-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat(monitoring): grafana agent (#125)
feat(grafana-agent): add initial configuration of grafana agent fix(monitoring): add vault and update template fix(monitoring): define http and grpc listen ports for agent fix(monitoring): add update and restart stanzas to grafana agent chore(monitoring): set identity ttl to 1h chore: add requirement limits to grafana agent --------- Signed-off-by: Bruce Becker <[email protected]>
- Loading branch information
1 parent
af8643c
commit 20304fb
Showing
2 changed files
with
183 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,102 @@ | ||
| variable "graf_agent_rel_url" { | ||
| description = "Base URL for grafana release packages." | ||
| type = string | ||
| default = "https://github.com/grafana/agent/releases/download" | ||
| } | ||
| variable "graf_agent_version" { | ||
| description = "Grafana Agent version to be used." | ||
| type = string | ||
| default = "0.40.3" | ||
| } | ||
|
|
||
| variable "scrape_interval" { | ||
| description = "Default scrape interval" | ||
| type = string | ||
| default = "60s" | ||
| } | ||
|
|
||
| job "grafana-agent" { | ||
| vault {} | ||
| type = "system" | ||
| group "nodes" { | ||
| restart { | ||
| render_templates = true | ||
| attempts = 2 | ||
| interval = "5m" | ||
| mode = "delay" | ||
| } | ||
| update { | ||
| max_parallel = 3 | ||
| health_check = "checks" | ||
| min_healthy_time = "10s" | ||
| healthy_deadline = "5m" | ||
| progress_deadline = "10m" | ||
| auto_revert = true | ||
| auto_promote = true | ||
| canary = 1 | ||
| } | ||
| network { | ||
| port "http" {} | ||
| port "grpc" {} | ||
| } | ||
|
|
||
| task "agent" { | ||
| resources { | ||
| memory = 25 | ||
| cpu = 25 | ||
| } | ||
| identity { | ||
| name = "vault" | ||
| aud = ["vault.io"] | ||
| env = true | ||
| file = true | ||
| change_mode = "restart" | ||
| ttl = "1h" | ||
| } | ||
|
|
||
| service { | ||
| port = "http" | ||
| name = "grafana-agent-http" | ||
| check { | ||
| type = "http" | ||
| name = "agent_health" | ||
| path = "/-/healthy" | ||
| interval = "20s" | ||
| timeout = "5s" | ||
| } | ||
| } | ||
|
|
||
| service { | ||
| port = "grpc" | ||
| name = "grafana-agent-grpc" | ||
| check { | ||
| type = "tcp" | ||
| interval = "20s" | ||
| timeout = "5s" | ||
| } | ||
| } | ||
| env { | ||
| HOSTNAME = attr.unique.hostname | ||
| } | ||
| driver = "raw_exec" | ||
| template { | ||
| data = file("grafana-agent.yml.tmpl") | ||
| destination = "local/agent.yml" | ||
| } | ||
| artifact { | ||
| source = "${var.graf_agent_rel_url}/v${var.graf_agent_version}/grafana-agent-linux-${attr.cpu.arch}.zip" | ||
| destination = "local/grafana-agent" | ||
| mode = "file" | ||
| } | ||
| config { | ||
| command = "local/grafana-agent" | ||
| args = [ | ||
| "-config.file", "local/agent.yml", | ||
| "-server.http.address", "${NOMAD_ADDR_http}", | ||
| "-server.grpc.address", "${NOMAD_ADDR_grpc}", | ||
| "-disable-reporting" | ||
| ] | ||
| } | ||
| } | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,81 @@ | ||
| {{ with secret "hashiatho.me-v2/grafana_cloud" }} | ||
| server: | ||
| log_level: info | ||
| metrics: | ||
| wal_directory: /tmp/wal | ||
| global: | ||
| scrape_interval: 60s | ||
| remote_write: | ||
