Add process summary metrics

As we're enabling `include_top_n` by default, a few visualizations from the Metricbeat-processes list were no longer correct (as they aggregate only a sample of the data). This adds a new `process_summary` metricset that adds these metrics. The fields are namespaced under `process.summary`. This PR adds summary metrics for the total number of processes and their state, as an extra document created by the `system.process` metricset.
elastic · May 12, 2017 · fbac667 · fbac667
1 parent e48b5d4
commit fbac667
Show file tree

Hide file tree

Showing 22 changed files with 345 additions and 31 deletions.
diff --git a/CHANGELOG.asciidoc b/CHANGELOG.asciidoc
@@ -55,6 +55,7 @@ https://github.com/elastic/beats/compare/v6.0.0-alpha1...master[Check the HEAD d
 *Metricbeat*
 
 - Add macOS implementation of the system diskio metricset. {issue}4144[4144]
+- Add process_summary metricset that records high level metrics about processes. {pull}4231[4231]
 
 *Packetbeat*
 

diff --git a/metricbeat/docs/fields.asciidoc b/metricbeat/docs/fields.asciidoc
@@ -10512,6 +10512,69 @@ type: long
 Total number of I/O operations performed on all devices by processes in the cgroup as seen by the throttling policy.
 
 
+[float]
+== process.summary Fields
+
+Summary metrics for the processes running on the host.
+
+
+
+[float]
+=== system.process.summary.total
+
+type: long
+
+Total number of processes on this host.
+
+
+[float]
+=== system.process.summary.running
+
+type: long
+
+Number of running processes on this host.
+
+
+[float]
+=== system.process.summary.idle
+
+type: long
+
+Number of idle processes on this host.
+
+
+[float]
+=== system.process.summary.sleeping
+
+type: long
+
+Number of sleeping processes on this host.
+
+
+[float]
+=== system.process.summary.stopped
+
+type: long
+
+Number of stopped processes on this host.
+
+
+[float]
+=== system.process.summary.zombie
+
+type: long
+
+Number of zombie processes on this host.
+
+
+[float]
+=== system.process.summary.unknown
+
+type: long
+
+Number of processes for which the state couldn't be retrieved or is unknown.
+
+
 [float]
 == socket Fields
 

diff --git a/metricbeat/docs/modules/system.asciidoc b/metricbeat/docs/modules/system.asciidoc
@@ -111,6 +111,9 @@ metricbeat.modules:
     # Network stats
     - network
 
+    # Processes summary
+    - process_summary
+
     # Per process stats
     - process
 
@@ -147,6 +150,8 @@ The following metricsets are available:
 
 * <<metricbeat-metricset-system-process,process>>
 
+* <<metricbeat-metricset-system-process_summary,process_summary>>
+
 * <<metricbeat-metricset-system-socket,socket>>
 
 include::system/core.asciidoc[]
@@ -167,5 +172,7 @@ include::system/network.asciidoc[]
 
 include::system/process.asciidoc[]
 
+include::system/process_summary.asciidoc[]
+
 include::system/socket.asciidoc[]
 
diff --git a/metricbeat/docs/modules/system/process_summary.asciidoc b/metricbeat/docs/modules/system/process_summary.asciidoc
@@ -0,0 +1,19 @@
+////
+This file is generated! See scripts/docs_collector.py
+////
+
+[[metricbeat-metricset-system-process_summary]]
+include::../../../module/system/process_summary/_meta/docs.asciidoc[]
+
+
+==== Fields
+
+For a description of each field in the metricset, see the
+<<exported-fields-system,exported fields>> section.
+
+Here is an example document generated by this metricset:
+
+[source,json]
+----
+include::../../../module/system/process_summary/_meta/data.json[]
+----
diff --git a/metricbeat/include/list.go b/metricbeat/include/list.go
@@ -87,6 +87,7 @@ import (
 	_ "github.com/elastic/beats/metricbeat/module/system/memory"
 	_ "github.com/elastic/beats/metricbeat/module/system/network"
 	_ "github.com/elastic/beats/metricbeat/module/system/process"
+	_ "github.com/elastic/beats/metricbeat/module/system/process_summary"
 	_ "github.com/elastic/beats/metricbeat/module/system/socket"
 	_ "github.com/elastic/beats/metricbeat/module/vsphere"
 	_ "github.com/elastic/beats/metricbeat/module/vsphere/datastore"

diff --git a/metricbeat/metricbeat.full.yml b/metricbeat/metricbeat.full.yml
@@ -52,6 +52,9 @@ metricbeat.modules:
     # Network stats
     - network
 
+    # Processes summary
+    - process_summary
+
     # Per process stats
     - process
 

diff --git a/metricbeat/metricbeat.yml b/metricbeat/metricbeat.yml
@@ -37,6 +37,9 @@ metricbeat.modules:
     # Network stats
     - network
 
