mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2025-07-20 20:01:40 +02:00
Compare commits
1 Commits
numastats_
...
cc-docs
Author | SHA1 | Date | |
---|---|---|---|
|
a1077b58a8 |
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package main
|
package main
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -78,14 +78,6 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
|
|||||||
"group": "NUMA",
|
"group": "NUMA",
|
||||||
}
|
}
|
||||||
|
|
||||||
m.config.SendAbsoluteValues = true
|
|
||||||
if len(config) > 0 {
|
|
||||||
err := json.Unmarshal(config, &m.config)
|
|
||||||
if err != nil {
|
|
||||||
return fmt.Errorf("unable to unmarshal numastat configuration: %s", err.Error())
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Loop for all NUMA node directories
|
// Loop for all NUMA node directories
|
||||||
base := "/sys/devices/system/node/node"
|
base := "/sys/devices/system/node/node"
|
||||||
globPattern := base + "[0-9]*"
|
globPattern := base + "[0-9]*"
|
||||||
@@ -153,11 +145,11 @@ func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessa
|
|||||||
}
|
}
|
||||||
|
|
||||||
if m.config.SendAbsoluteValues {
|
if m.config.SendAbsoluteValues {
|
||||||
msg, err := lp.NewMetric(
|
msg, err := lp.NewMessage(
|
||||||
"numastats_"+key,
|
"numastats_"+key,
|
||||||
t.tagSet,
|
t.tagSet,
|
||||||
m.meta,
|
m.meta,
|
||||||
value,
|
map[string]interface{}{"value": value},
|
||||||
now,
|
now,
|
||||||
)
|
)
|
||||||
if err == nil {
|
if err == nil {
|
||||||
@@ -169,11 +161,11 @@ func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessa
|
|||||||
prev, ok := t.previousValues[key]
|
prev, ok := t.previousValues[key]
|
||||||
if ok {
|
if ok {
|
||||||
rate := float64(value-prev) / timeDiff
|
rate := float64(value-prev) / timeDiff
|
||||||
msg, err := lp.NewMetric(
|
msg, err := lp.NewMessage(
|
||||||
"numastats_"+key+"_rate",
|
"numastats_"+key+"_rate",
|
||||||
t.tagSet,
|
t.tagSet,
|
||||||
m.meta,
|
m.meta,
|
||||||
rate,
|
map[string]interface{}{"value": rate},
|
||||||
now,
|
now,
|
||||||
)
|
)
|
||||||
if err == nil {
|
if err == nil {
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
@@ -38,8 +31,6 @@ type NvidiaCollectorDevice struct {
|
|||||||
excludeMetrics map[string]bool
|
excludeMetrics map[string]bool
|
||||||
tags map[string]string
|
tags map[string]string
|
||||||
meta map[string]string
|
meta map[string]string
|
||||||
lastEnergyReading uint64
|
|
||||||
lastEnergyTimestamp time.Time
|
|
||||||
}
|
}
|
||||||
|
|
||||||
type NvidiaCollector struct {
|
type NvidiaCollector struct {
|
||||||
@@ -158,8 +149,6 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
|
|||||||
|
|
||||||
// Add device handle
|
// Add device handle
|
||||||
g.device = device
|
g.device = device
|
||||||
g.lastEnergyReading = 0
|
|
||||||
g.lastEnergyTimestamp = time.Now()
|
|
||||||
|
|
||||||
// Add tags
|
// Add tags
|
||||||
g.tags = map[string]string{
|
g.tags = map[string]string{
|
||||||
@@ -217,7 +206,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readMemoryInfo(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_fb_mem_total"] || !device.excludeMetrics["nv_fb_mem_used"] || !device.excludeMetrics["nv_fb_mem_reserved"] {
|
if !device.excludeMetrics["nv_fb_mem_total"] || !device.excludeMetrics["nv_fb_mem_used"] || !device.excludeMetrics["nv_fb_mem_reserved"] {
|
||||||
var total uint64
|
var total uint64
|
||||||
var used uint64
|
var used uint64
|
||||||
@@ -261,7 +250,7 @@ func readMemoryInfo(device *NvidiaCollectorDevice, output chan lp.CCMessage) err
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readBarMemoryInfo(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_bar1_mem_total"] || !device.excludeMetrics["nv_bar1_mem_used"] {
|
if !device.excludeMetrics["nv_bar1_mem_total"] || !device.excludeMetrics["nv_bar1_mem_used"] {
|
||||||
meminfo, ret := nvml.DeviceGetBAR1MemoryInfo(device.device)
|
meminfo, ret := nvml.DeviceGetBAR1MemoryInfo(device.device)
|
||||||
if ret != nvml.SUCCESS {
|
if ret != nvml.SUCCESS {
|
||||||
@@ -288,7 +277,7 @@ func readBarMemoryInfo(device *NvidiaCollectorDevice, output chan lp.CCMessage)
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
|
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
|
||||||
if ret != nvml.SUCCESS {
|
if ret != nvml.SUCCESS {
|
||||||
err := errors.New(nvml.ErrorString(ret))
|
err := errors.New(nvml.ErrorString(ret))
|
||||||
@@ -330,7 +319,7 @@ func readUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage) er
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readTemp(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readTemp(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_temp"] {
|
if !device.excludeMetrics["nv_temp"] {
|
||||||
// Retrieves the current temperature readings for the device, in degrees C.
