Node_Exporter/collector/mdadm_linux.go
Ben Kochie 3e1b0f1bee
Don't count empty collection as success ()
Many collectors depend on underlying features to be enabled. This causes
confusion about what "success" means. This changes the behavior of the
`node_scrape_collector_success` metric.

* When a collector is unable to find data don't return success.
* Catch the no data error and send to Debug log level to avoid log spam.
* Update collectors to support this new functionality.
* Fix copy-pasta mistake in infiband debug message.

Closes: https://github.com/prometheus/node_exporter/issues/1323

Signed-off-by: Ben Kochie <superq@gmail.com>
2020-02-19 16:11:29 +01:00

192 lines
4.5 KiB
Go

// Copyright 2015 The Prometheus Authors
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
// +build !nomdadm
package collector
import (
"fmt"
"os"
"github.com/go-kit/kit/log"
"github.com/go-kit/kit/log/level"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/procfs"
)
type mdadmCollector struct {
logger log.Logger
}
func init() {
registerCollector("mdadm", defaultEnabled, NewMdadmCollector)
}
// NewMdadmCollector returns a new Collector exposing raid statistics.
func NewMdadmCollector(logger log.Logger) (Collector, error) {
return &mdadmCollector{logger}, nil
}
var (
activeDesc = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "md", "state"),
"Indicates the state of md-device.",
[]string{"device"},
prometheus.Labels{"state": "active"},
)
inActiveDesc = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "md", "state"),
"Indicates the state of md-device.",
[]string{"device"},
prometheus.Labels{"state": "inactive"},
)
recoveringDesc = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "md", "state"),
"Indicates the state of md-device.",
[]string{"device"},
prometheus.Labels{"state": "recovering"},
)
resyncDesc = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "md", "state"),
"Indicates the state of md-device.",
[]string{"device"},
prometheus.Labels{"state": "resync"},
)
disksDesc = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "md", "disks"),
"Number of active/failed/spare disks of device.",
[]string{"device", "state"},
nil,
)
disksTotalDesc = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "md", "disks_required"),
"Total number of disks of device.",
[]string{"device"},
nil,
)
blocksTotalDesc = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "md", "blocks"),
"Total number of blocks on device.",
[]string{"device"},
nil,
)
blocksSyncedDesc = prometheus.NewDesc(
prometheus.BuildFQName(namespace, "md", "blocks_synced"),
"Number of blocks synced on device.",
[]string{"device"},
nil,
)
)
func (c *mdadmCollector) Update(ch chan<- prometheus.Metric) error {
fs, errFs := procfs.NewFS(*procPath)
if errFs != nil {
return fmt.Errorf("failed to open procfs: %w", errFs)
}
mdStats, err := fs.MDStat()
if err != nil {
if os.IsNotExist(err) {
level.Debug(c.logger).Log("msg", "Not collecting mdstat, file does not exist", "file", *procPath)
return ErrNoData
}
return fmt.Errorf("error parsing mdstatus: %s", err)
}
for _, mdStat := range mdStats {
level.Debug(c.logger).Log("msg", "collecting metrics for device", "device", mdStat.Name)
stateVals := make(map[string]float64)
stateVals[mdStat.ActivityState] = 1
ch <- prometheus.MustNewConstMetric(
disksTotalDesc,
prometheus.GaugeValue,
float64(mdStat.DisksTotal),
mdStat.Name,
)
ch <- prometheus.MustNewConstMetric(
disksDesc,
prometheus.GaugeValue,
float64(mdStat.DisksActive),
mdStat.Name,
"active",
)
ch <- prometheus.MustNewConstMetric(
disksDesc,
prometheus.GaugeValue,
float64(mdStat.DisksFailed),
mdStat.Name,
"failed",
)
ch <- prometheus.MustNewConstMetric(
disksDesc,
prometheus.GaugeValue,
float64(mdStat.DisksSpare),
mdStat.Name,
"spare",
)
ch <- prometheus.MustNewConstMetric(
activeDesc,
prometheus.GaugeValue,
stateVals["active"],
mdStat.Name,
)
ch <- prometheus.MustNewConstMetric(
inActiveDesc,
prometheus.GaugeValue,
stateVals["inactive"],
mdStat.Name,
)
ch <- prometheus.MustNewConstMetric(
recoveringDesc,
prometheus.GaugeValue,
stateVals["recovering"],
mdStat.Name,
)
ch <- prometheus.MustNewConstMetric(
resyncDesc,
prometheus.GaugeValue,
stateVals["resyncing"],
mdStat.Name,
)
ch <- prometheus.MustNewConstMetric(
blocksTotalDesc,
prometheus.GaugeValue,
float64(mdStat.BlocksTotal),
mdStat.Name,
)
ch <- prometheus.MustNewConstMetric(
blocksSyncedDesc,
prometheus.GaugeValue,
float64(mdStat.BlocksSynced),
mdStat.Name,
)
}
return nil
}