Collector-specific configuration. LIKWID collector derives metrics itself, Run once CLI option

This commit is contained in:
Thomas Roehl
2021-11-25 14:04:03 +01:00
parent 57948e8cff
commit 51b8c62d4d
14 changed files with 981 additions and 381 deletions

View File

@@ -15,15 +15,44 @@ import (
"log"
"strings"
"time"
"os"
"unsafe"
"math"
"encoding/json"
"gopkg.in/Knetic/govaluate.v2"
"io/ioutil"
"strconv"
)
type LikwidCollectorMetricConfig struct {
Name string `json:"name"`
Calc string `json:"calc"`
Socket_scope bool `json:"socket_scope"`
Publish bool `json:"publish"`
}
type LikwidCollectorEventsetConfig struct {
Events map[string]string `json:"events"`
Metrics []LikwidCollectorMetricConfig `json:"metrics"`
}
type LikwidCollectorConfig struct {
Eventsets []LikwidCollectorEventsetConfig `json:"eventsets"`
Metrics []LikwidCollectorMetricConfig `json:"globalmetrics"`
ExcludeMetrics []string `json:"exclude_metrics"`
}
type LikwidCollector struct {
MetricCollector
cpulist []C.int
sock2tid map[int]int
metrics map[C.int]map[string]int
groups map[string]C.int
groups []C.int
config LikwidCollectorConfig
results map[int]map[int]map[string]interface{}
mresults map[int]map[int]map[string]float64
gmresults map[int]map[string]float64
basefreq float64
}
type LikwidMetric struct {
@@ -33,7 +62,7 @@ type LikwidMetric struct {
group_idx int
}
const GROUPPATH = `/home/unrz139/Work/cc-metric-collector/collectors/likwid/groups`
const GROUPPATH = `/apps/likwid/5.2.0/share/likwid/perfgroups`
var likwid_metrics = map[string][]LikwidMetric{
"MEM_DP": {LikwidMetric{name: "mem_bw", search: "Memory bandwidth [MBytes/s]", socket_scope: true},
@@ -57,6 +86,33 @@ func getMetricId(group C.int, search string) (int, error) {
return -1, errors.New(fmt.Sprintf("Cannot find metric for search string '%s' in group %d", search, int(group)))
}
func eventsToEventStr(events map[string]string) string {
elist := make([]string, 0)
for k, v := range events {
elist = append(elist, fmt.Sprintf("%s:%s", v, k))
}
return strings.Join(elist, ",")
}
func getBaseFreq() float64 {
var freq float64 = math.NaN()
C.power_init(0)
info := C.get_powerInfo()
if float64(info.baseFrequency) != 0 {
freq = float64(info.baseFrequency)
} else {
buffer, err := ioutil.ReadFile("/sys/devices/system/cpu/cpu0/cpufreq/bios_limit")
if err == nil {
data := strings.Replace(string(buffer), "\n", "", -1)
x, err := strconv.ParseInt(data, 0, 64)
if err == nil {
freq = float64(x)*1E3
}
}
}
return freq
}
func getSocketCpus() map[C.int]int {
slist := SocketList()
var cpu C.int
@@ -71,9 +127,15 @@ func getSocketCpus() map[C.int]int {
return outmap
}
func (m *LikwidCollector) Init() error {
func (m *LikwidCollector) Init(config []byte) error {
var ret C.int
m.name = "LikwidCollector"
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
if err != nil {
return err
}
}
m.setup()
cpulist := CpuList()
m.cpulist = make([]C.int, len(cpulist))
@@ -86,161 +148,183 @@ func (m *LikwidCollector) Init() error {
m.sock2tid[sid] = i
}
}
m.metrics = make(map[C.int]map[string]int)
m.groups = make(map[string]C.int)
m.results = make(map[int]map[int]map[string]interface{})
m.mresults = make(map[int]map[int]map[string]float64)
m.gmresults = make(map[int]map[string]float64)
ret = C.topology_init()
if ret != 0 {
return errors.New("Failed to initialize LIKWID topology")
}
os.Setenv("LIKWID_FORCE", "1")
ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
if ret != 0 {
C.topology_finalize()
return errors.New("Failed to initialize LIKWID topology")
}
gpath := C.CString(GROUPPATH)
C.config_setGroupPath(gpath)
