Merge pull request #26 from sysdiglabs/master

Master fetch

.circleci/config.yml

@@ -1,25 +1,20 @@
 ---
 version: 2.1
-
 orbs:
-  prometheus: prometheus/prometheus@0.11.0
-
+  prometheus: prometheus/prometheus@0.16.0
 executors:
   # This must match .promu.yml.
   golang:
     docker:
-      - image: circleci/golang:1.16
-
+      - image: cimg/go:1.18
 jobs:
   test:
     executor: golang
-
     steps:
       - prometheus/setup_environment
       - run: make
       - prometheus/store_artifact:
           file: elasticsearch_exporter
-
 workflows:
   version: 2
   elasticsearch_exporter:

.github/dependabot.yml

@@ -11,4 +11,8 @@ updates:
   schedule:
     interval: "daily"
   registries:
-  - docker-registry-quay-io
+  - docker-registry-quay-io
+- package-ecosystem: "gomod"
+  directory: "/"
+  schedule:
+    interval: "monthly"

.github/workflows/golangci-lint.yml

@@ -0,0 +1,30 @@
+name: golangci-lint
+on:
+  push:
+    paths:
+      - "go.sum"
+      - "go.mod"
+      - "**.go"
+      - "scripts/errcheck_excludes.txt"
+      - ".github/workflows/golangci-lint.yml"
+      - ".golangci.yml"
+  pull_request:
+
+jobs:
+  golangci:
+    name: lint
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+      - name: install Go
+        uses: actions/setup-go@v2
+        with:
+          go-version: 1.18.x
+      - name: Install snmp_exporter/generator dependencies
+        run: sudo apt-get update && sudo apt-get -y install libsnmp-dev
+        if: github.repository == 'prometheus/snmp_exporter'
+      - name: Lint
+        uses: golangci/golangci-lint-action@v3.2.0
+        with:
+          version: v1.45.2

.golangci.yml

@@ -1,4 +1,8 @@
 ---
+linters:
+  enable:
+    - revive
+
 issues:
   exclude-rules:
     - path: _test.go

.promu.yml

@@ -1,6 +1,6 @@
 go:
     # This must match .circle/config.yml.
-    version: 1.16
+    version: 1.18
 repository:
     path: github.com/prometheus-community/elasticsearch_exporter
 build:

.yamllint

@@ -0,0 +1,28 @@
+---
+extends: default
+
+rules:
+  braces:
+    max-spaces-inside: 1
+    level: error
+  brackets:
+    max-spaces-inside: 1
+    level: error
+  commas: disable
+  comments: disable
+  comments-indentation: disable
+  document-start: disable
+  indentation:
+    spaces: consistent
+    indent-sequences: consistent
+  key-duplicates:
+    ignore: |
+      config/testdata/section_key_dup.bad.yml
+  line-length: disable
+  truthy:
+    ignore: |
+      .github/workflows/codeql-analysis.yml
+      .github/workflows/funcbench.yml
+      .github/workflows/fuzzing.yml
+      .github/workflows/prombench.yml
+      .github/workflows/golangci-lint.yml

CODE_OF_CONDUCT.md

@@ -1,3 +1,3 @@
-## Prometheus Community Code of Conduct
+# Prometheus Community Code of Conduct
 
-Prometheus follows the [CNCF Code of Conduct](https://github.com/cncf/foundation/blob/master/code-of-conduct.md).
+Prometheus follows the [CNCF Code of Conduct](https://github.com/cncf/foundation/blob/main/code-of-conduct.md).

MAINTAINERS.md

@@ -0,0 +1,2 @@
+* Ben Kochie <superq@gmail.com> @SuperQ
+* Joe Adams <github@joeadams.io> @sysadmind

Makefile.common

@@ -36,29 +36,6 @@ GO_VERSION        ?= $(shell $(GO) version)
 GO_VERSION_NUMBER ?= $(word 3, $(GO_VERSION))
 PRE_GO_111        ?= $(shell echo $(GO_VERSION_NUMBER) | grep -E 'go1\.(10|[0-9])\.')
 
