cpus_list * Reduce number of required slices * Allow to send total values per core, socket and node * Send all metrics with same time stamp calcEventsetMetrics does only computiation, counter measurement is done before * Input parameters should be float64 when evaluating to float64 * Send all metrics with same time stamp calcGlobalMetrics does only computiation, counter measurement is done before * Remove unused variable gmresults * Add comments * Updated go packages * Add build with golang 1.21 * Switch to checkout action version 4 * Switch to setup-go action version 4 * Add workflow_dispatch to allow manual run of workflow * Add workflow_dispatch to allow manual run of workflow * Add release build jobs to runonce.yml * Switch to golang 1.20 for RHEL based distributions * Use dnf to download golang * Remove golang versions before 1.20 * Upgrade Ubuntu focal -> jammy * Pipe golang tar package directly to tar * Update golang version * Fix Ubuntu version number * Add links to ipmi and redfish receivers * Fix http server addr format * github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol * Corrected spelling * Add some comments * github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol * Allow other fields not only field "value" * Add some basic debugging documentation * Add some basic debugging documentation * Use a lock for the flush timer * Add tags in lexical order as required by AddTag() * Only access meta data, when it gets used as tag * Use slice to store lexialicly orderd key value pairs * Increase golang version requirement to 1.20. * Avoid package cmp to allow builds with golang v1.20 * Fix: Error NVML library not found did crash cc-metric-collector with "SIGSEGV: segmentation violation" * Add config option idle_timeout * Add basic authentication support * Add basic authentication support * Avoid unneccessary memory allocations * Add documentation for send_*_total values * Use generic package maps to clone maps * Reuse flush timer * Add Influx client options * Reuse ccTopology functionality * Do not store unused topology information * Add batch_size config * Cleanup * Use stype and stype-id for the NIC in NetstatCollector * Wait for concurrent flush operations to finish * Be more verbose in error messages * Reverted previous changes. Made the code to complex without much advantages * Use line protocol encoder * Go pkg update * Stop flush timer, when immediatelly flushing * Fix: Corrected unlock access to batch slice * Add config option to specify whether to use GZip compression in influx write requests * Add asynchron send of encoder metrics * Use DefaultServeMux instead of github.com/gorilla/mux * Add config option for HTTP keep-alives * Be more strict, when parsing json * Add config option for HTTP request timeout and Retry interval * Allow more then one background send operation * Fix %sysusers_create_package args (#108) %sysusers_create_package requires two arguments. See: https://github.com/systemd/systemd/blob/main/src/rpm/macros.systemd.in#L165 * Add nfsiostat to list of collectors --------- Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <holgerob@gmx.de> Co-authored-by: Obihörnchen <obihoernchende@gmail.com>
2023-12-04 12:21:26 +01:00
// buffer, err := os.ReadFile(statsfile)
// if err != nil {
// return make([]string, 0)
// }
// return strings.Split(string(buffer), "\n")
// }
var LustreAbsMetrics = []LustreMetricDefinition{
{
name: "lustre_read_requests",
lineprefix: "read_bytes",
lineoffset: 1,
unit: "requests",
calc: "none",
},
{
name: "lustre_write_requests",
lineprefix: "write_bytes",
lineoffset: 1,
unit: "requests",
calc: "none",
},
{
name: "lustre_read_bytes",
lineprefix: "read_bytes",
lineoffset: 6,
unit: "bytes",
calc: "none",
},
{
name: "lustre_write_bytes",
lineprefix: "write_bytes",
lineoffset: 6,
unit: "bytes",
calc: "none",
},
{
name: "lustre_open",
lineprefix: "open",
lineoffset: 1,
unit: "",
calc: "none",
},
{
name: "lustre_close",
lineprefix: "close",
lineoffset: 1,
unit: "",
calc: "none",
},
{
name: "lustre_setattr",
lineprefix: "setattr",
lineoffset: 1,
unit: "",
calc: "none",
},
{
name: "lustre_getattr",
lineprefix: "getattr",
lineoffset: 1,
unit: "",