|
// Retrieves the current temperature readings for the device, in degrees C.
|
||||||
//
|
//
|
||||||
@@ -349,7 +338,7 @@ func readTemp(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readFan(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_fan"] {
|
if !device.excludeMetrics["nv_fan"] {
|
||||||
// Retrieves the intended operating speed of the device's fan.
|
// Retrieves the intended operating speed of the device's fan.
|
||||||
//
|
//
|
||||||
@@ -372,7 +361,7 @@ func readFan(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// func readFans(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
// func readFans(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
// if !device.excludeMetrics["nv_fan"] {
|
// if !device.excludeMetrics["nv_fan"] {
|
||||||
// numFans, ret := nvml.DeviceGetNumFans(device.device)
|
// numFans, ret := nvml.DeviceGetNumFans(device.device)
|
||||||
// if ret == nvml.SUCCESS {
|
// if ret == nvml.SUCCESS {
|
||||||
@@ -393,7 +382,7 @@ func readFan(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
|||||||
// return nil
|
// return nil
|
||||||
// }
|
// }
|
||||||
|
|
||||||
func readEccMode(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_ecc_mode"] {
|
if !device.excludeMetrics["nv_ecc_mode"] {
|
||||||
// Retrieves the current and pending ECC modes for the device.
|
// Retrieves the current and pending ECC modes for the device.
|
||||||
//
|
//
|
||||||
@@ -427,7 +416,7 @@ func readEccMode(device *NvidiaCollectorDevice, output chan lp.CCMessage) error
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readPerfState(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_perf_state"] {
|
if !device.excludeMetrics["nv_perf_state"] {
|
||||||
// Retrieves the current performance state for the device.
|
// Retrieves the current performance state for the device.
|
||||||
//
|
//
|
||||||
@@ -447,16 +436,13 @@ func readPerfState(device *NvidiaCollectorDevice, output chan lp.CCMessage) erro
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readPowerUsage(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_power_usage"] {
|
if !device.excludeMetrics["nv_power_usage"] {
|
||||||
// Retrieves power usage for this GPU in milliwatts and its associated circuitry (e.g. memory)
|
// Retrieves power usage for this GPU in milliwatts and its associated circuitry (e.g. memory)
|
||||||
//
|
//
|
||||||
// On Fermi and Kepler GPUs the reading is accurate to within +/- 5% of current power draw.
|
// On Fermi and Kepler GPUs the reading is accurate to within +/- 5% of current power draw.
|
||||||
// On Ampere (except GA100) or newer GPUs, the API returns power averaged over 1 sec interval.
|
|
||||||
// On GA100 and older architectures, instantaneous power is returned.
|
|
||||||
//
|
//
|
||||||
// It is only available if power management mode is supported.
|
// It is only available if power management mode is supported
|
||||||
|
|
||||||
mode, ret := nvml.DeviceGetPowerManagementMode(device.device)
|
mode, ret := nvml.DeviceGetPowerManagementMode(device.device)
|
||||||
if ret != nvml.SUCCESS {
|
if ret != nvml.SUCCESS {
|
||||||
return nil
|
return nil
|
||||||
@@ -475,54 +461,7 @@ func readPowerUsage(device *NvidiaCollectorDevice, output chan lp.CCMessage) err
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readEnergyConsumption(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
// Retrieves total energy consumption for this GPU in millijoules (mJ) since the driver was last reloaded
|
|
||||||
|
|
||||||
// For Volta or newer fully supported devices.