+    # Processes summary
+    - process_summary
+
     # Per process stats
     - process
 

diff --git a/metricbeat/module/system/_meta/config.full.yml b/metricbeat/module/system/_meta/config.full.yml
@@ -24,6 +24,9 @@
     # Network stats
     - network
 
+    # Processes summary
+    - process_summary
+
     # Per process stats
     - process
 

diff --git a/metricbeat/module/system/_meta/config.yml b/metricbeat/module/system/_meta/config.yml
@@ -24,6 +24,9 @@
     # Network stats
     - network
 
+    # Processes summary
+    - process_summary
+
     # Per process stats
     - process
 

diff --git a/metricbeat/module/system/_meta/kibana/dashboard/Metricbeat-processes.json b/metricbeat/module/system/_meta/kibana/dashboard/Metricbeat-processes.json
@@ -4,7 +4,7 @@
   "description": "", 
   "title": "Metricbeat-processes", 
   "uiStateJSON": "{\"P-1\":{\"vis\":{\"params\":{\"sort\":{\"columnIndex\":null,\"direction\":null}}}},\"P-4\":{\"vis\":{\"params\":{\"sort\":{\"columnIndex\":null,\"direction\":null}}}}}", 
-  "panelsJSON": "[{\"col\":1,\"id\":\"System-Navigation\",\"panelIndex\":5,\"row\":1,\"size_x\":12,\"size_y\":1,\"type\":\"visualization\"},{\"col\":1,\"id\":\"Number-of-processes\",\"panelIndex\":7,\"row\":2,\"size_x\":3,\"size_y\":3,\"type\":\"visualization\"},{\"col\":4,\"id\":\"Process-state-by-host\",\"panelIndex\":9,\"row\":2,\"size_x\":5,\"size_y\":3,\"type\":\"visualization\"},{\"col\":9,\"id\":\"Number-of-processes-by-host\",\"panelIndex\":8,\"row\":2,\"size_x\":4,\"size_y\":3,\"type\":\"visualization\"},{\"col\":1,\"id\":\"CPU-usage-per-process\",\"panelIndex\":2,\"row\":8,\"size_x\":6,\"size_y\":8,\"type\":\"visualization\"},{\"col\":7,\"id\":\"Memory-usage-per-process\",\"panelIndex\":3,\"row\":8,\"size_x\":6,\"size_y\":8,\"type\":\"visualization\"},{\"col\":1,\"id\":\"Top-processes-by-memory-usage\",\"panelIndex\":1,\"row\":16,\"size_x\":6,\"size_y\":11,\"type\":\"visualization\"},{\"col\":7,\"id\":\"Top-processes-by-CPU-usage\",\"panelIndex\":4,\"row\":16,\"size_x\":6,\"size_y\":11,\"type\":\"visualization\"},{\"id\":\"Number-of-processes-over-time\",\"type\":\"visualization\",\"panelIndex\":10,\"size_x\":12,\"size_y\":3,\"col\":1,\"row\":5}]", 
+  "panelsJSON": "[{\"col\":1,\"id\":\"System-Navigation\",\"panelIndex\":5,\"row\":1,\"size_x\":12,\"size_y\":1,\"type\":\"visualization\"},{\"col\":1,\"id\":\"Number-of-processes\",\"panelIndex\":7,\"row\":2,\"size_x\":3,\"size_y\":3,\"type\":\"visualization\"},{\"col\":1,\"id\":\"CPU-usage-per-process\",\"panelIndex\":2,\"row\":5,\"size_x\":6,\"size_y\":8,\"type\":\"visualization\"},{\"col\":7,\"id\":\"Memory-usage-per-process\",\"panelIndex\":3,\"row\":5,\"size_x\":6,\"size_y\":8,\"type\":\"visualization\"},{\"col\":1,\"id\":\"Top-processes-by-memory-usage\",\"panelIndex\":1,\"row\":13,\"size_x\":6,\"size_y\":6,\"type\":\"visualization\"},{\"col\":7,\"id\":\"Top-processes-by-CPU-usage\",\"panelIndex\":4,\"row\":13,\"size_x\":6,\"size_y\":6,\"type\":\"visualization\"},{\"col\":4,\"id\":\"Number-of-processes-over-time\",\"panelIndex\":10,\"row\":2,\"size_x\":9,\"size_y\":3,\"type\":\"visualization\"}]", 
   "optionsJSON": "{\"darkTheme\":false}", 
   "version": 1, 
   "kibanaSavedObjectMeta": {

