aboutsummaryrefslogtreecommitdiffstats
path: root/terraform-ci-infra/1n_nmd/prometheus
diff options
context:
space:
mode:
authorpmikus <pmikus@cisco.com>2021-01-07 14:27:38 +0000
committerpmikus <pmikus@cisco.com>2021-01-29 08:44:37 +0000
commita44eef233de959c5679602dc6cd1ed866d6abc14 (patch)
tree2c4d0cd5e0d1293ae86a09cf26009b869c72360d /terraform-ci-infra/1n_nmd/prometheus
parent474163bc78aa418595b227c81056987b1114104d (diff)
Infra: Monitoring capability
+ Monitoring SOA + Nomad alertmanager job + Nomad prometheus job + Nomad grafana job Signed-off-by: pmikus <pmikus@cisco.com> Change-Id: I0b32e9c87276ba1a2d4a5322816f3473c737eae2
Diffstat (limited to 'terraform-ci-infra/1n_nmd/prometheus')
-rw-r--r--terraform-ci-infra/1n_nmd/prometheus/conf/nomad/prometheus.hcl569
-rw-r--r--terraform-ci-infra/1n_nmd/prometheus/main.tf37
-rw-r--r--terraform-ci-infra/1n_nmd/prometheus/variables.tf84
3 files changed, 690 insertions, 0 deletions
diff --git a/terraform-ci-infra/1n_nmd/prometheus/conf/nomad/prometheus.hcl b/terraform-ci-infra/1n_nmd/prometheus/conf/nomad/prometheus.hcl
new file mode 100644
index 0000000000..2d74662f31
--- /dev/null
+++ b/terraform-ci-infra/1n_nmd/prometheus/conf/nomad/prometheus.hcl
@@ -0,0 +1,569 @@
+job "${job_name}" {
+ # The "region" parameter specifies the region in which to execute the job.
+ # If omitted, this inherits the default region name of "global".
+ # region = "global"
+ #
+ # The "datacenters" parameter specifies the list of datacenters which should
+ # be considered when placing this task. This must be provided.
+ datacenters = "${datacenters}"
+
+ # The "type" parameter controls the type of job, which impacts the scheduler's
+ # decision on placement. This configuration is optional and defaults to
+ # "service". For a full list of job types and their differences, please see
+ # the online documentation.
+ #
+ # For more information, please see the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/jobspec/schedulers
+ #
+ type = "service"
+
+ update {
+ # The "max_parallel" parameter specifies the maximum number of updates to
+ # perform in parallel. In this case, this specifies to update a single task
+ # at a time.
+ max_parallel = 1
+
+ health_check = "checks"
+
+ # The "min_healthy_time" parameter specifies the minimum time the allocation
+ # must be in the healthy state before it is marked as healthy and unblocks
+ # further allocations from being updated.
+ min_healthy_time = "10s"
+
+ # The "healthy_deadline" parameter specifies the deadline in which the
+ # allocation must be marked as healthy after which the allocation is
+ # automatically transitioned to unhealthy. Transitioning to unhealthy will
+ # fail the deployment and potentially roll back the job if "auto_revert" is
+ # set to true.
+ healthy_deadline = "3m"
+
+ # The "progress_deadline" parameter specifies the deadline in which an
+ # allocation must be marked as healthy. The deadline begins when the first
+ # allocation for the deployment is created and is reset whenever an allocation
+ # as part of the deployment transitions to a healthy state. If no allocation
+ # transitions to the healthy state before the progress deadline, the
+ # deployment is marked as failed.
+ progress_deadline = "10m"
+
+%{ if use_canary }
+ # The "canary" parameter specifies that changes to the job that would result
+ # in destructive updates should create the specified number of canaries
+ # without stopping any previous allocations. Once the operator determines the
+ # canaries are healthy, they can be promoted which unblocks a rolling update
+ # of the remaining allocations at a rate of "max_parallel".
+ #
+ # Further, setting "canary" equal to the count of the task group allows
+ # blue/green deployments. When the job is updated, a full set of the new
+ # version is deployed and upon promotion the old version is stopped.
+ canary = 1
+
+ # Specifies if the job should auto-promote to the canary version when all
+ # canaries become healthy during a deployment. Defaults to false which means
+ # canaries must be manually updated with the nomad deployment promote
+ # command.
+ auto_promote = true
+
+ # The "auto_revert" parameter specifies if the job should auto-revert to the
+ # last stable job on deployment failure. A job is marked as stable if all the
+ # allocations as part of its deployment were marked healthy.
+ auto_revert = true
+%{ endif }
+ }
+
+ # The "group" stanza defines a series of tasks that should be co-located on
+ # the same Nomad client. Any task within a group will be placed on the same
+ # client.