|
|
||||||
if (!device.excludeMetrics["nv_energy"]) && (!device.excludeMetrics["nv_energy_abs"]) && (!device.excludeMetrics["nv_average_power"]) {
|
|
||||||
now := time.Now()
|
|
||||||
mode, ret := nvml.DeviceGetPowerManagementMode(device.device)
|
|
||||||
if ret != nvml.SUCCESS {
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
if mode == nvml.FEATURE_ENABLED {
|
|
||||||
energy, ret := nvml.DeviceGetTotalEnergyConsumption(device.device)
|
|
||||||
if ret == nvml.SUCCESS {
|
|
||||||
if device.lastEnergyReading != 0 {
|
|
||||||
if !device.excludeMetrics["nv_energy"] {
|
|
||||||
y, err := lp.NewMetric("nv_energy", device.tags, device.meta, (energy-device.lastEnergyReading)/1000, now)
|
|
||||||
if err == nil {
|
|
||||||
y.AddMeta("unit", "Joules")
|
|
||||||
output <- y
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if !device.excludeMetrics["nv_average_power"] {
|
|
||||||
|
|
||||||
energyDiff := (energy - device.lastEnergyReading) / 1000
|
|
||||||
timeDiff := now.Sub(device.lastEnergyTimestamp)
|
|
||||||
y, err := lp.NewMetric("nv_average_power", device.tags, device.meta, energyDiff/uint64(timeDiff.Seconds()), now)
|
|
||||||
if err == nil {
|
|
||||||
y.AddMeta("unit", "watts")
|
|
||||||
output <- y
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
if !device.excludeMetrics["nv_energy_abs"] {
|
|
||||||
y, err := lp.NewMetric("nv_energy_abs", device.tags, device.meta, energy/1000, now)
|
|
||||||
if err == nil {
|
|
||||||
y.AddMeta("unit", "Joules")
|
|
||||||
output <- y
|
|
||||||
}
|
|
||||||
}
|
|
||||||
device.lastEnergyReading = energy
|
|
||||||
device.lastEnergyTimestamp = time.Now()
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return nil
|
|
||||||
}
|
|
||||||
|
|
||||||
func readClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
|
||||||
// Retrieves the current clock speeds for the device.
|
// Retrieves the current clock speeds for the device.
|
||||||
//
|
//
|
||||||
// Available clock information:
|
// Available clock information:
|
||||||
@@ -574,7 +513,7 @@ func readClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readMaxClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
// Retrieves the maximum clock speeds for the device.
|
// Retrieves the maximum clock speeds for the device.
|
||||||
//
|
//
|
||||||
// Available clock information:
|
// Available clock information:
|
||||||
@@ -632,7 +571,7 @@ func readMaxClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) erro
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readEccErrors(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_ecc_uncorrected_error"] {
|
if !device.excludeMetrics["nv_ecc_uncorrected_error"] {
|
||||||
// Retrieves the total ECC error counts for the device.
|
// Retrieves the total ECC error counts for the device.
|
||||||
//
|
//
|
||||||
@@ -663,7 +602,7 @@ func readEccErrors(device *NvidiaCollectorDevice, output chan lp.CCMessage) erro
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readPowerLimit(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_power_max_limit"] {
|
if !device.excludeMetrics["nv_power_max_limit"] {
|
||||||
// Retrieves the power management limit associated with this device.
|
// Retrieves the power management limit associated with this device.