-GOVENDOR :=
-GO111MODULE :=
-ifeq (, $(PRE_GO_111))
-	ifneq (,$(wildcard go.mod))
-		# Enforce Go modules support just in case the directory is inside GOPATH (and for Travis CI).
-		GO111MODULE := on
-
-		ifneq (,$(wildcard vendor))
-			# Always use the local vendor/ directory to satisfy the dependencies.
-			GOOPTS := $(GOOPTS) -mod=vendor
-		endif
-	endif
-else
-	ifneq (,$(wildcard go.mod))
-		ifneq (,$(wildcard vendor))
-$(warning This repository requires Go >= 1.11 because of Go modules)
-$(warning Some recipes may not work as expected as the current Go runtime is '$(GO_VERSION_NUMBER)')
-		endif
-	else
-		# This repository isn't using Go modules (yet).
-		GOVENDOR := $(FIRST_GOPATH)/bin/govendor
-	endif
-endif
 PROMU        := $(FIRST_GOPATH)/bin/promu
 pkgs          = ./...
 
@@ -78,12 +55,12 @@ ifneq ($(shell which gotestsum),)
 endif
 endif
 
-PROMU_VERSION ?= 0.12.0
+PROMU_VERSION ?= 0.13.0
 PROMU_URL     := https://github.com/prometheus/promu/releases/download/v$(PROMU_VERSION)/promu-$(PROMU_VERSION).$(GO_BUILD_PLATFORM).tar.gz
 
 GOLANGCI_LINT :=
 GOLANGCI_LINT_OPTS ?=
-GOLANGCI_LINT_VERSION ?= v1.42.0
+GOLANGCI_LINT_VERSION ?= v1.45.2
 # golangci-lint only supports linux, darwin and windows platforms on i386/amd64.
 # windows isn't included here because of the path separator being different.
 ifeq ($(GOHOSTOS),$(filter $(GOHOSTOS),linux darwin))
@@ -150,58 +127,47 @@ common-check_license:
 .PHONY: common-deps
 common-deps:
 	@echo ">> getting dependencies"
-ifdef GO111MODULE
-	GO111MODULE=$(GO111MODULE) $(GO) mod download
-else
-	$(GO) get $(GOOPTS) -t ./...
-endif
+	$(GO) mod download
 
 .PHONY: update-go-deps
 update-go-deps:
 	@echo ">> updating Go dependencies"
 	@for m in $$($(GO) list -mod=readonly -m -f '{{ if and (not .Indirect) (not .Main)}}{{.Path}}{{end}}' all); do \
 		$(GO) get -d $$m; \
 	done
-	GO111MODULE=$(GO111MODULE) $(GO) mod tidy
-ifneq (,$(wildcard vendor))
-	GO111MODULE=$(GO111MODULE) $(GO) mod vendor
-endif
+	$(GO) mod tidy
 
 .PHONY: common-test-short
 common-test-short: $(GOTEST_DIR)
 	@echo ">> running short tests"
-	GO111MODULE=$(GO111MODULE) $(GOTEST) -short $(GOOPTS) $(pkgs)
+	$(GOTEST) -short $(GOOPTS) $(pkgs)
 
 .PHONY: common-test
 common-test: $(GOTEST_DIR)
 	@echo ">> running all tests"
-	GO111MODULE=$(GO111MODULE) $(GOTEST) $(test-flags) $(GOOPTS) $(pkgs)
+	$(GOTEST) $(test-flags) $(GOOPTS) $(pkgs)
 
 $(GOTEST_DIR):
 	@mkdir -p $@
 
 .PHONY: common-format
 common-format:
 	@echo ">> formatting code"
-	GO111MODULE=$(GO111MODULE) $(GO) fmt $(pkgs)
+	$(GO) fmt $(pkgs)
 
 .PHONY: common-vet
 common-vet:
 	@echo ">> vetting code"
-	GO111MODULE=$(GO111MODULE) $(GO) vet $(GOOPTS) $(pkgs)
+	$(GO) vet $(GOOPTS) $(pkgs)
 