+ #
+ # For more information and examples on the "group" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/group
+ #
+ group "prod-group1-${service_name}" {
+ # The "count" parameter specifies the number of the task groups that should
+ # be running under this group. This value must be non-negative and defaults
+ # to 1.
+ count = ${group_count}
+
+ # The volume stanza allows the group to specify that it requires a given
+ # volume from the cluster.
+ #
+ # For more information and examples on the "volume" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/volume
+ #
+ %{ if use_host_volume }
+ volume "prod-volume1-${service_name}" {
+ type = "host"
+ read_only = false
+ source = "${host_volume}"
+ }
+ %{ endif }
+
+ # The constraint allows restricting the set of eligible nodes. Constraints
+ # may filter on attributes or client metadata.
+ #
+ # For more information and examples on the "volume" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/constraint
+ #
+ constraint {
+ attribute = "$${attr.cpu.arch}"
+ operator = "!="
+ value = "arm64"
+ }
+
+ # The "task" stanza creates an individual unit of work, such as a Docker
+ # container, web application, or batch processing.
+ #
+ # For more information and examples on the "task" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/task
+ #
+ task "prod-task1-${service_name}" {
+ # The "driver" parameter specifies the task driver that should be used to
+ # run the task.
+ driver = "exec"
+
+ %{ if use_host_volume }
+ volume_mount {
+ volume = "prod-volume1-${service_name}"
+ destination = "${data_dir}"
+ read_only = false
+ }
+ %{ endif }
+
+ %{ if use_vault_provider }
+ vault {
+ policies = "${vault_kv_policy_name}"
+ }
+ %{ endif }
+
+ # The "config" stanza specifies the driver configuration, which is passed
+ # directly to the driver to start the task. The details of configurations
+ # are specific to each driver, so please see specific driver
+ # documentation for more information.
+ config {
+ command = "local/prometheus-${version}.linux-amd64/prometheus"
+ args = [
+ "--config.file=secrets/prometheus.yml",
+ "--storage.tsdb.path=${data_dir}prometheus/",
+ "--storage.tsdb.retention.time=15d"
+ ]
+ }
+
+ # The artifact stanza instructs Nomad to fetch and unpack a remote resource,
+ # such as a file, tarball, or binary. Nomad downloads artifacts using the
+ # popular go-getter library, which permits downloading artifacts from a
+ # variety of locations using a URL as the input source.
+ #
+ # For more information and examples on the "artifact" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/artifact
+ #
+ artifact {
+ source = "${url}"
+ }
+
+ # The "template" stanza instructs Nomad to manage a template, such as
+ # a configuration file or script. This template can optionally pull data
+ # from Consul or Vault to populate runtime configuration data.
+ #
+ # For more information and examples on the "template" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/template
+ #
+ template {
+ change_mode = "noop"
+ change_signal = "SIGINT"
+ destination = "secrets/alerts.yml"
+ left_delimiter = "{{{"
+ right_delimiter = "}}}"
+ data = <<EOH
+---
+groups:
+- name: "Consul"
+ rules:
+ - alert: ConsulServiceHealthcheckFailed
+ expr: consul_catalog_service_node_healthy == 0
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Consul service healthcheck failed (instance {{ $labels.instance }})."
+ description: "Service: `{{ $labels.service_name }}` Healthcheck: `{{ $labels.service_id }}`."
+ - alert: ConsulMissingMasterNode
+ expr: consul_raft_peers < 3
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Consul missing master node (instance {{ $labels.instance }})."
+ description: "Numbers of consul raft peers should be 3, in order to preserve quorum."
+ - alert: ConsulAgentUnhealthy
+ expr: consul_health_node_status{status="critical"} == 1
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Consul agent unhealthy (instance {{ $labels.instance }})."
+ description: "A Consul agent is down."
+- name: "Hosts"
+ rules:
+ - alert: NodeDown
+ expr: up == 0
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Prometheus target missing (instance {{ $labels.instance }})."
+ description: "A Prometheus target has disappeared. An exporter might be crashed."
+ - alert: HostHighCpuLoad
+ expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host high CPU load (instance {{ $labels.instance }})."
+ description: "CPU load is > 80%."
+ - alert: HostOutOfMemory
+ expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
+ for: 2m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host out of memory (instance {{ $labels.instance }})."
+ description: "Node memory is filling up (< 10% left)."
+ - alert: HostOomKillDetected
+ expr: increase(node_vmstat_oom_kill[1m]) > 0
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host OOM kill detected (instance {{ $labels.instance }})."
+ description: "OOM kill detected."