| - url: {{ .Data.data.metrics_url }}/api/prom/push | ||
| basic_auth: | ||
| password: '{{ .Data.data.api_key }}' | ||
| username: '{{ .Data.data.metrics_id }}' | ||
| logs: | ||
| configs: | ||
| - name: basic | ||
| clients: | ||
| - basic_auth: | ||
| username: '{{ .Data.data.logs_id }}' | ||
| password: '{{ .Data.data.api_key }}' | ||
| url: {{ .Data.data.logs_url }}/loki/api/v1/push | ||
| positions: | ||
| filename: /tmp/positions.yaml | ||
| scrape_configs: | ||
| - job_name: integrations/node_exporter_journal_scrape | ||
| journal: | ||
| max_age: 24h | ||
| labels: | ||
| instance: '{{ env "HOSTNAME" }}' | ||
| job: integrations/node_exporter | ||
| relabel_configs: | ||
| - source_labels: ['__journal__systemd_unit'] | ||
| target_label: 'unit' | ||
| - source_labels: ['__journal__boot_id'] | ||
| target_label: 'boot_id' | ||
| - source_labels: ['__journal__transport'] | ||
| target_label: 'transport' | ||
| - source_labels: ['__journal_priority_keyword'] | ||
| target_label: 'level' | ||
| - job_name: integrations/node_exporter_direct_scrape | ||
| static_configs: | ||
| - targets: | ||
| - localhost | ||
| labels: | ||
| instance: '{{ env "HOSTNAME" }}' | ||
| __path__: /var/log/{syslog,messages,*.log} | ||
| job: integrations/node_exporter | ||
|
|
||
| integrations: | ||
| prometheus_remote_write: | ||
| - basic_auth: | ||
| password: '{{ .Data.data.api_key }}' | ||
| username: '{{ .Data.data.metrics_id }}' | ||
| url: '{{ .Data.data.metrics_url }}/api/prom/push' | ||
| node_exporter: | ||
| enabled: true | ||
| # disable unused collectors | ||
| disable_collectors: | ||
| - ipvs #high cardinality on kubelet | ||
| - btrfs | ||
| - infiniband | ||
| - xfs | ||
| - zfs | ||
| # exclude dynamic interfaces | ||
| netclass_ignored_devices: "^(veth.*|cali.*|[a-f0-9]{15})$" | ||
| netdev_device_exclude: "^(veth.*|cali.*|[a-f0-9]{15})$" | ||
| # disable tmpfs | ||
| filesystem_fs_types_exclude: "^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|tmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$" | ||
| # drop extensive scrape statistics | ||
| relabel_configs: | ||
| - replacement: '{{ env "HOSTNAME" }}' | ||
| target_label: instance | ||
| metric_relabel_configs: | ||
| - action: drop | ||
| regex: node_scrape_collector_.+ | ||
| source_labels: | ||
| - __name__ | ||
| - action: keep | ||
| regex: node_arp_entries|node_boot_time_seconds|node_context_switches_total|node_cpu_seconds_total|node_disk_io_time_seconds_total|node_disk_io_time_weighted_seconds_total|node_disk_read_bytes_total|node_disk_read_time_seconds_total|node_disk_reads_completed_total|node_disk_write_time_seconds_total|node_disk_writes_completed_total|node_disk_written_bytes_total|node_filefd_allocated|node_filefd_maximum|node_filesystem_avail_bytes|node_filesystem_device_error|node_filesystem_files|node_filesystem_files_free|node_filesystem_readonly|node_filesystem_size_bytes|node_intr_total|node_load1|node_load15|node_load5|node_md_disks|node_md_disks_required|node_memory_Active_anon_bytes|node_memory_Active_bytes|node_memory_Active_file_bytes|node_memory_AnonHugePages_bytes|node_memory_AnonPages_bytes|node_memory_Bounce_bytes|node_memory_Buffers_bytes|node_memory_Cached_bytes|node_memory_CommitLimit_bytes|node_memory_Committed_AS_bytes|node_memory_DirectMap1G_bytes|node_memory_DirectMap2M_bytes|node_memory_DirectMap4k_bytes|node_memory_Dirty_bytes|node_memory_HugePages_Free|node_memory_HugePages_Rsvd|node_memory_HugePages_Surp|node_memory_HugePages_Total|node_memory_Hugepagesize_bytes|node_memory_Inactive_anon_bytes|node_memory_Inactive_bytes|node_memory_Inactive_file_bytes|node_memory_Mapped_bytes|node_memory_MemAvailable_bytes|node_memory_MemFree_bytes|node_memory_MemTotal_bytes|node_memory_SReclaimable_bytes|node_memory_SUnreclaim_bytes|node_memory_ShmemHugePages_bytes|node_memory_ShmemPmdMapped_bytes|node_memory_Shmem_bytes|node_memory_Slab_bytes|node_memory_SwapTotal_bytes|node_memory_VmallocChunk_bytes|node_memory_VmallocTotal_bytes|node_memory_VmallocUsed_bytes|node_memory_WritebackTmp_bytes|node_memory_Writeback_bytes|node_netstat_Icmp6_InErrors|node_netstat_Icmp6_InMsgs|node_netstat_Icmp6_OutMsgs|node_netstat_Icmp_InErrors|node_netstat_Icmp_InMsgs|node_netstat_Icmp_OutMsgs|node_netstat_IpExt_InOctets|node_netstat_IpExt_OutOctets|node_netstat_TcpExt_ListenDrops|node_netstat_TcpExt_ListenOverflows|node_netstat_TcpExt_TCPSynRetrans|node_netstat_Tcp_InErrs|node_netstat_Tcp_InSegs|node_netstat_Tcp_OutRsts|node_netstat_Tcp_OutSegs|node_netstat_Tcp_RetransSegs|node_netstat_Udp6_InDatagrams|node_netstat_Udp6_InErrors|node_netstat_Udp6_NoPorts|node_netstat_Udp6_OutDatagrams|node_netstat_Udp6_RcvbufErrors|node_netstat_Udp6_SndbufErrors|node_netstat_UdpLite_InErrors|node_netstat_Udp_InDatagrams|node_netstat_Udp_InErrors|node_netstat_Udp_NoPorts|node_netstat_Udp_OutDatagrams|node_netstat_Udp_RcvbufErrors|node_netstat_Udp_SndbufErrors|node_network_carrier|node_network_info|node_network_mtu_bytes|node_network_receive_bytes_total|node_network_receive_compressed_total|node_network_receive_drop_total|node_network_receive_errs_total|node_network_receive_fifo_total|node_network_receive_multicast_total|node_network_receive_packets_total|node_network_speed_bytes|node_network_transmit_bytes_total|node_network_transmit_compressed_total|node_network_transmit_drop_total|node_network_transmit_errs_total|node_network_transmit_fifo_total|node_network_transmit_multicast_total|node_network_transmit_packets_total|node_network_transmit_queue_length|node_network_up|node_nf_conntrack_entries|node_nf_conntrack_entries_limit|node_os_info|node_sockstat_FRAG6_inuse|node_sockstat_FRAG_inuse|node_sockstat_RAW6_inuse|node_sockstat_RAW_inuse|node_sockstat_TCP6_inuse|node_sockstat_TCP_alloc|node_sockstat_TCP_inuse|node_sockstat_TCP_mem|node_sockstat_TCP_mem_bytes|node_sockstat_TCP_orphan|node_sockstat_TCP_tw|node_sockstat_UDP6_inuse|node_sockstat_UDPLITE6_inuse|node_sockstat_UDPLITE_inuse|node_sockstat_UDP_inuse|node_sockstat_UDP_mem|node_sockstat_UDP_mem_bytes|node_sockstat_sockets_used|node_softnet_dropped_total|node_softnet_processed_total|node_softnet_times_squeezed_total|node_systemd_unit_state|node_textfile_scrape_error|node_time_zone_offset_seconds|node_timex_estimated_error_seconds|node_timex_maxerror_seconds|node_timex_offset_seconds|node_timex_sync_status|node_uname_info|node_vmstat_oom_kill|node_vmstat_pgfault|node_vmstat_pgmajfault|node_vmstat_pgpgin|node_vmstat_pgpgout|node_vmstat_pswpin|node_vmstat_pswpout|process_max_fds|process_open_fds | ||
| source_labels: | ||
| - __name__ | ||
| {{ end }} |