Karolis2011
fa57353a6e
- Introduced detailed configuration guidelines in alloy.instructions.md - Added general instructions for project structure in general.instructions.md - Created config.yaml for NAMU-PC with target hostnames - Implemented example.alloy and openwrt.alloy for service discovery and scraping - Added alloy_seed.json for initial configuration state - Developed demo.alloy for comprehensive monitoring setup - Established std.alloy for repository path formatting and host configuration loading - Updated test.alloy to utilize new host configuration loading
273 lines
15 KiB
Plaintext
273 lines
15 KiB
Plaintext
declare "ceph_linux" {
|
|
// Fetch targets dynamically from the HTTP SD endpoint
|
|
discovery.http "ceph_exporter_dynamic" {
|
|
url = "http://ceph-a.gr7.kkarolis.lt:8765/sd/prometheus/sd-config?service=ceph-exporter"
|
|
}
|
|
|
|
// Add ceph_cluster label to all discovered targets
|
|
discovery.relabel "ceph_exporter_with_cluster" {
|
|
targets = discovery.http.ceph_exporter_dynamic.targets
|
|
|
|
rule {
|
|
target_label = "ceph_cluster"
|
|
replacement = "gr7"
|
|
}
|
|
}
|
|
|
|
// Scrape all ceph-exporters (with ceph_cluster label)
|
|
prometheus.scrape "metrics_integrations_integrations_ceph" {
|
|
targets = discovery.relabel.ceph_exporter_with_cluster.output
|
|
forward_to = [prometheus.remote_write.metrics_service.receiver]
|
|
job_name = "integrations/ceph"
|
|
}
|
|
|
|
prometheus.remote_write "metrics_service" {
|
|
endpoint {
|
|
url = "https://prometheus-prod-24-prod-eu-west-2.grafana.net/api/prom/push"
|
|
|
|
basic_auth {
|
|
username = "1257735"
|
|
password = sys.env("GCLOUD_RW_API_KEY")
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
ceph_linux "default" { }
|
|
|
|
declare "linux_node_linux" {
|
|
discovery.relabel "integrations_node_exporter" {
|
|
targets = prometheus.exporter.unix.integrations_node_exporter.targets
|
|
|
|
rule {
|
|
target_label = "instance"
|
|
replacement = constants.hostname
|
|
}
|
|
|
|
rule {
|
|
target_label = "job"
|
|
replacement = "integrations/node_exporter"
|
|
}
|
|
}
|
|
|
|
prometheus.exporter.unix "integrations_node_exporter" {
|
|
disable_collectors = ["ipvs", "btrfs", "infiniband", "xfs", "zfs"]
|
|
|
|
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)$"
|
|
mount_points_exclude = "^/(dev|proc|run/credentials/.+|sys|var/lib/docker/.+)($|/)"
|
|
mount_timeout = "5s"
|
|
}
|
|
|
|
netclass {
|
|
ignored_devices = "^(veth.*|cali.*|[a-f0-9]{15})$"
|
|
}
|
|
|
|
netdev {
|
|
device_exclude = "^(veth.*|cali.*|[a-f0-9]{15})$"
|
|
}
|
|
}
|
|
|
|
prometheus.scrape "integrations_node_exporter" {
|
|
targets = discovery.relabel.integrations_node_exporter.output
|
|
forward_to = [prometheus.relabel.integrations_node_exporter.receiver]
|
|
}
|
|
|
|
prometheus.relabel "integrations_node_exporter" {
|
|
forward_to = [prometheus.remote_write.metrics_service.receiver]
|
|
|
|
rule {
|
|
source_labels = ["__name__"]
|
|
regex = "up|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"
|
|
action = "keep"
|
|
}
|
|
}
|
|
|
|
prometheus.remote_write "metrics_service" {
|
|
endpoint {
|
|
url = "https://prometheus-prod-24-prod-eu-west-2.grafana.net/api/prom/push"
|
|
|
|
basic_auth {
|
|
username = "1257735"
|
|
password = sys.env("GCLOUD_RW_API_KEY")
|
|
}
|
|
}
|
|
}
|
|
|
|
loki.source.journal "logs_integrations_integrations_node_exporter_journal_scrape" {
|
|
max_age = "24h0m0s"
|
|
relabel_rules = discovery.relabel.logs_integrations_integrations_node_exporter_journal_scrape.rules
|
|
forward_to = [loki.write.grafana_cloud_loki.receiver]
|
|
}
|
|
|
|
local.file_match "logs_integrations_integrations_node_exporter_direct_scrape" {
|
|
path_targets = [{
|
|
__address__ = "localhost",
|
|
__path__ = "/var/log/{syslog,messages,*.log}",
|
|
instance = constants.hostname,
|
|
job = "integrations/node_exporter",
|
|
}]
|
|
}
|
|
|
|
discovery.relabel "logs_integrations_integrations_node_exporter_journal_scrape" {
|
|
targets = []
|
|
|
|
rule {
|
|
source_labels = ["__journal__systemd_unit"]
|
|
target_label = "unit"
|
|
}
|
|
|
|
rule {
|
|
source_labels = ["__journal__boot_id"]
|
|
target_label = "boot_id"
|
|
}
|
|
|
|
rule {
|
|
source_labels = ["__journal__transport"]
|
|
target_label = "transport"
|
|
}
|
|
|
|
rule {
|
|
source_labels = ["__journal_priority_keyword"]
|
|
target_label = "level"
|
|
}
|
|
}
|
|
|
|
loki.source.file "logs_integrations_integrations_node_exporter_direct_scrape" {
|
|
targets = local.file_match.logs_integrations_integrations_node_exporter_direct_scrape.targets
|
|
forward_to = [loki.write.grafana_cloud_loki.receiver]
|
|
}
|
|
|
|
loki.write "grafana_cloud_loki" {
|
|
endpoint {
|
|
url = "https://logs-prod-012.grafana.net/loki/api/v1/push"
|
|
|
|
basic_auth {
|
|
username = "727913"
|
|
password = sys.env("GCLOUD_RW_API_KEY")
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
linux_node_linux "default" { }
|
|
|
|
declare "self_monitoring_logs_linux" {
|
|
// THIS IS A GENERATED REMOTE CONFIGURATION.