calc: "none",
},
{
name: "lustre_statfs",
lineprefix: "statfs",
lineoffset: 1,
unit: "",
calc: "none",
},
{
name: "lustre_inode_permission",
lineprefix: "inode_permission",
lineoffset: 1,
unit: "",
calc: "none",
},
}
var LustreDiffMetrics = []LustreMetricDefinition{
{
name: "lustre_read_requests_diff",
lineprefix: "read_bytes",
lineoffset: 1,
unit: "requests",
calc: "difference",
},
{
name: "lustre_write_requests_diff",
lineprefix: "write_bytes",
lineoffset: 1,
unit: "requests",
calc: "difference",
},
{
name: "lustre_read_bytes_diff",
lineprefix: "read_bytes",
lineoffset: 6,
unit: "bytes",
calc: "difference",
},
{
name: "lustre_write_bytes_diff",
lineprefix: "write_bytes",
lineoffset: 6,
unit: "bytes",
calc: "difference",
},
{
name: "lustre_open_diff",
lineprefix: "open",
lineoffset: 1,
unit: "",
calc: "difference",
},
{
name: "lustre_close_diff",
lineprefix: "close",
lineoffset: 1,
unit: "",
calc: "difference",
},
{
name: "lustre_setattr_diff",
lineprefix: "setattr",
lineoffset: 1,
unit: "",
calc: "difference",
},
{
name: "lustre_getattr_diff",
lineprefix: "getattr",
lineoffset: 1,
unit: "",
calc: "difference",
},
{
name: "lustre_statfs_diff",
lineprefix: "statfs",
lineoffset: 1,
unit: "",
calc: "difference",
},
{
name: "lustre_inode_permission_diff",
lineprefix: "inode_permission",
lineoffset: 1,
unit: "",
calc: "difference",
},
}
var LustreDeriveMetrics = []LustreMetricDefinition{
{
name: "lustre_read_requests_rate",
lineprefix: "read_bytes",
lineoffset: 1,
unit: "requests/sec",
calc: "derivative",
},
{
name: "lustre_write_requests_rate",
lineprefix: "write_bytes",
lineoffset: 1,
unit: "requests/sec",
calc: "derivative",
},
{
name: "lustre_read_bw",
lineprefix: "read_bytes",
lineoffset: 6,
unit: "bytes/sec",
calc: "derivative",
},
{
name: "lustre_write_bw",
lineprefix: "write_bytes",
lineoffset: 6,
unit: "bytes/sec",
calc: "derivative",
},
}
Modularize the whole thing (#16) * Use channels, add a metric router, split up configuration and use extended version of Influx line protocol internally * Use central timer for collectors and router. Add expressions to router * Add expression to router config * Update entry points * Start with README * Update README for CCMetric * Formatting * Update README.md * Add README for MultiChanTicker * Add README for MultiChanTicker * Update README.md * Add README to metric router * Update main README * Remove SinkEntity type * Update README for sinks * Update go files * Update README for receivers * Update collectors README * Update collectors README * Use seperate page per collector * Fix for tempstat page * Add docs for customcmd collector * Add docs for ipmistat collector * Add docs for topprocs collector * Update customCmdMetric.md * Use seconds when calculating LIKWID metrics * Add IB metrics ib_recv_pkts and ib_xmit_pkts * Drop domain part of host name * Updated to latest stable version of likwid * Define source code dependencies in Makefile * Add GPFS / IBM Spectrum Scale collector * Add vet and staticcheck make targets * Add vet and staticcheck make targets * Avoid go vet warning: struct field tag `json:"..., omitempty"` not compatible with reflect.StructTag.Get: suspicious space in struct tag value struct field tag `json:"...", omitempty` not compatible with reflect.StructTag.Get: key:"value" pairs not separated by spaces * Add sample collector to README.md * Add CPU frequency collector * Avoid staticcheck warning: redundant return statement * Avoid staticcheck warning: unnecessary assignment to the blank identifier * Simplified code * Add CPUFreqCollectorCpuinfo a metric collector to measure the current frequency of the CPUs as obtained from /proc/cpuinfo Only measure on the first hyperthread * Add collector for NFS clients * Move publication of metrics into Flush() for NatsSink * Update GitHub actions * Refactoring * Avoid vet warning: Println arg list ends with redundant newline * Avoid vet warning struct field commands has json tag but is not exported * Avoid vet warning: return copies lock value. * Corrected typo * Refactoring * Add go sources in internal/... * Bad separator in Makefile * Fix Infiniband collector Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
