simplify chrony and add some tests (#712)

* simplify chrony and add some tests

* update charts

* update readme

* fix ref_measurement_time on chrony restart

* update go.d.conf

* update plugin readme

* fix tests

* fix reviewdog warnings

* fix readme

README.md

@@ -34,6 +34,7 @@ Go.d.plugin is shipped with [`Netdata`](https://github.com/netdata/netdata).
 | [activemq](https://github.com/netdata/go.d.plugin/tree/master/modules/activemq)                     | `ActiveMQ`                      |
 | [apache](https://github.com/netdata/go.d.plugin/tree/master/modules/apache)                         | `Apache`                        |
 | [bind](https://github.com/netdata/go.d.plugin/tree/master/modules/bind)                             | `ISC Bind`                      |
+| [chrony](https://github.com/netdata/go.d.plugin/tree/master/modules/chrony)                         | `Chrony`                        |
 | [cockroachdb](https://github.com/netdata/go.d.plugin/tree/master/modules/cockroachdb)               | `CockroachDB`                   |
 | [consul](https://github.com/netdata/go.d.plugin/tree/master/modules/consul)                         | `Consul`                        |
 | [coredns](https://github.com/netdata/go.d.plugin/tree/master/modules/coredns)                       | `CoreDNS`                       |

config/go.d.conf

@@ -18,7 +18,7 @@ modules:
 #  activemq: yes
 #  apache: yes
 #  bind: yes
-#  chrony: no
+#  chrony: yes
 #  cockroachdb: yes
 #  consul: yes
 #  coredns: yes

config/go.d/chrony.conf

@@ -61,11 +61,6 @@
 #    Syntax:
 #      address: 127.0.0.1:53
 #
-#  - protocol
-#    DNS query transport protocol. Valid options: udp, tcp, tcp-tls.
-#    Syntax:
-#      protocol: udp
-#
 #  - timeout
 #    DNS query timeout (dial, write and read) in seconds.
 #    Syntax:
@@ -90,10 +85,8 @@
 
 jobs:
   - name: local
-    protocol: udp
     address: '127.0.0.1:323'
     timeout: 1
 
 #  - name: remote
-#    protocol: udp
 #    address: '203.0.113.0:323'

modules/chrony/README.md

@@ -1,19 +1,77 @@
-# chrony monitoring with Netdata
-
-[`chrony`](https://chrony.tuxfamily.org/)  is a versatile implementation of the Network Time Protocol (NTP).
-
-The modules will monitor local host `chrony` server.
-
-This module use golang to collect chrony and produces:
-* stratum
-* frequency
-* last offset
-* RMS offset
-* residual freq
-* root delay
-* root dispersion
-* skew
-* leap status
-* update interval
-* current correction
-* current source server address
+<!--
+title: "Chrony monitoring with Netdata"
+custom_edit_url: https://github.com/netdata/go.d.plugin/edit/master/modules/chrony/README.md
+sidebar_label: "Chrony"
+-->
+
+# Chrony monitoring with Netdata
+
+[chrony](https://chrony.tuxfamily.org/) is a versatile implementation of the Network Time Protocol (NTP).
+
+This module monitors the system's clock performance and peers activity status using Chrony communication protocol v6.
+
+## Charts
+
+It produces the following charts:
+
+- Distance to the reference clock
+- Current correction
+- Network path delay to stratum-1
+- Dispersion accumulated back to stratum-1
+- Offset on the last clock update
+- Long-term average of the offset value
+- Frequency
+- Residual frequency
+- Skew
+- Interval between the last two clock updates
+- Time since the last measurement
+- Leap status
+- Peers activity
+
+## Configuration
+
+Edit the `go.d/chrony.conf` configuration file using `edit-config` from the
+Netdata [config directory](https://learn.netdata.cloud/docs/configure/nodes), which is typically at `/etc/netdata`.
+
+```bash
+cd /etc/netdata   # Replace this path with your Netdata config directory, if different
+sudo ./edit-config go.d/chrony.conf
+```
+
+Configuration example:
+
+```yaml
+jobs:
+  - name: local
+    address: '127.0.0.1:323'
+    timeout: 1
+
+  - name: remote
+    address: '203.0.113.0:323'
+    timeout: 3
+```
+
+For all available options please see
+module [configuration file](https://github.com/netdata/go.d.plugin/blob/master/config/go.d/chrony.conf).
+
+---
+
+## Troubleshooting
+
+To troubleshoot issues with the `chrony` collector, run the `go.d.plugin` with the debug option enabled. The
+output should give you clues as to why the collector isn't working.
+
+First, navigate to your plugins directory, usually at `/usr/libexec/netdata/plugins.d/`. If that's not the case on your
+system, open `netdata.conf` and look for the setting `plugins directory`. Once you're in the plugin's directory, switch
+to the `netdata` user.
+
+```bash
+cd /usr/libexec/netdata/plugins.d/
+sudo -u netdata -s
+```
+
+You can now run the `go.d.plugin` to debug the collector:
+
+```bash
+./go.d.plugin -d -m chrony
+```

modules/chrony/charts.go

@@ -4,146 +4,148 @@ package chrony
 
 import (
 	"github.com/netdata/go.d.plugin/agent/module"
-	"net"
+	"github.com/netdata/go.d.plugin/modules/chrony/client"
 )
 