C.free(unsafe.Pointer(gpath))
for g, metrics := range likwid_metrics {
cstr := C.CString(g)
gid := C.perfmon_addEventSet(cstr)
if gid >= 0 {
gmetrics := 0
for i, metric := range metrics {
idx, err := getMetricId(gid, metric.search)
if err != nil {
log.Print(err)
} else {
likwid_metrics[g][i].group_idx = idx
gmetrics++
}
}
if gmetrics > 0 {
m.groups[g] = gid
}
} else {
log.Print("Failed to add events set ", g)
}
C.free(unsafe.Pointer(cstr))
for i, evset := range m.config.Eventsets {
estr := eventsToEventStr(evset.Events)
cstr := C.CString(estr)
gid := C.perfmon_addEventSet(cstr)
if gid >= 0 {
m.groups = append(m.groups, gid)
}
C.free(unsafe.Pointer(cstr))
m.results[i] = make(map[int]map[string]interface{})
m.mresults[i] = make(map[int]map[string]float64)
for tid, _ := range m.cpulist {
m.results[i][tid] = make(map[string]interface{})
m.mresults[i][tid] = make(map[string]float64)
m.gmresults[tid] = make(map[string]float64)
}
}
if len(m.groups) == 0 {
C.perfmon_finalize()
C.topology_finalize()
return errors.New("No LIKWID performance group initialized")
}
m.basefreq = getBaseFreq()
log.Print(m.basefreq)
m.init = true
return nil
}
func (m *LikwidCollector) Read(interval time.Duration, out *[]lp.MutableMetric) {
if m.init {
var ret C.int
core_fp_any := make(map[int]float64, len(m.cpulist))
for _, cpu := range m.cpulist {
core_fp_any[int(cpu)] = 0.0
if !m.init {
return
}
var ret C.int
for i, gid := range m.groups {
evset := m.config.Eventsets[i]
ret = C.perfmon_setupCounters(gid)
if ret != 0 {
log.Print("Failed to setup performance group ", C.perfmon_getGroupName(gid))
continue
}
for gname, gid := range m.groups {
ret = C.perfmon_setupCounters(gid)
if ret != 0 {
log.Print("Failed to setup performance group ", gname)
continue
}
ret = C.perfmon_startCounters()
if ret != 0 {
log.Print("Failed to start performance group ", gname)
continue
}
time.Sleep(interval)
ret = C.perfmon_stopCounters()
if ret != 0 {
log.Print("Failed to stop performance group ", gname)
continue
}
for _, lmetric := range likwid_metrics[gname] {
if lmetric.name == "pwr1" || lmetric.name == "pwr2" {
continue
}
mname := lmetric.name
inverse := false
if mname == "cpi" {
mname = "ipc"
inverse = true
}
if lmetric.socket_scope {
for sid, tid := range m.sock2tid {
res := C.perfmon_getLastMetric(gid, C.int(lmetric.group_idx), C.int(tid))
y, err := lp.New(lmetric.name,
map[string]string{"type": "socket", "type-id": fmt.Sprintf("%d", int(sid))},
map[string]interface{}{"value": float64(res)},
time.Now())
if err == nil {
*out = append(*out, y)
}
// log.Print("Metric '", lmetric.name,"' on Socket ",int(sid)," returns ", m.sockets[int(sid)][lmetric.name])
}
} else {
for tid, cpu := range m.cpulist {
res := C.perfmon_getLastMetric(gid, C.int(lmetric.group_idx), C.int(tid))
value := float64(res)
if inverse {
value = 1.0 / value
}
y, err := lp.New(mname,
map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", int(cpu))},
map[string]interface{}{"value": value},
time.Now())
if err == nil {
*out = append(*out, y)
}
if lmetric.name == "flops_dp" {
core_fp_any[int(cpu)] += 2 * float64(res)
}
if lmetric.name == "flops_sp" {
core_fp_any[int(cpu)] += float64(res)
}
// log.Print("Metric '", lmetric.name,"' on CPU ",int(cpu)," returns ", m.cpus[int(cpu)][lmetric.name])
}
}
}
for sid, tid := range m.sock2tid {
sum := 0.0
valid := false
for _, lmetric := range likwid_metrics[gname] {
if lmetric.name == "pwr1" || lmetric.name == "pwr2" {
res := C.perfmon_getLastMetric(gid, C.int(lmetric.group_idx), C.int(tid))
sum += float64(res)
valid = true
}