 .PHONY: common-lint
 common-lint: $(GOLANGCI_LINT)
 ifdef GOLANGCI_LINT
 	@echo ">> running golangci-lint"
-ifdef GO111MODULE
 # 'go list' needs to be executed before staticcheck to prepopulate the modules cache.
 # Otherwise staticcheck might fail randomly for some reason not yet explained.
-	GO111MODULE=$(GO111MODULE) $(GO) list -e -compiled -test=true -export=false -deps=true -find=false -tags= -- ./... > /dev/null
-	GO111MODULE=$(GO111MODULE) $(GOLANGCI_LINT) run $(GOLANGCI_LINT_OPTS) $(pkgs)
-else
-	$(GOLANGCI_LINT) run $(pkgs)
-endif
+	$(GO) list -e -compiled -test=true -export=false -deps=true -find=false -tags= -- ./... > /dev/null
+	$(GOLANGCI_LINT) run $(GOLANGCI_LINT_OPTS) $(pkgs)
 endif
 
 .PHONY: common-yamllint
@@ -218,28 +184,15 @@ endif
 common-staticcheck: lint
 
 .PHONY: common-unused
-common-unused: $(GOVENDOR)
-ifdef GOVENDOR
-	@echo ">> running check for unused packages"
-	@$(GOVENDOR) list +unused | grep . && exit 1 || echo 'No unused packages'
-else
-ifdef GO111MODULE
+common-unused:
 	@echo ">> running check for unused/missing packages in go.mod"
-	GO111MODULE=$(GO111MODULE) $(GO) mod tidy
-ifeq (,$(wildcard vendor))
+	$(GO) mod tidy
 	@git diff --exit-code -- go.sum go.mod
-else
-	@echo ">> running check for unused packages in vendor/"
-	GO111MODULE=$(GO111MODULE) $(GO) mod vendor
-	@git diff --exit-code -- go.sum go.mod vendor/
-endif
-endif
-endif
 
 .PHONY: common-build
 common-build: promu
 	@echo ">> building binaries"
-	GO111MODULE=$(GO111MODULE) $(PROMU) build --prefix $(PREFIX) $(PROMU_BINARIES)
+	$(PROMU) build --prefix $(PREFIX) $(PROMU_BINARIES)
 
 .PHONY: common-tarball
 common-tarball: promu
@@ -295,12 +248,6 @@ $(GOLANGCI_LINT):
 		| sh -s -- -b $(FIRST_GOPATH)/bin $(GOLANGCI_LINT_VERSION)
 endif
 
-ifdef GOVENDOR
-.PHONY: $(GOVENDOR)
-$(GOVENDOR):
-	GOOS= GOARCH= $(GO) get -u github.com/kardianos/govendor
-endif
-
 .PHONY: precheck
 precheck::
 

README.md

@@ -2,7 +2,7 @@
 [![CircleCI](https://circleci.com/gh/prometheus-community/elasticsearch_exporter.svg?style=svg)](https://circleci.com/gh/prometheus-community/elasticsearch_exporter)
 [![Go Report Card](https://goreportcard.com/badge/github.com/prometheus-community/elasticsearch_exporter)](https://goreportcard.com/report/github.com/prometheus-community/elasticsearch_exporter)
 
-Prometheus exporter for various metrics about ElasticSearch, written in Go.
+Prometheus exporter for various metrics about Elasticsearch, written in Go.
 
 ### Installation
 
@@ -30,11 +30,16 @@ elasticsearch_exporter:
 
 #### Kubernetes
 
-You can find a helm chart in the stable charts repository at https://github.com/kubernetes/charts/tree/master/stable/elasticsearch-exporter.
+You can find a helm chart in the prometheus-community charts repository at https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-elasticsearch-exporter
+
+```bash
+helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
+helm install [RELEASE_NAME] prometheus-community/prometheus-elasticsearch-exporter
+```
 
 ### Configuration
 
-**NOTE:** The exporter fetches information from an ElasticSearch cluster on every scrape, therefore having a too short scrape interval can impose load on ES master nodes, particularly if you run with `--es.all` and `--es.indices`. We suggest you measure how long fetching `/_nodes/stats` and `/_all/_stats` takes for your ES cluster to determine whether your scraping interval is too short. As a last resort, you can scrape this exporter using a dedicated job with its own scraping interval.
+**NOTE:** The exporter fetches information from an Elasticsearch cluster on every scrape, therefore having a too short scrape interval can impose load on ES master nodes, particularly if you run with `--es.all` and `--es.indices`. We suggest you measure how long fetching `/_nodes/stats` and `/_all/_stats` takes for your ES cluster to determine whether your scraping interval is too short. As a last resort, you can scrape this exporter using a dedicated job with its own scraping interval.
 
