PMM-5058 Update node_exporter-like metrics.

.travis.yml

@@ -32,8 +32,8 @@ env:
   global:
     # AWS - PMM Autotest account. TODO https://jira.percona.com/browse/PMM-4896
     # Travis secrets are not exposed to pull requests from forks: https://docs.travis-ci.com/user/pull-requests#pull-requests-and-security-restrictions
-    - AWS_ACCESS_KEY=AKIAZPBRO3QWINUW4BHY
-    - secure: "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"
+    - AWS_ACCESS_KEY=AKIAZPBRO3QWKASXOQEZ
+    - secure: "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"
 
 script:
   - make travis

README.md

@@ -20,10 +20,11 @@ Create configration file `config.yml`:
 ```yaml
 ---
 instances:
-  - instance: rds-aurora1
-    region: us-east-1
-  - instance: rds-mysql57
-    region: us-east-1
+  - region: us-east-1
+    instance: rds-aurora1
+
+  - region: us-east-1
+    instance: rds-mysql57
     aws_access_key: AKIAIOSFODNN7EXAMPLE
     aws_secret_key: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
     labels:

basic/collector_test.go

@@ -16,7 +16,7 @@ import (
 func getCollector(t *testing.T) *Collector {
 	t.Helper()
 
-	cfg, err := config.Load("../config.yml")
+	cfg, err := config.Load("../config.tests.yml")
 	require.NoError(t, err)
 	client := client.New()
 	sess, err := sessions.New(cfg.Instances, client.HTTP(), false)

config.tests.yml

@@ -0,0 +1,12 @@
+---
+# Shared configuration for all tests.
+
+instances:
+  - region: us-east-1
+    instance: rds-aurora1
+  - region: us-east-1
+    instance: rds-aurora57
+  - region: us-east-1
+    instance: rds-mysql56
+  - region: us-west-1
+    instance: rds-mysql57

enhanced/metrics.go

@@ -98,22 +98,22 @@ type loadAverageMinute struct {
 
 //nolint:lll
 type memory struct {
-	Active         int `json:"active"         node:"Active"          m:"1024" help:"The amount of assigned memory, in kilobytes."`
-	Buffers        int `json:"buffers"        node:"Buffers"         m:"1024" help:"The amount of memory used for buffering I/O requests prior to writing to the storage device, in kilobytes."`
-	Cached         int `json:"cached"         node:"Cached"          m:"1024" help:"The amount of memory used for caching file system–based I/O."`
-	Dirty          int `json:"dirty"          node:"Dirty"           m:"1024" help:"The amount of memory pages in RAM that have been modified but not written to their related data block in storage, in kilobytes."`
-	Free           int `json:"free"           node:"MemFree"         m:"1024" help:"The amount of unassigned memory, in kilobytes."`
-	HugePagesFree  int `json:"hugePagesFree"  node:"HugePages_Free"  m:"1"    help:"The number of free huge pages. Huge pages are a feature of the Linux kernel."`
-	HugePagesRsvd  int `json:"hugePagesRsvd"  node:"HugePages_Rsvd"  m:"1"    help:"The number of committed huge pages."`
-	HugePagesSize  int `json:"hugePagesSize"  node:"Hugepagesize"    m:"1024" help:"The size for each huge pages unit, in kilobytes."`
-	HugePagesSurp  int `json:"hugePagesSurp"  node:"HugePages_Surp"  m:"1"    help:"The number of available surplus huge pages over the total."`
-	HugePagesTotal int `json:"hugePagesTotal" node:"HugePages_Total" m:"1"    help:"The total number of huge pages for the system."`
-	Inactive       int `json:"inactive"       node:"Inactive"        m:"1024" help:"The amount of least-frequently used memory pages, in kilobytes."`
-	Mapped         int `json:"mapped"         node:"Mapped"          m:"1024" help:"The total amount of file-system contents that is memory mapped inside a process address space, in kilobytes."`