+ - alert: HostMemoryUnderMemoryPressure
+ expr: rate(node_vmstat_pgmajfault[1m]) > 1000
+ for: 2m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host memory under memory pressure (instance {{ $labels.instance }})."
+ description: "The node is under heavy memory pressure. High rate of major page faults."
+ - alert: HostOutOfDiskSpace
+ expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
+ for: 2m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host out of disk space (instance {{ $labels.instance }})."
+ description: "Disk is almost full (< 10% left)."
+ - alert: HostRaidDiskFailure
+ expr: node_md_disks{state="failed"} > 0
+ for: 2m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host RAID disk failure (instance {{ $labels.instance }})."
+ description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap."
+ - alert: HostConntrackLimit
+ expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8
+ for: 5m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host conntrack limit (instance {{ $labels.instance }})."
+ description: "The number of conntrack is approching limit."
+ - alert: HostNetworkInterfaceSaturated
+ expr: (rate(node_network_receive_bytes_total{device!~"^tap.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*"} > 0.8
+ for: 1m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host Network Interface Saturated (instance {{ $labels.instance }})."
+ description: "The network interface {{ $labels.interface }} on {{ $labels.instance }} is getting overloaded."
+ - alert: HostSystemdServiceCrashed
+ expr: node_systemd_unit_state{state="failed"} == 1
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host SystemD service crashed (instance {{ $labels.instance }})."
+ description: "SystemD service crashed."
+ - alert: HostEdacCorrectableErrorsDetected
+ expr: increase(node_edac_correctable_errors_total[1m]) > 0
+ for: 0m
+ labels:
+ severity: info
+ annotations:
+ summary: "Host EDAC Correctable Errors detected (instance {{ $labels.instance }})."
+ description: '{{ $labels.instance }} has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'
+ - alert: HostEdacUncorrectableErrorsDetected
+ expr: node_edac_uncorrectable_errors_total > 0
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }})."
+ description: '{{ $labels.instance }} has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.'
+- name: "Min.io"
+ rules:
+ - alert: MinioDiskOffline
+ expr: minio_offline_disks > 0
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Minio disk offline (instance {{ $labels.instance }})"
+ description: "Minio disk is offline."
+ - alert: MinioStorageSpaceExhausted
+ expr: minio_disk_storage_free_bytes / 1024 / 1024 / 1024 < 10
+ for: 2m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Minio storage space exhausted (instance {{ $labels.instance }})."
+ description: "Minio storage space is low (< 10 GB)."
+- name: "Prometheus"
+ rules:
+ - alert: PrometheusConfigurationReloadFailure
+ expr: prometheus_config_last_reload_successful != 1
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Prometheus configuration reload failure (instance {{ $labels.instance }})."
+ description: "Prometheus configuration reload error."
+ - alert: PrometheusTooManyRestarts
+ expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Prometheus too many restarts (instance {{ $labels.instance }})."
+ description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping."
+ - alert: PrometheusAlertmanagerConfigurationReloadFailure
+ expr: alertmanager_config_last_reload_successful != 1
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})."
+ description: "AlertManager configuration reload error."
+ - alert: PrometheusRuleEvaluationFailures
+ expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Prometheus rule evaluation failures (instance {{ $labels.instance }})."
+ description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts."
+ - alert: PrometheusTargetScrapingSlow
+ expr: prometheus_target_interval_length_seconds{quantile="0.9"} > 60
+ for: 5m
+ labels:
+ severity: warning
+ annotations:
+ summary: "Prometheus target scraping slow (instance {{ $labels.instance }})."
+ description: "Prometheus is scraping exporters slowly."
+ - alert: PrometheusTsdbCompactionsFailed
+ expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Prometheus TSDB compactions failed (instance {{ $labels.instance }})."
+ description: "Prometheus encountered {{ $value }} TSDB compactions failures."
+ - alert: PrometheusTsdbHeadTruncationsFailed
+ expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Prometheus TSDB head truncations failed (instance {{ $labels.instance }})."
+ description: "Prometheus encountered {{ $value }} TSDB head truncation failures."
+ - alert: PrometheusTsdbWalCorruptions
+ expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})."
+ description: "Prometheus encountered {{ $value }} TSDB WAL corruptions."
+ - alert: PrometheusTsdbWalTruncationsFailed
+ expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
+ for: 0m
+ labels:
+ severity: critical
+ annotations:
+ summary: "Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})."
+ description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures."