+const scaleFactor = client.ScaleFactor
+
 var charts = module.Charts{
-	{
-		ID:    "running",
-		Title: "chrony is functional and can be monitored",
-		Units: "hop",
-		Type:  module.Area,
-		Ctx:   "chrony.running",
-		Dims: module.Dims{
-			{ID: "running", Name: "running", Algo: module.Absolute, Div: 1, Mul: 1},
-		},
-	},
 	{
 		ID:    "stratum",
-		Title: "distance from reference clock",
+		Title: "Distance to the reference clock",
 		Units: "level",
-		Type:  module.Area,
+		Fam:   "stratum",
 		Ctx:   "chrony.stratum",
 		Dims: module.Dims{
-			{ID: "stratum", Name: "stratum", Algo: module.Absolute, Div: 1, Mul: 1},
+			{ID: "stratum", Name: "stratum"},
 		},
 	},
 	{
-		ID: "leap_status",
-		//  LEAP_Normal = 0,
-		//  LEAP_InsertSecond = 1,
-		//  LEAP_DeleteSecond = 2,
-		//  LEAP_Unsynchronised = 3
-		Title: "Leap status can be Normal, Insert second, Delete second or Not synchronised.",
-		Units: "hop",
-		Ctx:   "chrony.leap_status",
+		ID:    "current_correction",
+		Title: "Current correction",
+		Units: "seconds",
+		Fam:   "correction",
+		Ctx:   "chrony.current_correction",
 		Dims: module.Dims{
-			{ID: "leap_status", Name: "leap_status", Algo: module.Absolute, Div: 1, Mul: 1},
+			{ID: "current_correction", Div: scaleFactor},
 		},
 	},
 	{
 		ID:    "root_delay",
-		Title: "the total of the network path delays to the stratum-1 computer",
+		Title: "Network path delay to stratum-1",
 		Units: "seconds",
-		Type:  module.Area,
+		Fam:   "root",
 		Ctx:   "chrony.root_delay",
 		Dims: module.Dims{
-			{ID: "root_delay", Name: "root_delay", Algo: module.Absolute, Div: scaleFactor, Mul: 1},
+			{ID: "root_delay", Div: scaleFactor},
 		},
 	},
 	{
 		ID:    "root_dispersion",
-		Title: "total dispersion accumulated through all the computers back to the stratum-1 computer",
+		Title: "Dispersion accumulated back to stratum-1",
 		Units: "seconds",
-		Type:  module.Area,
+		Fam:   "root",
 		Ctx:   "chrony.root_dispersion",
 		Dims: module.Dims{
-			{ID: "root_dispersion", Name: "root_dispersion", Algo: module.Absolute, Div: scaleFactor, Mul: 1},
+			{ID: "root_dispersion", Div: scaleFactor},
 		},
 	},
 	{
-		ID:    "skew",
-		Title: "estimated error bound on the frequency",
-		Units: "ppm",
-		Type:  module.Area,
-		Ctx:   "chrony.skew",
+		ID:    "last_offset",
+		Title: "Offset on the last clock update",
+		Units: "seconds",
+		Fam:   "offset",
+		Ctx:   "chrony.last_offset",
+		Dims: module.Dims{
+			{ID: "last_offset", Name: "offset", Div: scaleFactor},
+		},
+	},
+	{
+		ID:    "rms_offset",
+		Title: "Long-term average of the offset value",
+		Units: "seconds",
+		Fam:   "offset",
+		Ctx:   "chrony.rms_offset",
 		Dims: module.Dims{
-			{ID: "skew", Name: "skew", Algo: module.Absolute, Div: scaleFactor, Mul: 1},
+			{ID: "rms_offset", Name: "offset", Div: scaleFactor},
 		},
 	},
 	{
 		ID:    "frequency",
-		Title: "the rate by which the system’s clock would be would be wrong",
+		Title: "Frequency",
 		Units: "ppm",
-		Type:  module.Area,
+		Fam:   "frequency",
 		Ctx:   "chrony.frequency",
 		Dims: module.Dims{
-			{ID: "frequency", Name: "frequency", Algo: module.Absolute, Div: scaleFactor, Mul: 1},
+			{ID: "frequency", Div: scaleFactor},
 		},
 	},
 	{
-		ID:    "offset",
-		Title: "the offset between clock update",
-		Units: "seconds",
-		Type:  module.Area,
-		Ctx:   "chrony.offset",
+		ID:    "residual_frequency",