2022-01-25 15:37:43 +01:00
func (m *LustreCollector) Init(config json.RawMessage) error {
2021-11-25 15:11:39 +01:00
var err error
2021-03-25 17:47:08 +01:00
m.name = "LustreCollector"
m.parallel = true
if len(config) > 0 {
2021-11-25 15:11:39 +01:00
err = json.Unmarshal(config, &m.config)
if err != nil {
return err
}
}
2021-03-25 16:52:28 +01:00
m.setup()
2021-10-04 15:23:43 +02:00
m.tags = map[string]string{"type": "node"}
Modularize the whole thing (#16) * Use channels, add a metric router, split up configuration and use extended version of Influx line protocol internally * Use central timer for collectors and router. Add expressions to router * Add expression to router config * Update entry points * Start with README * Update README for CCMetric * Formatting * Update README.md * Add README for MultiChanTicker * Add README for MultiChanTicker * Update README.md * Add README to metric router * Update main README * Remove SinkEntity type * Update README for sinks * Update go files * Update README for receivers * Update collectors README * Update collectors README * Use seperate page per collector * Fix for tempstat page * Add docs for customcmd collector * Add docs for ipmistat collector * Add docs for topprocs collector * Update customCmdMetric.md * Use seconds when calculating LIKWID metrics * Add IB metrics ib_recv_pkts and ib_xmit_pkts * Drop domain part of host name * Updated to latest stable version of likwid * Define source code dependencies in Makefile * Add GPFS / IBM Spectrum Scale collector * Add vet and staticcheck make targets * Add vet and staticcheck make targets * Avoid go vet warning: struct field tag `json:"..., omitempty"` not compatible with reflect.StructTag.Get: suspicious space in struct tag value struct field tag `json:"...", omitempty` not compatible with reflect.StructTag.Get: key:"value" pairs not separated by spaces * Add sample collector to README.md * Add CPU frequency collector * Avoid staticcheck warning: redundant return statement * Avoid staticcheck warning: unnecessary assignment to the blank identifier * Simplified code * Add CPUFreqCollectorCpuinfo a metric collector to measure the current frequency of the CPUs as obtained from /proc/cpuinfo Only measure on the first hyperthread * Add collector for NFS clients * Move publication of metrics into Flush() for NatsSink * Update GitHub actions * Refactoring * Avoid vet warning: Println arg list ends with redundant newline * Avoid vet warning struct field commands has json tag but is not exported * Avoid vet warning: return copies lock value. * Corrected typo * Refactoring * Add go sources in internal/... * Bad separator in Makefile * Fix Infiniband collector Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
2022-01-25 15:37:43 +01:00
m.meta = map[string]string{"source": m.name, "group": "Lustre"}
// Lustre file system statistics can only be queried by user root
// or with password-less sudo
2022-03-04 11:32:10 +01:00
if !m.config.Sudo {
user, err := user.Current()
if err != nil {
cclog.ComponentError(m.name, "Failed to get current user:", err.Error())
return err
}
if user.Uid != "0" {
cclog.ComponentError(m.name, "Lustre file system statistics can only be queried by user root")
return err
}
} else {
p, err := exec.LookPath("sudo")
if err != nil {
cclog.ComponentError(m.name, "Cannot find 'sudo'")
return err
}
m.sudoCmd = p
}
p, err := exec.LookPath(m.config.LCtlCommand)
if err != nil {
p, err = exec.LookPath(LCTL_CMD)
if err != nil {
return err
2021-11-25 15:11:39 +01:00
}
2021-10-04 15:23:43 +02:00
}
m.lctl = p
m.definitions = []LustreMetricDefinition{}
if m.config.SendAbsoluteValues {
for _, def := range LustreAbsMetrics {
if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
m.definitions = append(m.definitions, def)
}
}
}
if m.config.SendDiffValues {
for _, def := range LustreDiffMetrics {
if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
m.definitions = append(m.definitions, def)
}
}
}
if m.config.SendDerivedValues {
for _, def := range LustreDeriveMetrics {
if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
m.definitions = append(m.definitions, def)
}
}
}
if len(m.definitions) == 0 {