-	PageTables     int `json:"pageTables"     node:"PageTables"      m:"1024" help:"The amount of memory used by page tables, in kilobytes."`
-	Slab           int `json:"slab"           node:"Slab"            m:"1024" help:"The amount of reusable kernel data structures, in kilobytes."`
-	Total          int `json:"total"          node:"MemTotal"        m:"1024" help:"The total amount of memory, in kilobytes."`
-	Writeback      int `json:"writeback"      node:"Writeback"       m:"1024" help:"The amount of dirty pages in RAM that are still being written to the backing storage, in kilobytes."`
+	Active         int `json:"active"         node:"Active_bytes"       m:"1024" help:"The amount of assigned memory, in kilobytes."`
+	Buffers        int `json:"buffers"        node:"Buffers_bytes"      m:"1024" help:"The amount of memory used for buffering I/O requests prior to writing to the storage device, in kilobytes."`
+	Cached         int `json:"cached"         node:"Cached_bytes"       m:"1024" help:"The amount of memory used for caching file system–based I/O."`
+	Dirty          int `json:"dirty"          node:"Dirty_bytes"        m:"1024" help:"The amount of memory pages in RAM that have been modified but not written to their related data block in storage, in kilobytes."`
+	Free           int `json:"free"           node:"MemFree_bytes"      m:"1024" help:"The amount of unassigned memory, in kilobytes."`
+	HugePagesFree  int `json:"hugePagesFree"  node:"HugePages_Free"     m:"1"    help:"The number of free huge pages. Huge pages are a feature of the Linux kernel."`
+	HugePagesRsvd  int `json:"hugePagesRsvd"  node:"HugePages_Rsvd"     m:"1"    help:"The number of committed huge pages."`
+	HugePagesSize  int `json:"hugePagesSize"  node:"Hugepagesize_bytes" m:"1024" help:"The size for each huge pages unit, in kilobytes."`
+	HugePagesSurp  int `json:"hugePagesSurp"  node:"HugePages_Surp"     m:"1"    help:"The number of available surplus huge pages over the total."`
+	HugePagesTotal int `json:"hugePagesTotal" node:"HugePages_Total"    m:"1"    help:"The total number of huge pages for the system."`
+	Inactive       int `json:"inactive"       node:"Inactive_bytes"     m:"1024" help:"The amount of least-frequently used memory pages, in kilobytes."`
+	Mapped         int `json:"mapped"         node:"Mapped_bytes"       m:"1024" help:"The total amount of file-system contents that is memory mapped inside a process address space, in kilobytes."`
+	PageTables     int `json:"pageTables"     node:"PageTables_bytes"   m:"1024" help:"The amount of memory used by page tables, in kilobytes."`
+	Slab           int `json:"slab"           node:"Slab_bytes"         m:"1024" help:"The amount of reusable kernel data structures, in kilobytes."`
+	Total          int `json:"total"          node:"MemTotal_bytes"     m:"1024" help:"The total amount of memory, in kilobytes."`
+	Writeback      int `json:"writeback"      node:"Writeback_bytes"    m:"1024" help:"The amount of dirty pages in RAM that are still being written to the backing storage, in kilobytes."`
 }
 
 type network struct {
@@ -136,9 +136,9 @@ type processList struct {
 
 //nolint:lll
 type swap struct {
-	Cached float64 `json:"cached" node:"node_memory_SwapCached" m:"1024" help:"The amount of swap memory, in kilobytes, used as cache memory."  nodehelp:"Memory information field SwapCached."`
-	Free   float64 `json:"free"   node:"node_memory_SwapFree"   m:"1024" help:"The total amount of swap memory free, in kilobytes."             nodehelp:"Memory information field SwapFree."`
