implemented fetching rules from a remote server for conditional gathering

Author: Serhii Zakharov

README.md

@@ -1,7 +1,7 @@
 # Insights Operator
 
-This cluster operator gathers anonymized system configuration and reports it to Red Hat Insights. It is a part of the 
-standard OpenShift distribution. The data collected allows for debugging in the event of cluster failures or 
+This cluster operator gathers anonymized system configuration and reports it to Red Hat Insights. It is a part of the
+standard OpenShift distribution. The data collected allows for debugging in the event of cluster failures or
 unanticipated errors.
 
 # Table of Contents
@@ -12,26 +12,27 @@ unanticipated errors.
 - [Testing](#testing)
 - [Documentation](#documentation)
 - [Getting metrics from Prometheus](#getting-metrics-from-prometheus)
-  - [Generate the certificate and key](#generate-the-certificate-and-key)
-  - [Prometheus metrics provided by Insights Operator](#prometheus-metrics-provided-by-insights-operator)
-    - [Running IO locally](#running-io-locally)
-    - [Running IO on K8s](#running-io-on-k8s)
-  - [Getting the data directly from Prometheus](#getting-the-data-directly-from-prometheus)
-  - [Debugging Prometheus metrics without valid CA](#debugging-prometheus-metrics-without-valid-ca)
+    - [Generate the certificate and key](#generate-the-certificate-and-key)
+    - [Prometheus metrics provided by Insights Operator](#prometheus-metrics-provided-by-insights-operator)
+        - [Running IO locally](#running-io-locally)
+        - [Running IO on K8s](#running-io-on-k8s)
+    - [Getting the data directly from Prometheus](#getting-the-data-directly-from-prometheus)
+    - [Debugging Prometheus metrics without valid CA](#debugging-prometheus-metrics-without-valid-ca)
 - [Debugging](#debugging)
-  - [Using the profiler](#using-the-profiler)
-    - [Starting IO with the profiler](#starting-io-with-the-profiler)
-    - [Collect profiling data](#collect-profiling-data)
-    - [Analyzing profiling data](#analyzing-profiling-data)
+    - [Using the profiler](#using-the-profiler)
+        - [Starting IO with the profiler](#starting-io-with-the-profiler)
+        - [Collect profiling data](#collect-profiling-data)
+        - [Analyzing profiling data](#analyzing-profiling-data)
 - [Changelog](#changelog)
-  - [Updating the changelog](#updating-the-changelog)
+    - [Updating the changelog](#updating-the-changelog)
 - [Reported data](#reported-data)
-  - [Insights Operator Archive](#insights-operator-archive)
-    - [Sample IO archive](#sample-io-archive)
-    - [Generating a sample archive](#generating-a-sample-archive)
-    - [Formatting archive json files](#formatting-archive-json-files)
-    - [Obfuscating an archive](#obfuscating-an-archive)
-    - [Updating the sample archive](#updating-the-sample-archive)
+    - [Insights Operator Archive](#insights-operator-archive)
+        - [Sample IO archive](#sample-io-archive)
+        - [Generating a sample archive](#generating-a-sample-archive)
+        - [Formatting archive json files](#formatting-archive-json-files)
+        - [Obfuscating an archive](#obfuscating-an-archive)
+        - [Updating the sample archive](#updating-the-sample-archive)
+- [Conditional Gathering](#conditional-gathering)
 - [Contributing](#contributing)
 - [Support](#support)
 - [License](#license)
@@ -60,7 +61,7 @@ Unit tests can be started by the following command:
 make test
 ```
 
-It is also possible to specify CLI options for Go test. For example, if you need to disable test results caching, 
+It is also possible to specify CLI options for Go test. For example, if you need to disable test results caching,
 use the following command:
 
 ```shell script
@@ -72,8 +73,8 @@ VERBOSE=-count=1 make test
 # Documentation
 
 
-The document [docs/gathered-data](docs/gathered-data.md) contains the list of collected data and the API that is used 
-to collect it. This documentation is generated by the command bellow, by collecting the comment tags located above 
+The document [docs/gathered-data](docs/gathered-data.md) contains the list of collected data and the API that is used
+to collect it. This documentation is generated by the command bellow, by collecting the comment tags located above
 each Gather method.
 