|
||||||
//
|
//
|
||||||
@@ -683,7 +622,7 @@ func readPowerLimit(device *NvidiaCollectorDevice, output chan lp.CCMessage) err
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readEncUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
|
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
|
||||||
if ret != nvml.SUCCESS {
|
if ret != nvml.SUCCESS {
|
||||||
err := errors.New(nvml.ErrorString(ret))
|
err := errors.New(nvml.ErrorString(ret))
|
||||||
@@ -710,7 +649,7 @@ func readEncUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage)
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readDecUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
|
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
|
||||||
if ret != nvml.SUCCESS {
|
if ret != nvml.SUCCESS {
|
||||||
err := errors.New(nvml.ErrorString(ret))
|
err := errors.New(nvml.ErrorString(ret))
|
||||||
@@ -737,7 +676,7 @@ func readDecUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage)
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readRemappedRows(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_remapped_rows_corrected"] ||
|
if !device.excludeMetrics["nv_remapped_rows_corrected"] ||
|
||||||
!device.excludeMetrics["nv_remapped_rows_uncorrected"] ||
|
!device.excludeMetrics["nv_remapped_rows_uncorrected"] ||
|
||||||
!device.excludeMetrics["nv_remapped_rows_pending"] ||
|
!device.excludeMetrics["nv_remapped_rows_pending"] ||
|
||||||
@@ -790,7 +729,7 @@ func readRemappedRows(device *NvidiaCollectorDevice, output chan lp.CCMessage) e
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readProcessCounts(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
if !device.excludeMetrics["nv_compute_processes"] {
|
if !device.excludeMetrics["nv_compute_processes"] {
|
||||||
// Get information about processes with a compute context on a device
|
// Get information about processes with a compute context on a device
|
||||||
//
|
//
|
||||||
@@ -882,7 +821,7 @@ func readProcessCounts(device *NvidiaCollectorDevice, output chan lp.CCMessage)
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readViolationStats(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
var violTime nvml.ViolationTime
|
var violTime nvml.ViolationTime
|
||||||
var ret nvml.Return
|
var ret nvml.Return
|
||||||
|
|
||||||
@@ -996,7 +935,7 @@ func readViolationStats(device *NvidiaCollectorDevice, output chan lp.CCMessage)
|
|||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
func readNVLinkStats(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
|
||||||
// Retrieves the specified error counter value
|
// Retrieves the specified error counter value
|
||||||
// Please refer to \a nvmlNvLinkErrorCounter_t for error counters that are available
|
// Please refer to \a nvmlNvLinkErrorCounter_t for error counters that are available
|
||||||
//
|
//
|
||||||
@@ -1131,7 +1070,7 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
|
|||||||
return
|
return
|
||||||
}
|
}
|
||||||
|
|
||||||
readAll := func(device *NvidiaCollectorDevice, output chan lp.CCMessage) {
|
readAll := func(device NvidiaCollectorDevice, output chan lp.CCMessage) {
|
||||||
name, ret := nvml.DeviceGetName(device.device)
|
name, ret := nvml.DeviceGetName(device.device)
|
||||||
if ret != nvml.SUCCESS {
|
if ret != nvml.SUCCESS {
|
||||||
name = "NoName"
|
name = "NoName"
|
||||||
@@ -1171,11 +1110,6 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
|
|||||||
cclog.ComponentDebug(m.name, "readPowerUsage for device", name, "failed")
|
cclog.ComponentDebug(m.name, "readPowerUsage for device", name, "failed")
|
||||||
}
|
}
|
||||||
|
|
||||||
err = readEnergyConsumption(device, output)
|
|
||||||
if err != nil {
|
|
||||||
cclog.ComponentDebug(m.name, "readEnergyConsumption for device", name, "failed")
|
|
||||||
}
|
|
||||||
|
|
||||||
err = readClocks(device, output)
|
err = readClocks(device, output)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
cclog.ComponentDebug(m.name, "readClocks for device", name, "failed")
|
cclog.ComponentDebug(m.name, "readClocks for device", name, "failed")
|
||||||
@@ -1235,7 +1169,7 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
|
|||||||
// Actual read loop over all attached Nvidia GPUs
|
// Actual read loop over all attached Nvidia GPUs
|
||||||
for i := 0; i < m.num_gpus; i++ {
|
for i := 0; i < m.num_gpus; i++ {
|
||||||
|
|
||||||
readAll(&m.gpus[i], output)
|
readAll(m.gpus[i], output)
|
||||||
|
|
||||||
// Iterate over all MIG devices if any
|
// Iterate over all MIG devices if any
|
||||||
if m.config.ProcessMigDevices {
|
if m.config.ProcessMigDevices {
|
||||||
@@ -1309,7 +1243,7 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
readAll(&migDevice, output)
|
readAll(migDevice, output)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@@ -82,8 +82,5 @@ Metrics:
|
|||||||
* `nv_nvlink_ecc_errors`
|
* `nv_nvlink_ecc_errors`
|
||||||
* `nv_nvlink_replay_errors`
|
* `nv_nvlink_replay_errors`
|
||||||
* `nv_nvlink_recovery_errors`
|
* `nv_nvlink_recovery_errors`
|
||||||
* `nv_energy`
|
|
||||||
* `nv_energy_abs`
|
|
||||||
* `nv_average_power`
|
|
||||||
|
|
||||||
Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`.
|
Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`.