+EOH
+ }
+
+ template {
+ change_mode = "noop"
+ change_signal = "SIGINT"
+ destination = "secrets/prometheus.yml"
+ data = <<EOH
+---
+global:
+ scrape_interval: 5s
+ scrape_timeout: 5s
+ evaluation_interval: 5s
+
+alerting:
+ alertmanagers:
+ - consul_sd_configs:
+ - server: '{{ env "NOMAD_IP_prometheus" }}:8500'
+ services: [ 'alertmanager' ]
+
+rule_files:
+ - 'alerts.yml'
+
+scrape_configs:
+
+ - job_name: 'Nomad Cluster'
+ consul_sd_configs:
+ - server: '{{ env "NOMAD_IP_prometheus" }}:8500'
+ services: [ 'nomad-client', 'nomad' ]
+ relabel_configs:
+ - source_labels: [__meta_consul_tags]
+ regex: '(.*)http(.*)'
+ action: keep
+ metrics_path: /v1/metrics
+ params:
+ format: [ 'prometheus' ]
+
+ - job_name: 'Consul Cluster'
+ static_configs:
+ - targets: [ '10.30.51.30:8500', '10.30.51.32:8500', '10.30.51.33:8500' ]
+ metrics_path: /v1/agent/metrics
+ params:
+ format: [ 'prometheus' ]
+
+ - job_name: 'Alertmanager'
+ consul_sd_configs:
+ - server: '{{ env "NOMAD_IP_prometheus" }}:8500'
+ services: [ 'alertmanager' ]
+
+ - job_name: 'Blackbox Exporter (icmp)'
+ static_configs:
+ - targets: [ 'gerrit.fd.io' ]
+ - targets: [ 'jenkins.fd.io' ]
+ - targets: [ '10.30.51.32' ]
+ params:
+ module: [ 'icmp_v4' ]
+ relabel_configs:
+ - source_labels: [__address__]
+ target_label: __param_target
+ - source_labels: [__param_target]
+ target_label: instance
+ - target_label: __address__
+ replacement: localhost:9115
+ metrics_path: /probe
+
+ - job_name: 'Blackbox Exporter (http)'
+ static_configs:
+ - targets: [ 'gerrit.fd.io' ]
+ - targets: [ 'jenkins.fd.io' ]
+ params:
+ module: [ 'http_2xx' ]
+ relabel_configs:
+ - source_labels: [__address__]
+ target_label: __param_target
+ - source_labels: [__param_target]
+ target_label: instance
+ - target_label: __address__
+ replacement: localhost:9115
+ metrics_path: /probe
+
+ - job_name: 'cAdvisor Exporter'
+ consul_sd_configs:
+ - server: '{{ env "NOMAD_IP_prometheus" }}:8500'
+ services: [ 'cadvisorexporter' ]
+
+ - job_name: 'Grafana'
+ consul_sd_configs:
+ - server: '{{ env "NOMAD_IP_prometheus" }}:8500'
+ services: [ 'grafana' ]
+
+ - job_name: 'Node Exporter'
+ consul_sd_configs:
+ - server: '{{ env "NOMAD_IP_prometheus" }}:8500'
+ services: [ 'nodeexporter' ]
+
+ - job_name: 'Prometheus'
+ consul_sd_configs:
+ - server: '{{ env "NOMAD_IP_prometheus" }}:8500'
+ services: [ 'prometheus' ]
+
+ - job_name: 'Minio'
+ bearer_token: eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ3NjQ1ODEzMzcsImlzcyI6InByb21ldGhldXMiLCJzdWIiOiJtaW5pbyJ9.oeTw3EIaiFmlDikrHXWiWXMH2vxLfDLkfjEC7G2N3M_keH_xyA_l2ofLLNYtopa_3GCEZnxLQdPuFZrmgpkDWg
+ consul_sd_configs:
+ - server: '{{ env "NOMAD_IP_prometheus" }}:8500'
+ services: [ 'storage' ]
+ metrics_path: /minio/prometheus/metrics
+EOH
+ }
+
+ # The service stanza instructs Nomad to register a service with Consul.
+ #
+ # For more information and examples on the "task" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/service
+ #
+ service {
+ name = "${service_name}"
+ port = "${service_name}"
+ tags = [ "${service_name}$${NOMAD_ALLOC_INDEX}" ]
+ check {
+ name = "Prometheus Check Live"
+ type = "http"
+ path = "/-/healthy"
+ interval = "10s"
+ timeout = "2s"
+ }
+ }
+
+ # The "resources" stanza describes the requirements a task needs to
+ # execute. Resource requirements include memory, network, cpu, and more.
+ # This ensures the task will execute on a machine that contains enough
+ # resource capacity.