 To start generating the document run:
@@ -86,12 +87,12 @@ make docs
 
 ## Generate the certificate and key
 
-Certificate and key are required to access Prometheus metrics (instead 404 Forbidden is returned). It is possible 
-to generate these two files from Kubernetes config file. Certificate is stored in `users/admin/client-cerfificate-data` 
-and key in `users/admin/client-key-data`. Please note that these values are encoded by using Base64 encoding, 
+Certificate and key are required to access Prometheus metrics (instead 404 Forbidden is returned). It is possible
+to generate these two files from Kubernetes config file. Certificate is stored in `users/admin/client-cerfificate-data`
+and key in `users/admin/client-key-data`. Please note that these values are encoded by using Base64 encoding,
 so it is needed to decode them, for example by `base64 -d`.
 
-There's a tool named `gen_cert_key.py` that can be used to automatically generate both files. It is stored in `tools` 
+There's a tool named `gen_cert_key.py` that can be used to automatically generate both files. It is stored in `tools`
 subdirectory.
 
 ```shell script
@@ -100,10 +101,10 @@ gen_cert_file.py kubeconfig.yaml
 
 ## Prometheus metrics provided by Insights Operator
 
-It is possible to read Prometheus metrics provided by Insights Operator. Example of metrics exposed by 
+It is possible to read Prometheus metrics provided by Insights Operator. Example of metrics exposed by
 Insights Operator can be found at [metrics.txt](docs/metrics.txt)
 
-Depending on how or where the IO is running you may have different ways to retrieve the metrics. 
+Depending on how or where the IO is running you may have different ways to retrieve the metrics.
 Here is a list of some options, so you can find the one that fits you:
 
 ### Running IO locally
@@ -185,7 +186,7 @@ go tool pprof http://localhost:6060/debug/pprof/profile?seconds=30
 go tool pprof http://localhost:6060/debug/pprof/heap
 ```
 
-These commands will create a compressed file that can be visualized using a variety of tools, one of them is 
+These commands will create a compressed file that can be visualized using a variety of tools, one of them is
 the `pprof` tool.
 
 ### Analyzing profiling data
@@ -213,7 +214,7 @@ It uses both the local git and GitHub`s API to update the file so:
 
 It can be used 2 ways:
 
-1. Providing no command line arguments the script will update the current `CHANGELOG.md` with the latest changes 
+1. Providing no command line arguments the script will update the current `CHANGELOG.md` with the latest changes
 2. according to the local git state.
 
 > 🚨 IMPORTANT: It will only work with changelogs created with this script
@@ -222,7 +223,7 @@ It can be used 2 ways:
 go run cmd/changelog/main.go
 ```
 
-2. Providing 2 command line arguments, `AFTER` and `UNTIL` dates the script will generate a new `CHANGELOG.md` within 
+2. Providing 2 command line arguments, `AFTER` and `UNTIL` dates the script will generate a new `CHANGELOG.md` within
 the provided time frame.
 
 ```shell script
@@ -235,17 +236,17 @@ go run cmd/changelog/main.go 2021-01-10 2021-01-20
 * ClusterOperator objects
 * All non-secret global config (hostnames and URLs anonymized)
 
-The list of all collected data with description, location in produced archive and link to Api and some examples is 
+The list of all collected data with description, location in produced archive and link to Api and some examples is
 at [docs/gathered-data.md](docs/gathered-data.md)
 
-The resulting data is packed in `.tar.gz` archive with folder structure indicated in the document. Example of such 
+The resulting data is packed in `.tar.gz` archive with folder structure indicated in the document. Example of such
 archive is at [docs/insights-archive-sample](docs/insights-archive-sample).
 