 Below is the command line options summary:
 ```bash
@@ -49,22 +54,24 @@ elasticsearch_exporter --help
 | es.indices              | 1.0.2                 | If true, query stats for all indices in the cluster. | false |
 | es.indices_settings     | 1.0.4rc1              | If true, query settings stats for all indices in the cluster. | false |
 | es.indices_mappings     | 1.2.0                 | If true, query stats for mappings of all indices of the cluster. | false |
+| es.aliases              | 1.0.4rc1              | If true, include informational aliases metrics. | true |
 | es.shards               | 1.0.3rc1              | If true, query stats for all indices in the cluster, including shard-level stats (implies `es.indices=true`). | false |
 | es.snapshots            | 1.0.4rc1              | If true, query stats for the cluster snapshots. | false |
+| es.slm                  |                       | If true, query stats for SLM. | false |
 | es.timeout              | 1.0.2                 | Timeout for trying to get stats from Elasticsearch. (ex: 20s) | 5s |
 | es.ca                   | 1.0.2                 | Path to PEM file that contains trusted Certificate Authorities for the Elasticsearch connection. | |
 | es.client-private-key   | 1.0.2                 | Path to PEM file that contains the private key for client auth when connecting to Elasticsearch. | |
 | es.client-cert          | 1.0.2                 | Path to PEM file that contains the corresponding cert for the private key to connect to Elasticsearch. | |
 | es.clusterinfo.interval | 1.1.0rc1              |  Cluster info update interval for the cluster label | 5m |
 | es.ssl-skip-verify      | 1.0.4rc1              | Skip SSL verification when connecting to Elasticsearch. | false |
-| es.apiKey               | unreleased            | API Key to use for authenticating against Elasticsearch. |  |
 | web.listen-address      | 1.0.2                 | Address to listen on for web interface and telemetry. | :9114 |
 | web.telemetry-path      | 1.0.2                 | Path under which to expose metrics. | /metrics |
 | version                 | 1.0.2                 | Show version info on stdout and exit. | |
 
 Commandline parameters start with a single `-` for versions less than `1.1.0rc1`.
-For versions greater than `1.1.0rc1`, commandline parameters are specified with `--`. Also, all commandline parameters can be provided as environment variables. The environment variable name is derived from the parameter name
-by replacing `.` and `-` with `_` and upper-casing the parameter name.
+For versions greater than `1.1.0rc1`, commandline parameters are specified with `--`.
+
+The API key used to connect can be set with the `ES_API_KEY` environment variable.
 
 #### Elasticsearch 7.x security privileges
 
@@ -81,6 +88,7 @@ es.indices | `indices` `monitor` (per index or `*`) | All actions that are requi
 es.indices_settings | `indices` `monitor` (per index or `*`) |
 es.shards | not sure if `indices` or `cluster` `monitor` or both |
 es.snapshots | `cluster:admin/snapshot/status` and `cluster:admin/repository/get` | [ES Forum Post](https://discuss.elastic.co/t/permissions-for-backup-user-with-x-pack/88057)
+es.slm | `read_slm`
 
 Further Information
 - [Build in Users](https://www.elastic.co/guide/en/elastic-stack-overview/7.3/built-in-users.html)
@@ -139,8 +147,8 @@ Further Information
 | elasticsearch_indices_indexing_index_total                            | counter   | 1           | Total index calls
 | elasticsearch_indices_mappings_stats_fields                           | gauge     | 1           | Count of fields currently mapped by index
 | elasticsearch_indices_mappings_stats_json_parse_failures_total        | counter   | 0           | Number of errors while parsing JSON
-| elasticsearch_indices_mappings_stats_scrapes_total                    | counter   | 0           | Current total ElasticSearch Indices Mappings scrapes
-| elasticsearch_indices_mappings_stats_up                               | gauge     | 0           | Was the last scrape of the ElasticSearch Indices Mappings endpoint successful
+| elasticsearch_indices_mappings_stats_scrapes_total                    | counter   | 0           | Current total Elasticsearch Indices Mappings scrapes
+| elasticsearch_indices_mappings_stats_up                               | gauge     | 0           | Was the last scrape of the Elasticsearch Indices Mappings endpoint successful
 | elasticsearch_indices_merges_docs_total                               | counter   | 1           | Cumulative docs merged
 | elasticsearch_indices_merges_total                                    | counter   | 1           | Total merges