return errors.New("no metrics to collect")
}
2021-11-25 15:11:39 +01:00
devices := m.getDevices()
if len(devices) == 0 {
return errors.New("no Lustre devices found")
}
m.stats = make(map[string]map[string]int64)
for _, d := range devices {
m.stats[d] = make(map[string]int64)
data := m.getDeviceDataCommand(d)
for _, def := range m.definitions {
x, err := getMetricData(data, def.lineprefix, def.lineoffset)
if err == nil {
m.stats[d][def.name] = x
} else {
m.stats[d][def.name] = 0
}
}
}
m.lastTimestamp = time.Now()
m.init = true
return nil
2021-03-25 16:52:28 +01:00
}
Modularize the whole thing (#16) * Use channels, add a metric router, split up configuration and use extended version of Influx line protocol internally * Use central timer for collectors and router. Add expressions to router * Add expression to router config * Update entry points * Start with README * Update README for CCMetric * Formatting * Update README.md * Add README for MultiChanTicker * Add README for MultiChanTicker * Update README.md * Add README to metric router * Update main README * Remove SinkEntity type * Update README for sinks * Update go files * Update README for receivers * Update collectors README * Update collectors README * Use seperate page per collector * Fix for tempstat page * Add docs for customcmd collector * Add docs for ipmistat collector * Add docs for topprocs collector * Update customCmdMetric.md * Use seconds when calculating LIKWID metrics * Add IB metrics ib_recv_pkts and ib_xmit_pkts * Drop domain part of host name * Updated to latest stable version of likwid * Define source code dependencies in Makefile * Add GPFS / IBM Spectrum Scale collector * Add vet and staticcheck make targets * Add vet and staticcheck make targets * Avoid go vet warning: struct field tag `json:"..., omitempty"` not compatible with reflect.StructTag.Get: suspicious space in struct tag value struct field tag `json:"...", omitempty` not compatible with reflect.StructTag.Get: key:"value" pairs not separated by spaces * Add sample collector to README.md * Add CPU frequency collector * Avoid staticcheck warning: redundant return statement * Avoid staticcheck warning: unnecessary assignment to the blank identifier * Simplified code * Add CPUFreqCollectorCpuinfo a metric collector to measure the current frequency of the CPUs as obtained from /proc/cpuinfo Only measure on the first hyperthread * Add collector for NFS clients * Move publication of metrics into Flush() for NatsSink * Update GitHub actions * Refactoring * Avoid vet warning: Println arg list ends with redundant newline * Avoid vet warning struct field commands has json tag but is not exported * Avoid vet warning: return copies lock value. * Corrected typo * Refactoring * Add go sources in internal/... * Bad separator in Makefile * Fix Infiniband collector Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
2022-01-25 15:37:43 +01:00
func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric) {
2021-11-25 15:11:39 +01:00
if !m.init {
return
}
now := time.Now()
tdiff := now.Sub(m.lastTimestamp)
for device, devData := range m.stats {
data := m.getDeviceDataCommand(device)
for _, def := range m.definitions {
var use_x int64
var err error
var y lp.CCMetric
x, err := getMetricData(data, def.lineprefix, def.lineoffset)
if err == nil {
use_x = x
} else {
use_x = devData[def.name]
}
var value interface{}
switch def.calc {
case "none":
value = use_x
y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
case "difference":
value = use_x - devData[def.name]
if value.(int64) < 0 {
value = 0
2021-11-25 15:11:39 +01:00
}
y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
case "derivative":
value = float64(use_x-devData[def.name]) / tdiff.Seconds()
if value.(float64) < 0 {
value = 0
}
y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
2021-11-25 15:11:39 +01:00
}
if err == nil {
y.AddTag("device", device)
if len(def.unit) > 0 {
y.AddMeta("unit", def.unit)
}
output <- y
}
devData[def.name] = use_x
}
2021-03-25 16:52:28 +01:00
}
m.lastTimestamp = now
2021-03-25 16:52:28 +01:00
}
func (m *LustreCollector) Close() {
2021-10-04 15:47:03 +02:00
m.init = false
2021-03-25 16:52:28 +01:00
}