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package collectors
|
package collectors
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package metricAggregator
|
package metricAggregator
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package metricAggregator
|
package metricAggregator
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -236,13 +236,13 @@ __deprecated__
|
|||||||
|
|
||||||
|
|
||||||
The cc-metric-collector tries to read the data from the system as it is reported. If available, it tries to read the metric unit from the system as well (e.g. from `/proc/meminfo`). The problem is that, depending on the source, the metric units are named differently. Just think about `byte`, `Byte`, `B`, `bytes`, ...
|
The cc-metric-collector tries to read the data from the system as it is reported. If available, it tries to read the metric unit from the system as well (e.g. from `/proc/meminfo`). The problem is that, depending on the source, the metric units are named differently. Just think about `byte`, `Byte`, `B`, `bytes`, ...
|
||||||
The [cc-units](https://github.com/ClusterCockpit/cc-lib/ccUnits) package provides us a normalization option to use the same metric unit name for all metrics. It this option is set to true, all `unit` meta tags are normalized.
|
The [cc-units](https://github.com/ClusterCockpit/cc-units) package provides us a normalization option to use the same metric unit name for all metrics. It this option is set to true, all `unit` meta tags are normalized.
|
||||||
|
|
||||||
## The `change_unit_prefix` section
|
## The `change_unit_prefix` section
|
||||||
|
|
||||||
__deprecated__
|
__deprecated__
|
||||||
|
|
||||||
It is often the case that metrics are reported by the system using a rather outdated unit prefix (like `/proc/meminfo` still uses kByte despite current memory sizes are in the GByte range). If you want to change the prefix of a unit, you can do that with the help of [cc-units](https://github.com/ClusterCockpit/cc-lib/ccUnits). The setting works on the metric name and requires the new prefix for the metric. The cc-units package determines the scaling factor.
|
It is often the case that metrics are reported by the system using a rather outdated unit prefix (like `/proc/meminfo` still uses kByte despite current memory sizes are in the GByte range). If you want to change the prefix of a unit, you can do that with the help of [cc-units](https://github.com/ClusterCockpit/cc-units). The setting works on the metric name and requires the new prefix for the metric. The cc-units package determines the scaling factor.
|
||||||
|
|
||||||
# Aggregate metric values of the current interval with the `interval_aggregates` option
|
# Aggregate metric values of the current interval with the `interval_aggregates` option
|
||||||
|
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package metricRouter
|
package metricRouter
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package metricRouter
|
package metricRouter
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package ccTopology
|
package ccTopology
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
125
pkg/hostlist/hostlist.go
Normal file
125
pkg/hostlist/hostlist.go
Normal file
@@ -0,0 +1,125 @@
|
|||||||
|
package hostlist
|
||||||
|
|
||||||
|
import (
|
||||||
|
"fmt"
|
||||||
|
"regexp"
|
||||||
|
"sort"
|
||||||
|
"strconv"
|
||||||
|
"strings"
|
||||||
|
)
|
||||||
|
|
||||||
|
func Expand(in string) (result []string, err error) {
|
||||||
|
|
||||||
|
// Create ranges regular expression
|
||||||
|
reStNumber := "[[:digit:]]+"
|
||||||
|
reStRange := reStNumber + "-" + reStNumber
|
||||||
|
reStOptionalNumberOrRange := "(" + reStNumber + ",|" + reStRange + ",)*"
|
||||||
|
reStNumberOrRange := "(" + reStNumber + "|" + reStRange + ")"
|
||||||
|
reStBraceLeft := "[[]"
|
||||||
|
reStBraceRight := "[]]"
|
||||||
|
reStRanges := reStBraceLeft +
|
||||||
|
reStOptionalNumberOrRange +
|
||||||
|
reStNumberOrRange +
|
||||||
|
reStBraceRight
|
||||||
|
reRanges := regexp.MustCompile(reStRanges)
|
||||||
|
|
||||||
|
// Create host list regular expression
|
||||||
|
reStDNSChars := "[a-zA-Z0-9-]+"
|
||||||
|
reStPrefix := "^(" + reStDNSChars + ")"
|
||||||
|
reStOptionalSuffix := "(" + reStDNSChars + ")?"