diff --git a/metricbeat/module/system/_meta/kibana/visualization/Number-of-processes-by-host.json b/metricbeat/module/system/_meta/kibana/visualization/Number-of-processes-by-host.json
diff --git a/metricbeat/module/system/_meta/kibana/visualization/Number-of-processes-over-time.json b/metricbeat/module/system/_meta/kibana/visualization/Number-of-processes-over-time.json
@@ -1,11 +1,10 @@
 {
-  "visState": "{\"title\":\"Number of processes over time\",\"type\":\"line\",\"params\":{\"shareYAxis\":true,\"addTooltip\":true,\"addLegend\":true,\"legendPosition\":\"right\",\"showCircles\":true,\"smoothLines\":false,\"interpolate\":\"linear\",\"scale\":\"linear\",\"drawLinesBetweenPoints\":true,\"radiusRatio\":9,\"times\":[],\"addTimeMarker\":false,\"defaultYExtents\":false,\"setYExtents\":false,\"yAxis\":{}},\"aggs\":[{\"id\":\"1\",\"enabled\":true,\"type\":\"cardinality\",\"schema\":\"metric\",\"params\":{\"field\":\"system.process.pid\",\"customLabel\":\"Number of processes\"}},{\"id\":\"2\",\"enabled\":true,\"type\":\"date_histogram\",\"schema\":\"segment\",\"params\":{\"field\":\"@timestamp\",\"interval\":\"auto\",\"customInterval\":\"2h\",\"min_doc_count\":1,\"extended_bounds\":{}}}],\"listeners\":{}}", 
+  "visState": "{\"title\":\"Number of processes over time\",\"type\":\"line\",\"params\":{\"shareYAxis\":true,\"addTooltip\":true,\"addLegend\":true,\"legendPosition\":\"bottom\",\"showCircles\":true,\"smoothLines\":false,\"interpolate\":\"linear\",\"scale\":\"linear\",\"drawLinesBetweenPoints\":true,\"radiusRatio\":9,\"times\":[],\"addTimeMarker\":false,\"defaultYExtents\":false,\"setYExtents\":false,\"yAxis\":{},\"grid\":{\"categoryLines\":false,\"style\":{\"color\":\"#eee\"}},\"categoryAxes\":[{\"id\":\"CategoryAxis-1\",\"type\":\"category\",\"position\":\"bottom\",\"show\":true,\"style\":{},\"scale\":{\"type\":\"linear\"},\"labels\":{\"show\":true,\"truncate\":100},\"title\":{\"text\":\"@timestamp per 30 seconds\"}}],\"valueAxes\":[{\"id\":\"ValueAxis-1\",\"name\":\"LeftAxis-1\",\"type\":\"value\",\"position\":\"left\",\"show\":true,\"style\":{},\"scale\":{\"type\":\"linear\",\"mode\":\"normal\"},\"labels\":{\"show\":true,\"rotate\":0,\"filter\":false,\"truncate\":100},\"title\":{\"text\":\"Average system.process.summary.total\"}}],\"seriesParams\":[{\"show\":true,\"mode\":\"normal\",\"type\":\"line\",\"drawLinesBetweenPoints\":true,\"showCircles\":true,\"interpolate\":\"linear\",\"lineWidth\":2,\"data\":{\"id\":\"1\",\"label\":\"Average system.process.summary.total\"},\"valueAxis\":\"ValueAxis-1\"}]},\"aggs\":[{\"id\":\"1\",\"enabled\":true,\"type\":\"avg\",\"schema\":\"metric\",\"params\":{\"field\":\"system.process.summary.total\"}},{\"id\":\"2\",\"enabled\":true,\"type\":\"date_histogram\",\"schema\":\"segment\",\"params\":{\"field\":\"@timestamp\",\"interval\":\"auto\",\"customInterval\":\"2h\",\"min_doc_count\":1,\"extended_bounds\":{}}}],\"listeners\":{}}", 
   "description": "", 
   "title": "Number of processes over time", 
   "uiStateJSON": "{}", 
   "version": 1, 
-  "savedSearchId": "Process-stats", 
   "kibanaSavedObjectMeta": {
-    "searchSourceJSON": "{\"filter\":[]}"
+    "searchSourceJSON": "{\"filter\":[],\"index\":\"metricbeat-*\",\"query\":{\"query_string\":{\"query\":\"metricset.name: process_summary\",\"analyze_wildcard\":true}},\"highlight\":{\"pre_tags\":[\"@kibana-highlighted-field@\"],\"post_tags\":[\"@/kibana-highlighted-field@\"],\"fields\":{\"*\":{}},\"require_field_match\":false,\"fragment_size\":2147483647}}"
   }
 }
diff --git a/metricbeat/module/system/_meta/kibana/visualization/Number-of-processes.json b/metricbeat/module/system/_meta/kibana/visualization/Number-of-processes.json
@@ -1,11 +1,10 @@
 {
-  "visState": "{\"title\":\"Number of processes\",\"type\":\"metric\",\"params\":{\"handleNoResults\":true,\"fontSize\":\"40\"},\"aggs\":[{\"id\":\"1\",\"enabled\":true,\"type\":\"cardinality\",\"schema\":\"metric\",\"params\":{\"field\":\"system.process.name\",\"customLabel\":\"Number of Processes\"}}],\"listeners\":{}}", 
+  "visState": "{\"title\":\"Number of processes\",\"type\":\"metric\",\"params\":{\"fontSize\":\"40\",\"handleNoResults\":true},\"aggs\":[{\"id\":\"1\",\"enabled\":true,\"type\":\"max\",\"schema\":\"metric\",\"params\":{\"field\":\"system.process.summary.total\",\"customLabel\":\"Max number of processes\"}}],\"listeners\":{}}", 
   "description": "", 
   "title": "Number of processes", 
   "uiStateJSON": "{}", 
   "version": 1, 
-  "savedSearchId": "Process-stats", 
   "kibanaSavedObjectMeta": {
-    "searchSourceJSON": "{\"filter\":[]}"
+    "searchSourceJSON": "{\"filter\":[],\"index\":\"metricbeat-*\",\"query\":{\"query_string\":{\"query\":\"metricset.name:process_summary\",\"analyze_wildcard\":true}},\"highlight\":{\"pre_tags\":[\"@kibana-highlighted-field@\"],\"post_tags\":[\"@/kibana-highlighted-field@\"],\"fields\":{\"*\":{}},\"require_field_match\":false,\"fragment_size\":2147483647}}"
   }
 }
diff --git a/metricbeat/module/system/_meta/kibana/visualization/Process-state-by-host.json b/metricbeat/module/system/_meta/kibana/visualization/Process-state-by-host.json
diff --git a/metricbeat/module/system/process/helper.go b/metricbeat/module/system/process/helper.go
@@ -16,6 +16,7 @@ import (
 	"github.com/elastic/beats/metricbeat/module/system"
 	"github.com/elastic/beats/metricbeat/module/system/memory"
 	sigar "github.com/elastic/gosigar"
+	"github.com/pkg/errors"
 )
 