 ## Insights Operator Archive
 
 ### Sample IO archive
 
-There is a sample IO archive maintained in this repo to use as a quick reference. (can be found 
+There is a sample IO archive maintained in this repo to use as a quick reference. (can be found
 at [docs/insights-archive-sample](https://github.com/openshift/insights-operator/tree/master/docs/insights-archive-sample))
 
 To keep it up-to-date it is **required** to update this manually when developing a new data enhancement.
@@ -311,8 +312,18 @@ the `managedFields` field when it was removed from the IO archive to save space:
 ./scripts/update_sample_archive.sh <Path of directory with the NEW extracted IO archive> '"managedFields":'
 ```
 
-The path of the sample archive directory should be constant relative to
-the path of the script and therefore does not have to be specified explicitly.
+The path of the sample archive directory should be constant relative to the path of the script and therefore does not
+have to be specified explicitly.
+
+# Conditional Gathering
+
+Conditional Gatherer fetches its config from remote URL which is set in the config, the default one for local
+development is set to `http://localhost:8000/`. You can start a mock server following the next steps:
+
+- `git clone https://github.com/RedHatInsights/insights-operator-gathering-conditions.git`
+- `cd insights-operator-gathering-conditions/`
+- `./build.sh`
+- `python3 -m http.server --directory build/`
 
 # Contributing
 

config/local.yaml

@@ -5,6 +5,7 @@ leaderElection:
 interval: "5m"
 storagePath: /tmp/insights-operator
 endpoint: http://[::1]:8081
+conditionalGathererEndpoint: http://localhost:8000/
 impersonate: system:serviceaccount:openshift-insights:gather
 gather:
   - ALL

config/pod.yaml

@@ -5,6 +5,7 @@ leaderElection:
 interval: "2h"
 storagePath: /var/lib/insights-operator
 endpoint: https://cloud.redhat.com/api/ingress/v1/upload
+conditionalGathererEndpoint: http://localhost:8000/
 impersonate: system:serviceaccount:openshift-insights:gather
 pull_report:
   endpoint: https://cloud.redhat.com/api/insights-results-aggregator/v1/clusters/%s/report

pkg/config/config.go

@@ -11,11 +11,12 @@ import (
 
 // Serialized defines the standard config for this operator.
 type Serialized struct {
-	Report      bool   `json:"report"`
-	StoragePath string `json:"storagePath"`
-	Interval    string `json:"interval"`
-	Endpoint    string `json:"endpoint"`
-	PullReport  struct {
+	Report                      bool   `json:"report"`
+	StoragePath                 string `json:"storagePath"`
+	Interval                    string `json:"interval"`
+	Endpoint                    string `json:"endpoint"`
+	ConditionalGathererEndpoint string `json:"conditionalGathererEndpoint"`
+	PullReport                  struct {
 		Endpoint     string `json:"endpoint"`
 		Delay        string `json:"delay"`
 		Timeout      string `json:"timeout"`
@@ -33,15 +34,16 @@ type Serialized struct {
 
 // Controller defines the standard config for this operator.
 type Controller struct {
-	Report               bool
-	StoragePath          string
-	Interval             time.Duration
-	Endpoint             string
-	ReportEndpoint       string
-	ReportPullingDelay   time.Duration
-	ReportMinRetryTime   time.Duration
-	ReportPullingTimeout time.Duration
-	Impersonate          string
+	Report                      bool
+	StoragePath                 string
+	Interval                    time.Duration
+	Endpoint                    string
+	ConditionalGathererEndpoint string `json:"conditionalGathererEndpoint"`
+	ReportEndpoint              string
+	ReportPullingDelay          time.Duration
+	ReportMinRetryTime          time.Duration
+	ReportPullingTimeout        time.Duration
+	Impersonate                 string
 	// list of gathering functions to enable