+		Title: "Residual frequency",
+		Units: "ppm",
+		Fam:   "frequency",
+		Ctx:   "chrony.residual_frequency",
 		Dims: module.Dims{
-			{ID: "last_offset", Name: "last", Algo: module.Absolute, Div: scaleFactor, Mul: 1},
-			{ID: "rms_offset", Name: "rms", Algo: module.Absolute, Div: scaleFactor, Mul: 1},
+			{ID: "residual_frequency", Div: scaleFactor},
 		},
 	},
 	{
-		ID:    "update_interval",
-		Title: "last clock update interval",
-		Units: "seconds",
-		Type:  module.Area,
-		Ctx:   "chrony.update_interval",
+		ID:    "skew",
+		Title: "Skew",
+		Units: "ppm",
+		Fam:   "frequency",
+		Ctx:   "chrony.skew",
 		Dims: module.Dims{
-			{ID: "update_interval", Name: "update_interval", Algo: module.Absolute, Div: scaleFactor, Mul: 1},
+			{ID: "skew", Div: scaleFactor},
 		},
 	},
 	{
-		ID:    "current_correction",
-		Title: "last clock update interval",
+		ID:    "update_interval",
+		Title: "Interval between the last two clock updates",
 		Units: "seconds",
-		Type:  module.Area,
-		Ctx:   "chrony.current_correction",
+		Fam:   "updates",
+		Ctx:   "chrony.update_interval",
 		Dims: module.Dims{
-			{ID: "current_correction", Name: "current_correction", Algo: module.Absolute, Div: scaleFactor, Mul: 1},
+			{ID: "update_interval", Div: scaleFactor},
 		},
 	},
 	{
-		ID:    "ref_timestamp",
-		Title: "last clock update interval",
+		ID:    "ref_measurement_time",
+		Title: "Time since the last measurement",
 		Units: "seconds",
-		Type:  module.Line,
-		Ctx:   "chrony.ref_timestamp",
+		Fam:   "updates",
+		Ctx:   "chrony.ref_measurement_time",
 		Dims: module.Dims{
-			{ID: "ref_timestamp", Name: "ref_timestamp", Algo: module.Absolute, Div: 1, Mul: 1},
+			{ID: "ref_measurement_time"},
 		},
 	},
 	{
-		ID:    "activity",
-		Title: "activity status",
-		Units: "count",
-		Ctx:   "chrony.activity",
-		Type:  module.Area,
+		ID:    "leap_status",
+		Title: "Leap status",
+		Units: "status",
+		Fam:   "leap status",
+		Ctx:   "chrony.leap_status",
 		Dims: module.Dims{
-			{ID: "online_sources", Name: "online_sources", Algo: module.Absolute, Div: 1, Mul: 1},
-			{ID: "offline_sources", Name: "offline_sources", Algo: module.Absolute, Div: 1, Mul: 1},
-			{ID: "burst_online_sources", Name: "burst_online_sources", Algo: module.Absolute, Div: 1, Mul: 1},
-			{ID: "burst_offline_sources", Name: "burst_offline_sources", Algo: module.Absolute, Div: 1, Mul: 1},
-			{ID: "unresolved_sources", Name: "unresolved_sources", Algo: module.Absolute, Div: 1, Mul: 1},
+			{ID: "leap_status_normal", Name: "normal"},
+			{ID: "leap_status_insert_second", Name: "insert_second"},
+			{ID: "leap_status_delete_second", Name: "delete_second"},
+			{ID: "leap_status_unsynchronised", Name: "unsynchronised"},
 		},
 	},
 	{
-		ID:    "source",
-		Title: "Activity Source Server",
-		Units: "hop",
-		Ctx:   "chrony.source",
-		Type:  module.Area,
+		ID:    "activity",
+		Title: "Peers activity",
+		Units: "sources",
+		Fam:   "activity",
+		Ctx:   "chrony.activity",
+		Type:  module.Stacked,
 		Dims: module.Dims{
-			{ID: net.IPv4zero.String(), Name: net.IPv4zero.String(), Algo: module.Absolute, Div: 1, Mul: 1},
+			{ID: "online_sources", Name: "online"},
+			{ID: "offline_sources", Name: "offline"},
+			{ID: "burst_online_sources", Name: "burst_online"},
+			{ID: "burst_offline_sources", Name: "burst_offline"},
+			{ID: "unresolved_sources", Name: "unresolved"},
 		},
 	},
 }