|
||||||
|
re := regexp.MustCompile(reStPrefix + "([[][0-9,-]+[]])?" + reStOptionalSuffix)
|
||||||
|
|
||||||
|
// Remove all delimiters from the input
|
||||||
|
in = strings.TrimLeft(in, ", ")
|
||||||
|
|
||||||
|
for len(in) > 0 {
|
||||||
|
if v := re.FindStringSubmatch(in); v != nil {
|
||||||
|
|
||||||
|
// Remove matched part from the input
|
||||||
|
lenPrefix := len(v[0])
|
||||||
|
in = in[lenPrefix:]
|
||||||
|
|
||||||
|
// Remove all delimiters from the input
|
||||||
|
in = strings.TrimLeft(in, ", ")
|
||||||
|
|
||||||
|
// matched prefix, range and suffix
|
||||||
|
hlPrefix := v[1]
|
||||||
|
hlRanges := v[2]
|
||||||
|
hlSuffix := v[3]
|
||||||
|
|
||||||
|
// Single node without ranges
|
||||||
|
if hlRanges == "" {
|
||||||
|
result = append(result, hlPrefix)
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
// Node with ranges
|
||||||
|
if v := reRanges.FindStringSubmatch(hlRanges); v != nil {
|
||||||
|
|
||||||
|
// Remove braces
|
||||||
|
hlRanges = hlRanges[1 : len(hlRanges)-1]
|
||||||
|
|
||||||
|
// Split host ranges at ,
|
||||||
|
for _, hlRange := range strings.Split(hlRanges, ",") {
|
||||||
|
|
||||||
|
// Split host range at -
|
||||||
|
RangeStartEnd := strings.Split(hlRange, "-")
|
||||||
|
|
||||||
|
// Range is only a single number
|
||||||
|
if len(RangeStartEnd) == 1 {
|
||||||
|
result = append(result, hlPrefix+RangeStartEnd[0]+hlSuffix)
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
// Range has a start and an end
|
||||||
|
widthRangeStart := len(RangeStartEnd[0])
|
||||||
|
widthRangeEnd := len(RangeStartEnd[1])
|
||||||
|
iStart, _ := strconv.ParseUint(RangeStartEnd[0], 10, 64)
|
||||||
|
iEnd, _ := strconv.ParseUint(RangeStartEnd[1], 10, 64)
|
||||||
|
if iStart > iEnd {
|
||||||
|
return nil, fmt.Errorf("single range start is greater than end: %s", hlRange)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Create print format string for range numbers
|
||||||
|
doPadding := widthRangeStart == widthRangeEnd
|
||||||
|
widthPadding := widthRangeStart
|
||||||
|
var formatString string
|
||||||
|
if doPadding {
|
||||||
|
formatString = "%0" + fmt.Sprint(widthPadding) + "d"
|
||||||
|
} else {
|
||||||
|
formatString = "%d"
|
||||||
|
}
|
||||||
|
formatString = hlPrefix + formatString + hlSuffix
|
||||||
|
|
||||||
|
// Add nodes from this range
|
||||||
|
for i := iStart; i <= iEnd; i++ {
|
||||||
|
result = append(result, fmt.Sprintf(formatString, i))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
return nil, fmt.Errorf("not at hostlist range: %s", hlRanges)
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
return nil, fmt.Errorf("not a hostlist: %s", in)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if result != nil {
|
||||||
|
// sort
|
||||||
|
sort.Strings(result)
|
||||||
|
|
||||||
|
// uniq
|
||||||
|
previous := 1
|
||||||
|
for current := 1; current < len(result); current++ {
|
||||||
|
if result[current-1] != result[current] {
|
||||||
|
if previous != current {
|
||||||
|
result[previous] = result[current]
|
||||||
|
}
|
||||||
|
previous++
|
||||||
|
}
|
||||||
|
}
|
||||||
|
result = result[:previous]
|
||||||
|
}
|
||||||
|
|
||||||
|
return
|
||||||
|
}
|
126
pkg/hostlist/hostlist_test.go
Normal file
126
pkg/hostlist/hostlist_test.go
Normal file
@@ -0,0 +1,126 @@
|
|||||||
|
package hostlist
|
||||||
|
|
||||||
|
import (
|
||||||
|
"testing"
|
||||||
|
)
|
||||||
|
|
||||||
|
func TestExpand(t *testing.T) {
|
||||||
|
|
||||||
|
// Compare two slices of strings
|
||||||
|
equal := func(a, b []string) bool {
|
||||||
|
if len(a) != len(b) {
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
for i, v := range a {
|
||||||
|
if v != b[i] {
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
type testDefinition struct {