+ #
+ # For more information and examples on the "resources" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/resources
+ #
+ resources {
+ cpu = ${cpu}
+ memory = ${mem}
+ # The network stanza specifies the networking requirements for the task
+ # group, including the network mode and port allocations. When scheduling
+ # jobs in Nomad they are provisioned across your fleet of machines along
+ # with other jobs and services. Because you don't know in advance what host
+ # your job will be provisioned on, Nomad will provide your tasks with
+ # network configuration when they start up.
+ #
+ # For more information and examples on the "template" stanza, please see
+ # the online documentation at:
+ #
+ # https://www.nomadproject.io/docs/job-specification/network
+ #
+ network {
+ port "${service_name}" {
+ static = ${port}
+ }
+ }
+ }
+ }
+ }
+} \ No newline at end of file
diff --git a/terraform-ci-infra/1n_nmd/prometheus/main.tf b/terraform-ci-infra/1n_nmd/prometheus/main.tf
new file mode 100644
index 0000000000..9506ba3941
--- /dev/null
+++ b/terraform-ci-infra/1n_nmd/prometheus/main.tf
@@ -0,0 +1,37 @@
+locals {
+ datacenters = join(",", var.nomad_datacenters)
+
+ prometheus_url = join("",
+ [
+ "https://github.com",
+ "/prometheus/prometheus/releases/download/",
+ "v${var.prometheus_version}/",
+ "prometheus-${var.prometheus_version}.linux-amd64.tar.gz"
+ ]
+ )
+}
+
+data "template_file" "nomad_job_prometheus" {
+ template = file("${path.module}/conf/nomad/prometheus.hcl")
+ vars = {
+ datacenters = local.datacenters
+ url = local.prometheus_url
+ job_name = var.prometheus_job_name
+ use_canary = var.prometheus_use_canary
+ group_count = var.prometheus_group_count
+ use_host_volume = var.prometheus_use_host_volume
+ host_volume = var.nomad_host_volume
+ data_dir = var.prometheus_data_dir
+ service_name = var.prometheus_service_name
+ use_vault_provider = var.prometheus_vault_secret.use_vault_provider
+ version = var.prometheus_version
+ cpu = var.prometheus_cpu
+ mem = var.prometheus_mem
+ port = var.prometheus_port
+ }
+}
+
+resource "nomad_job" "nomad_job_prometheus" {
+ jobspec = data.template_file.nomad_job_prometheus.rendered
+ detach = false
+} \ No newline at end of file
diff --git a/terraform-ci-infra/1n_nmd/prometheus/variables.tf b/terraform-ci-infra/1n_nmd/prometheus/variables.tf
new file mode 100644
index 0000000000..a509533ccd
--- /dev/null
+++ b/terraform-ci-infra/1n_nmd/prometheus/variables.tf
@@ -0,0 +1,84 @@
+# Nomad
+variable "nomad_datacenters" {
+ description = "Nomad data centers"
+ type = list(string)
+ default = [ "dc1" ]
+}
+
+variable "nomad_host_volume" {
+ description = "Nomad Host Volume"
+ type = string
+ default = "persistence"
+}
+
+# Prometheus
+variable "prometheus_job_name" {
+ description = "Prometheus job name"
+ type = string
+ default = "prometheus"
+}
+
+variable "prometheus_group_count" {
+ description = "Number of prometheus group instances"
+ type = number
+ default = 1
+}
+
+variable "prometheus_service_name" {
+ description = "Prometheus service name"
+ type = string
+ default = "prometheus"
+}
+
+variable "prometheus_version" {
+ description = "Prometheus version"
+ type = string
+ default = "v2.24.0"
+}
+
+variable "prometheus_use_canary" {
+ description = "Uses canary deployment"
+ type = bool
+ default = false
+}
+
+variable "prometheus_vault_secret" {
+ description = "Set of properties to be able to fetch secret from vault"
+ type = object({
+ use_vault_provider = bool,
+ vault_kv_policy_name = string,
+ vault_kv_path = string,
+ vault_kv_field_access_key = string,
+ vault_kv_field_secret_key = string
+ })
+}
+
+variable "prometheus_cpu" {
+ description = "Prometheus CPU allocation"
+ type = number
+ default = 2000
+}
+
+variable "prometheus_mem" {
+ description = "Prometheus RAM allocation"
+ type = number
+ default = 8192
+}
+
+variable "prometheus_port" {
+ description = "Prometheus TCP allocation"
+ type = number
+ default = 9200
+}
+
+variable "prometheus_data_dir" {
+ description = "Prometheus DISK allocation"
+ type = string
+ default = "/data"
+}
+
+variable "prometheus_use_host_volume" {
+ description = "Use Nomad host volume feature"
+ type = bool
+ default = false
+} \ No newline at end of file