-	Total  float64 `json:"total"  node:"node_memory_SwapTotal"  m:"1024" help:"The total amount of swap memory available, in kilobytes."        nodehelp:"Memory information field SwapTotal."`
+	Cached float64 `json:"cached" node:"node_memory_SwapCached_bytes" m:"1024" help:"The amount of swap memory, in kilobytes, used as cache memory."  nodehelp:"Memory information field SwapCached."`
+	Free   float64 `json:"free"   node:"node_memory_SwapFree_bytes"   m:"1024" help:"The total amount of swap memory free, in kilobytes."             nodehelp:"Memory information field SwapFree."`
+	Total  float64 `json:"total"  node:"node_memory_SwapTotal_bytes"  m:"1024" help:"The total amount of swap memory available, in kilobytes."        nodehelp:"Memory information field SwapTotal."`
 
 	// we use multiplier 0.25 to convert a number of kilobytes to a number of 4k pages (what our dashboards assume)
 	In  float64 `json:"in"  node:"node_vmstat_pswpin"  m:"0.25" help:"The total amount of memory, in kilobytes, swapped in from disk." nodehelp:"/proc/vmstat information field pswpin"`
@@ -259,12 +259,12 @@ func makeNodeDiskMetrics(s *diskIO, constLabels prometheus.Labels) []prometheus.
 	res := make([]prometheus.Metric, 0, 2)
 
 	if s.ReadKb != nil {
-		desc := prometheus.NewDesc("node_disk_bytes_read", "The total number of bytes read successfully.", labelKeys, constLabels)
+		desc := prometheus.NewDesc("node_disk_read_bytes_total", "The total number of bytes read successfully.", labelKeys, constLabels)
 		m := prometheus.MustNewConstMetric(desc, prometheus.CounterValue, float64(*s.ReadKb*1024), labelValues...)
 		res = append(res, m)
 	}
 	if s.WriteKb != nil {
-		desc := prometheus.NewDesc("node_disk_bytes_written", "The total number of bytes written successfully.", labelKeys, constLabels)
+		desc := prometheus.NewDesc("node_disk_written_bytes_total", "The total number of bytes written successfully.", labelKeys, constLabels)
 		m := prometheus.MustNewConstMetric(desc, prometheus.CounterValue, float64(*s.WriteKb*1024), labelValues...)
 		res = append(res, m)
 	}
@@ -310,11 +310,11 @@ func makeNodeFilesystemMetrics(s *fileSys, constLabels prometheus.Labels) []prom
 	res = append(res, prometheus.MustNewConstMetric(desc, prometheus.GaugeValue, float64((s.MaxFiles-s.UsedFiles)*1024), labelValues...))
 
 	// report the same value for node_filesystem_free and node_filesystem_avail because we use both metrics in our dashboards
-	desc = prometheus.NewDesc("node_filesystem_size", "Filesystem size in bytes.", labelKeys, constLabels)
+	desc = prometheus.NewDesc("node_filesystem_size_bytes", "Filesystem size in bytes.", labelKeys, constLabels)
 	res = append(res, prometheus.MustNewConstMetric(desc, prometheus.GaugeValue, float64(s.Total*1024), labelValues...))
-	desc = prometheus.NewDesc("node_filesystem_free", "Filesystem free space in bytes.", labelKeys, constLabels)
+	desc = prometheus.NewDesc("node_filesystem_free_bytes", "Filesystem free space in bytes.", labelKeys, constLabels)
 	res = append(res, prometheus.MustNewConstMetric(desc, prometheus.GaugeValue, float64((s.Total-s.Used)*1024), labelValues...))
-	desc = prometheus.NewDesc("node_filesystem_avail", "Filesystem space available to non-root users in bytes.", labelKeys, constLabels)
+	desc = prometheus.NewDesc("node_filesystem_avail_bytes", "Filesystem space available to non-root users in bytes.", labelKeys, constLabels)
 	res = append(res, prometheus.MustNewConstMetric(desc, prometheus.GaugeValue, float64((s.Total-s.Used)*1024), labelValues...))
 
 	return res