 	// if there's a string "ALL", we enable everything
 	// otherwise, each string should consist of 2 parts:
@@ -84,6 +86,7 @@ type Converter func(s *Serialized, cfg *Controller) (*Controller, error)
 func (c *Controller) ToString() string {
 	return fmt.Sprintf("enabled=%t "+
 		"endpoint=%s "+
+		"conditional_gatherer_endpoint=%s "+
 		"interval=%s "+
 		"username=%t "+
 		"token=%t "+
@@ -93,6 +96,7 @@ func (c *Controller) ToString() string {
 		"pollingTimeout=%s",
 		c.Report,
 		c.Endpoint,
+		c.ConditionalGathererEndpoint,
 		c.Interval,
 		len(c.Username) > 0,
 		len(c.Token) > 0,
@@ -106,6 +110,7 @@ func (c *Controller) MergeWith(cfg *Controller) {
 	c.mergeCredentials(cfg)
 	c.mergeInterval(cfg)
 	c.mergeEndpoint(cfg)
+	c.mergeConditionalGathererEndpoint(cfg)
 	c.mergeReport(cfg)
 	c.mergeOCM(cfg)
 	c.mergeHTTP(cfg)
@@ -122,6 +127,12 @@ func (c *Controller) mergeEndpoint(cfg *Controller) {
 	}
 }
 
+func (c *Controller) mergeConditionalGathererEndpoint(cfg *Controller) {
+	if len(cfg.ConditionalGathererEndpoint) > 0 {
+		c.ConditionalGathererEndpoint = cfg.ConditionalGathererEndpoint
+	}
+}
+
 func (c *Controller) mergeReport(cfg *Controller) {
 	if len(cfg.ReportEndpoint) > 0 {
 		c.ReportEndpoint = cfg.ReportEndpoint
@@ -168,6 +179,7 @@ func ToController(s *Serialized, cfg *Controller) (*Controller, error) { // noli
 	cfg.Report = s.Report
 	cfg.StoragePath = s.StoragePath
 	cfg.Endpoint = s.Endpoint
+	cfg.ConditionalGathererEndpoint = s.ConditionalGathererEndpoint
 	cfg.Impersonate = s.Impersonate
 	cfg.Gather = s.Gather
 	cfg.EnableGlobalObfuscation = s.EnableGlobalObfuscation
@@ -254,6 +266,7 @@ func ToDisconnectedController(s *Serialized, cfg *Controller) (*Controller, erro
 	cfg.Impersonate = s.Impersonate
 	cfg.Gather = s.Gather
 	cfg.EnableGlobalObfuscation = s.EnableGlobalObfuscation
+	cfg.ConditionalGathererEndpoint = s.ConditionalGathererEndpoint
 
 	if len(s.Interval) > 0 {
 		d, err := time.ParseDuration(s.Interval)

pkg/config/configobserver/config.go

@@ -26,6 +26,7 @@ func LoadConfigFromSecret(secret *v1.Secret) (config.Controller, error) {
 
 	cfg.loadCredentials(secret.Data)
 	cfg.loadEndpoint(secret.Data)
+	cfg.loadConditionalGathererEndpoint(secret.Data)
 	cfg.loadHTTP(secret.Data)
 	cfg.loadReport(secret.Data)
 	cfg.loadOCM(secret.Data)
@@ -64,6 +65,12 @@ func (c *Config) loadEndpoint(data map[string][]byte) {
 	}
 }
 
+func (c *Config) loadConditionalGathererEndpoint(data map[string][]byte) {
+	if endpoint, ok := data["conditionalGathererEndpoint"]; ok {
+		c.ConditionalGathererEndpoint = string(endpoint)
+	}
+}
+
 func (c *Config) loadHTTP(data map[string][]byte) {
 	if httpProxy, ok := data["httpProxy"]; ok {
 		c.HTTPConfig.HTTPProxy = string(httpProxy)

pkg/gather/gather.go

@@ -61,7 +61,7 @@ func CreateAllGatherers(
 		anonymizer, controller.Interval,
 	)
 	workloadsGatherer := workloads.New(gatherProtoKubeConfig)
-	conditionalGatherer := conditional.New(gatherProtoKubeConfig, metricsGatherKubeConfig, gatherKubeConfig)
+	conditionalGatherer := conditional.New(gatherProtoKubeConfig, metricsGatherKubeConfig, gatherKubeConfig, controller)
 
 	return []gatherers.Interface{clusterConfigGatherer, workloadsGatherer, conditionalGatherer}
 }
@@ -100,7 +100,7 @@ func CollectAndRecordGatherer(
 				gathererName, result.FunctionName, err,
 			)
 
-			errs = append(errs, fmt.Errorf(errStr))
+			errs = append(errs, fmt.Errorf("%v", errStr))
 		}
 		recordedRecs := 0
 		for _, r := range result.Records {

pkg/gatherers/common/constants.go

@@ -1,8 +1,11 @@
 package common
 
+import "time"
+
 const (
 	// ImageConfigQPS is the maximum qps for image client
 	ImageConfigQPS = 10
 	// ImageConfigBurst is the maximum burst for image client
-	ImageConfigBurst = 10
+	ImageConfigBurst                      = 10
+	ConditionalGathererHTTPRequestTimeout = time.Minute
 )