|
||||||
|
input string
|
||||||
|
resultExpected []string
|
||||||
|
errorExpected bool
|
||||||
|
}
|
||||||
|
|
||||||
|
expandTests := []testDefinition{
|
||||||
|
{
|
||||||
|
// Single node
|
||||||
|
input: "n1",
|
||||||
|
resultExpected: []string{"n1"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Single node, duplicated
|
||||||
|
input: "n1,n1",
|
||||||
|
resultExpected: []string{"n1"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Single node with padding
|
||||||
|
input: "n[01]",
|
||||||
|
resultExpected: []string{"n01"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Single node with suffix
|
||||||
|
input: "n[01]-p",
|
||||||
|
resultExpected: []string{"n01-p"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Multiple nodes with a single range
|
||||||
|
input: "n[1-2]",
|
||||||
|
resultExpected: []string{"n1", "n2"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Multiple nodes with a single range and a single index
|
||||||
|
input: "n[1-2,3]",
|
||||||
|
resultExpected: []string{"n1", "n2", "n3"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Multiple nodes with different prefixes
|
||||||
|
input: "n[1-2],m[1,2]",
|
||||||
|
resultExpected: []string{"m1", "m2", "n1", "n2"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Multiple nodes with different suffixes
|
||||||
|
input: "n[1-2]-p,n[1,2]-q",
|
||||||
|
resultExpected: []string{"n1-p", "n1-q", "n2-p", "n2-q"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Multiple nodes with and without node ranges
|
||||||
|
input: " n09, n[01-04,06-07,09] , , n10,n04",
|
||||||
|
resultExpected: []string{"n01", "n02", "n03", "n04", "n06", "n07", "n09", "n10"},
|
||||||
|
errorExpected: false,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Forbidden DNS character
|
||||||
|
input: "n@",
|
||||||
|
resultExpected: []string{},
|
||||||
|
errorExpected: true,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Forbidden range
|
||||||
|
input: "n[1-2-2,3]",
|
||||||
|
resultExpected: []string{},
|
||||||
|
errorExpected: true,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
// Forbidden range limits
|
||||||
|
input: "n[2-1]",
|
||||||
|
resultExpected: []string{},
|
||||||
|
errorExpected: true,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
for _, expandTest := range expandTests {
|
||||||
|
result, err := Expand(expandTest.input)
|
||||||
|
|
||||||
|
hasError := err != nil
|
||||||
|
if hasError != expandTest.errorExpected && hasError {
|
||||||
|
t.Errorf("Expand('%s') failed: unexpected error '%v'",
|
||||||
|
expandTest.input, err)
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
if hasError != expandTest.errorExpected && !hasError {
|
||||||
|
t.Errorf("Expand('%s') did not fail as expected: got result '%+v'",
|
||||||
|
expandTest.input, result)
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
if !hasError && !equal(result, expandTest.resultExpected) {
|
||||||
|
t.Errorf("Expand('%s') failed: got result '%+v', expected result '%v'",
|
||||||
|
expandTest.input, result, expandTest.resultExpected)
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
t.Logf("Checked hostlist.Expand('%s'): result = '%+v', err = '%v'",
|
||||||
|
expandTest.input, result, err)
|
||||||
|
}
|
||||||
|
}
|
@@ -1,10 +1,3 @@
|
|||||||
// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
|
|
||||||
// All rights reserved. This file is part of cc-lib.
|
|
||||||
// Use of this source code is governed by a MIT-style
|
|
||||||
// license that can be found in the LICENSE file.
|
|
||||||
// additional authors:
|
|
||||||
// Holger Obermaier (NHR@KIT)
|
|
||||||
|
|
||||||
package multiChanTicker
|
package multiChanTicker
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
Reference in New Issue
Block a user