}
if valid {
y, err := lp.New("power",
map[string]string{"type": "socket", "type-id": fmt.Sprintf("%d", int(sid))},
map[string]interface{}{"value": float64(sum)},
time.Now())
if err == nil {
*out = append(*out, y)
}
}
}
for cpu := range m.cpulist {
y, err := lp.New("flops_any",
map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", int(cpu))},
map[string]interface{}{"value": float64(core_fp_any[int(cpu)])},
time.Now())
if err == nil {
*out = append(*out, y)
}
}
ret = C.perfmon_startCounters()
if ret != 0 {
log.Print("Failed to start performance group ", C.perfmon_getGroupName(gid))
continue
}
time.Sleep(interval)
ret = C.perfmon_stopCounters()
if ret != 0 {
log.Print("Failed to stop performance group ", C.perfmon_getGroupName(gid))
continue
}
var eidx C.int
for tid, _ := range m.cpulist {
for eidx = 0; int(eidx) < len(evset.Events); eidx++ {
ctr := C.perfmon_getCounterName(gid, eidx)
gctr := C.GoString(ctr)
res := C.perfmon_getLastResult(gid, eidx, C.int(tid))
m.results[i][tid][gctr] = float64(res)
}
m.results[i][tid]["time"] = float64(interval)
m.results[i][tid]["inverseClock"] = float64(1.0/m.basefreq)
for _, metric := range evset.Metrics {
expression, err := govaluate.NewEvaluableExpression(metric.Calc)
if err != nil {
log.Print(err.Error())
continue
}
result, err := expression.Evaluate(m.results[i][tid]);
if err != nil {
log.Print(err.Error())
continue
}
m.mresults[i][tid][metric.Name] = float64(result.(float64))
}
}
}
for _, metric := range m.config.Metrics {
for tid, _ := range m.cpulist {
var params map[string]interface{}
expression, err := govaluate.NewEvaluableExpression(metric.Calc)
if err != nil {
log.Print(err.Error())
continue
}
params = make(map[string]interface{})
for j, _ := range m.groups {
for mname, mres := range m.mresults[j][tid] {
params[mname] = mres
}
}
result, err := expression.Evaluate(params);
if err != nil {
log.Print(err.Error())
continue
}
m.gmresults[tid][metric.Name] = float64(result.(float64))
}
}
for i, _ := range m.groups {
evset := m.config.Eventsets[i]
for _, metric := range evset.Metrics {
_, skip := stringArrayContains(m.config.ExcludeMetrics, metric.Name)
if metric.Publish && !skip {
if metric.Socket_scope {
for sid, tid := range m.sock2tid {
y, err := lp.New(metric.Name,
map[string]string{"type": "socket", "type-id": fmt.Sprintf("%d", int(sid))},
map[string]interface{}{"value": m.mresults[i][tid][metric.Name]},
time.Now())
if err == nil {
*out = append(*out, y)
}
}
} else {
for tid, cpu := range m.cpulist {
y, err := lp.New(metric.Name,
map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", int(cpu))},
map[string]interface{}{"value": m.mresults[i][tid][metric.Name]},
time.Now())
if err == nil {
*out = append(*out, y)
}
}
}
}
}
}
for _, metric := range m.config.Metrics {
_, skip := stringArrayContains(m.config.ExcludeMetrics, metric.Name)
if metric.Publish && !skip {
if metric.Socket_scope {
for sid, tid := range m.sock2tid {
y, err := lp.New(metric.Name,
map[string]string{"type": "socket", "type-id": fmt.Sprintf("%d", int(sid))},
map[string]interface{}{"value": m.gmresults[tid][metric.Name]},
time.Now())
if err == nil {
*out = append(*out, y)
}
}
} else {
for tid, cpu := range m.cpulist {
y, err := lp.New(metric.Name,
map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", int(cpu))},
map[string]interface{}{"value": m.gmresults[tid][metric.Name]},
time.Now())
if err == nil {
*out = append(*out, y)
}
}
}
}
}
}
func (m *LikwidCollector) Close() {
if m.init {
m.init = false
C.perfmon_finalize()
C.topology_finalize()
m.init = false
}
return
}