Add process start time to cluster metrics. (#11405)

master
Ritesh H Shukla 4 years ago committed by GitHub
parent 838d4dafbd
commit c4848f9b4f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
  1. 32
      cmd/metrics-v2.go
  2. 1
      docs/metrics/prometheus/list.md

@ -53,18 +53,19 @@ const (
capacityRawSubsystem MetricSubsystem = "capacity_raw" capacityRawSubsystem MetricSubsystem = "capacity_raw"
capacityUsableSubsystem MetricSubsystem = "capacity_usable" capacityUsableSubsystem MetricSubsystem = "capacity_usable"
diskSubsystem MetricSubsystem = "disk" diskSubsystem MetricSubsystem = "disk"
fileDescriptorSubsystem MetricSubsystem = "file_descriptor"
goRoutines MetricSubsystem = "go_routine" goRoutines MetricSubsystem = "go_routine"
ioSubsystem MetricSubsystem = "io"
nodesSubsystem MetricSubsystem = "nodes" nodesSubsystem MetricSubsystem = "nodes"
objectsSubsystem MetricSubsystem = "objects" objectsSubsystem MetricSubsystem = "objects"
fileDescriptorSubsystem MetricSubsystem = "file_descriptor" processSubsystem MetricSubsystem = "process"
ioSubsystem MetricSubsystem = "io"
replicationSubsystem MetricSubsystem = "replication" replicationSubsystem MetricSubsystem = "replication"
requestsSubsystem MetricSubsystem = "requests" requestsSubsystem MetricSubsystem = "requests"
timeSubsystem MetricSubsystem = "time" timeSubsystem MetricSubsystem = "time"
trafficSubsystem MetricSubsystem = "traffic" trafficSubsystem MetricSubsystem = "traffic"
softwareSubsystem MetricSubsystem = "software"
sysCallSubsystem MetricSubsystem = "syscall" sysCallSubsystem MetricSubsystem = "syscall"
usageSubsystem MetricSubsystem = "usage" usageSubsystem MetricSubsystem = "usage"
softwareSubsystem MetricSubsystem = "software"
) )
// MetricName are the individual names for the metric. // MetricName are the individual names for the metric.
@ -107,6 +108,7 @@ const (
ttfbDistribution = "ttbf_seconds_distribution" ttfbDistribution = "ttbf_seconds_distribution"
lastActivityTime = "last_activity_nano_seconds" lastActivityTime = "last_activity_nano_seconds"
startTime = "starttime_seconds"
) )
const ( const (
@ -631,6 +633,15 @@ func getMinIOGORoutineCountMD() MetricDescription {
Type: gaugeMetric, Type: gaugeMetric,
} }
} }
func getMinIOProcessStartTimeMD() MetricDescription {
return MetricDescription{
Namespace: nodeMetricNamespace,
Subsystem: processSubsystem,
Name: startTime,
Help: "Start time for MinIO process per node in seconds.",
Type: gaugeMetric,
}
}
func getMinioProcMetrics() MetricsGroup { func getMinioProcMetrics() MetricsGroup {
return MetricsGroup{ return MetricsGroup{
Metrics: []Metric{}, Metrics: []Metric{},
@ -656,6 +667,16 @@ func getMinioProcMetrics() MetricsGroup {
logger.LogOnceIf(ctx, err, ioSubsystem) logger.LogOnceIf(ctx, err, ioSubsystem)
return return
} }
stat, err := p.Stat()
if err != nil {
logger.LogOnceIf(ctx, err, processSubsystem)
return
}
startTime, err := stat.StartTime()
if err != nil {
logger.LogOnceIf(ctx, err, startTime)
return
}
metrics.Metrics = append(metrics.Metrics, metrics.Metrics = append(metrics.Metrics,
Metric{ Metric{
@ -698,6 +719,11 @@ func getMinioProcMetrics() MetricsGroup {
Description: getMinioProcessIOWriteCachedBytesMD(), Description: getMinioProcessIOWriteCachedBytesMD(),
Value: float64(io.WChar), Value: float64(io.WChar),
}) })
metrics.Metrics = append(metrics.Metrics,
Metric{
Description: getMinIOProcessStartTimeMD(),
Value: startTime,
})
}, },
} }
} }

@ -37,6 +37,7 @@ These metrics can be from any MinIO server once per collection.
|`minio_node_io_read_bytes` |Total bytes read by the process from the underlying storage system, /proc/[pid]/io read_bytes | |`minio_node_io_read_bytes` |Total bytes read by the process from the underlying storage system, /proc/[pid]/io read_bytes |
|`minio_node_io_wchar_bytes` |Total bytes written by the process to the underlying storage system including page cache, /proc/[pid]/io wchar | |`minio_node_io_wchar_bytes` |Total bytes written by the process to the underlying storage system including page cache, /proc/[pid]/io wchar |
|`minio_node_io_write_bytes` |Total bytes written by the process to the underlying storage system, /proc/[pid]/io write_bytes | |`minio_node_io_write_bytes` |Total bytes written by the process to the underlying storage system, /proc/[pid]/io write_bytes |
|`minio_node_process_starttime_seconds` |Start time for MinIO process per node in seconds. |
|`minio_node_syscall_read_total` |Total read SysCalls to the kernel. /proc/[pid]/io syscr | |`minio_node_syscall_read_total` |Total read SysCalls to the kernel. /proc/[pid]/io syscr |
|`minio_node_syscall_write_total` |Total write SysCalls to the kernel. /proc/[pid]/io syscw | |`minio_node_syscall_write_total` |Total write SysCalls to the kernel. /proc/[pid]/io syscw |
|`minio_s3_requests_error_total` |Total number S3 requests with errors | |`minio_s3_requests_error_total` |Total number S3 requests with errors |

Loading…
Cancel
Save