 type ProcsMap map[int]*Process
@@ -335,8 +336,7 @@ func (procStats *ProcStats) GetProcStats() ([]common.MapStr, error) {
 
 	pids, err := Pids()
 	if err != nil {
-		logp.Warn("Getting the list of pids: %v", err)
-		return nil, err
+		return nil, errors.Wrap(err, "failed to fetch the list of PIDs")
 	}
 
 	var processes []Process

diff --git a/metricbeat/module/system/process_summary/_meta/data.json b/metricbeat/module/system/process_summary/_meta/data.json
@@ -0,0 +1,24 @@
+{
+    "@timestamp": "2016-05-23T08:05:34.853Z",
+    "beat": {
+        "hostname": "host.example.com",
+        "name": "host.example.com"
+    },
+    "metricset": {
+        "module": "system",
+        "name": "process_summary",
+        "rtt": 115
+    },
+    "system": {
+        "process_summary": {
+            "idle": 0,
+            "running": 225,
+            "sleeping": 0,
+            "stopped": 0,
+            "total": 355,
+            "unknown": 130,
+            "zombie": 0
+        }
+    },
+    "type": "metricsets"
+}
diff --git a/metricbeat/module/system/process_summary/_meta/docs.asciidoc b/metricbeat/module/system/process_summary/_meta/docs.asciidoc
@@ -0,0 +1,4 @@
+=== System Process Summary MetricSet
+
+This is the `process_summary` metricset of the module system. It collects high
+level statistics about the running processes.
diff --git a/metricbeat/module/system/process_summary/_meta/fields.yml b/metricbeat/module/system/process_summary/_meta/fields.yml
@@ -0,0 +1,34 @@
+- name: process.summary
+  title: Process Summary
+  type: group
+  description: >
+    Summary metrics for the processes running on the host.
+  fields:
+    - name: total
+      type: long
+      description: >
+        Total number of processes on this host.
+    - name: running
+      type: long
+      description: >
+        Number of running processes on this host.
+    - name: idle
+      type: long
+      description: >
+        Number of idle processes on this host.
+    - name: sleeping
+      type: long
+      description: >
+        Number of sleeping processes on this host.
+    - name: stopped
+      type: long
+      description: >
+        Number of stopped processes on this host.
+    - name: zombie
+      type: long
+      description: >
+        Number of zombie processes on this host.
+    - name: unknown
+      type: long
+      description: >
+        Number of processes for which the state couldn't be retrieved or is unknown.
diff --git a/metricbeat/module/system/process_summary/doc.go b/metricbeat/module/system/process_summary/doc.go
@@ -0,0 +1,5 @@
+/*
+Package process_summary collects high level summary metrics about the running processes.
+It is implemented on darwin, freebsd, linux, and windows.
+*/
+package process_summary