 | elasticsearch_indices_merges_total_size_bytes_total                   | counter   | 1           | Total merge size in bytes
@@ -188,7 +196,7 @@ Further Information
 | elasticsearch_os_load5                                                | gauge     | 1           | Midterm load average
 | elasticsearch_os_load15                                               | gauge     | 1           | Longterm load average
 | elasticsearch_process_cpu_percent                                     | gauge     | 1           | Percent CPU used by process
-| elasticsearch_process_cpu_time_seconds_sum                            | counter   | 3           | Process CPU time in seconds
+| elasticsearch_process_cpu_seconds_total                               | counter   | 1           | Process CPU time in seconds
 | elasticsearch_process_mem_resident_size_bytes                         | gauge     | 1           | Resident memory in use by process in bytes
 | elasticsearch_process_mem_share_size_bytes                            | gauge     | 1           | Shared memory in use by process in bytes
 | elasticsearch_process_mem_virtual_size_bytes                          | gauge     | 1           | Total virtual memory used in bytes
@@ -216,12 +224,29 @@ Further Information
 | elasticsearch_clusterinfo_last_retrieval_success_ts                   | gauge     | 1           | Timestamp of the last successful cluster info retrieval
 | elasticsearch_clusterinfo_up                                          | gauge     | 1           | Up metric for the cluster info collector
 | elasticsearch_clusterinfo_version_info                                | gauge     | 6           | Constant metric with ES version information as labels
+| elasticsearch_slm_stats_up                                            | gauge     | 0           | Up metric for SLM collector
+| elasticsearch_slm_stats_total_scrapes                                 | counter   | 0           | Number of scrapes for SLM collector
+| elasticsearch_slm_stats_json_parse_failures                           | counter   | 0           | JSON parse failures for SLM collector
+| elasticsearch_slm_stats_retention_runs_total                          | counter   | 0           | Total retention runs
+| elasticsearch_slm_stats_retention_failed_total                        | counter   | 0           | Total failed retention runs
+| elasticsearch_slm_stats_retention_timed_out_total                     | counter   | 0           | Total retention run timeouts
+| elasticsearch_slm_stats_retention_deletion_time_seconds               | gauge     | 0           | Retention run deletion time
+| elasticsearch_slm_stats_total_snapshots_taken_total                   | counter   | 0           | Total snapshots taken
+| elasticsearch_slm_stats_total_snapshots_failed_total                  | counter   | 0           | Total snapshots failed
+| elasticsearch_slm_stats_total_snapshots_deleted_total                 | counter   | 0           | Total snapshots deleted
+| elasticsearch_slm_stats_total_snapshots_failed_total                  | counter   | 0           | Total snapshots failed
+| elasticsearch_slm_stats_snapshots_taken_total                         | counter   | 1           | Snapshots taken by policy
+| elasticsearch_slm_stats_snapshots_failed_total                        | counter   | 1           | Snapshots failed by policy
+| elasticsearch_slm_stats_snapshots_deleted_total                       | counter   | 1           | Snapshots deleted by policy
+| elasticsearch_slm_stats_snapshot_deletion_failures_total              | counter   | 1           | Snapshot deletion failures by policy
+| elasticsearch_slm_stats_operation_mode                                | gauge     | 1           | SLM operation mode (Running, stopping, stopped)
+
 
 ### Alerts & Recording Rules
 
 We provide examples for [Prometheus](http://prometheus.io) [alerts and recording rules](examples/prometheus/elasticsearch.rules) as well as an [Grafana](http://www.grafana.org) [Dashboard](examples/grafana/dashboard.json) and a [Kubernetes](http://kubernetes.io) [Deployment](examples/kubernetes/deployment.yml).
 
-The example dashboard needs the [node_exporter](https://github.com/prometheus/node_exporter) installed. In order to select the nodes that belong to the ElasticSearch cluster, we rely on a label `cluster`.
+The example dashboard needs the [node_exporter](https://github.com/prometheus/node_exporter) installed. In order to select the nodes that belong to the Elasticsearch cluster, we rely on a label `cluster`.
 Depending on your setup, it can derived from the platform metadata:
 
 For example on [GCE](https://cloud.google.com)