|
|
//
|
|
// * You can edit the contents and matchers for this configuration without them being overwritten.
|
|
// * If you delete ALL generated configurations, the latest default versions will be recreated.
|
|
// * This configuration requires the following environment variables to be set wherever alloy is running:
|
|
// * GCLOUD_RW_API_KEY: The Grafana Cloud API key with write access to Loki.
|
|
// * GCLOUD_FM_COLLECTOR_ID: A unique collector ID matching the remotecfg id argument value.
|
|
|
|
// Write logs to your Grafana Cloud Loki instance.
|
|
loki.write "grafana_cloud_loki" {
|
|
endpoint {
|
|
url = "https://logs-prod-012.grafana.net/loki/api/v1/push"
|
|
|
|
basic_auth {
|
|
username = "727913"
|
|
password = sys.env("GCLOUD_RW_API_KEY")
|
|
}
|
|
}
|
|
}
|
|
|
|
// Read Alloy logs when running as a systemd service with the following additional labels:
|
|
// * job: "integrations/alloy" is compatible with Grafana Cloud's Alloy Health Integrations.
|
|
// * collector_id: The unique collector ID matching the remotecfg id argument value.
|
|
// Used to match collector-specific metrics to power the 'Collector
|
|
// Health' section of the Fleet Management UI.
|
|
loki.source.journal "alloy_logs_unit" {
|
|
matches = "_SYSTEMD_UNIT=alloy.service"
|
|
forward_to = [loki.write.grafana_cloud_loki.receiver]
|
|
labels = {"job" = "integrations/alloy", "collector_id" = sys.env("GCLOUD_FM_COLLECTOR_ID")}
|
|
}
|
|
|
|
// Read Alloy logs from syslog with the following additional labels:
|
|
// * job: "integrations/alloy" is compatible with Grafana Cloud's Alloy Health Integrations.
|
|
// * collector_id: The unique collector ID matching the remotecfg id argument value.
|
|
// Used to match collector-specific metrics to power the 'Collector
|
|
// Health' section of the Fleet Management UI.
|
|
loki.source.journal "alloy_logs_tag" {
|
|
matches = "SYSLOG_IDENTIFIER=alloy"
|
|
forward_to = [loki.write.grafana_cloud_loki.receiver]
|
|
labels = {"job" = "integrations/alloy", "collector_id" = sys.env("GCLOUD_FM_COLLECTOR_ID")}
|
|
}
|
|
}
|
|
|
|
self_monitoring_logs_linux "default" { }
|
|
|
|
declare "self_monitoring_metrics" {
|
|
// THIS IS A GENERATED REMOTE CONFIGURATION.
|
|
//
|
|
// * You can edit the contents and matchers for this configuration without them being overwritten.
|
|
// * If you delete ALL generated configurations, the latest default versions will be recreated.
|
|
// * This configuration requires the following environment variables to be set wherever alloy is running:
|
|
// * GCLOUD_RW_API_KEY: The Grafana Cloud API key with write access to Loki.
|
|
// * GCLOUD_FM_COLLECTOR_ID: A unique collector ID matching the remotecfg id argument value.
|
|
|
|
// Export Alloy metrics in memory.
|
|
prometheus.exporter.self "integrations_alloy_health" { }
|
|
|
|
// Target Alloy metrics with the following additional labels:
|
|
// * job: "integrations/alloy" is compatible with Grafana Cloud's Alloy Health Integrations.
|
|
// * collector_id: The unique collector ID matching the remotecfg id argument value.
|
|
// Used to match collector-specific metrics to power the 'Collector
|
|
// Health' section of the Fleet Management UI.
|
|
// * instance: The hostname of the machine running Alloy.
|
|
discovery.relabel "integrations_alloy_health" {
|
|
targets = prometheus.exporter.self.integrations_alloy_health.targets
|
|
|
|
rule {
|
|
action = "replace"
|
|
target_label = "collector_id"
|
|
replacement = sys.env("GCLOUD_FM_COLLECTOR_ID")
|
|
}
|
|
|
|
rule {
|
|
target_label = "instance"
|
|
replacement = constants.hostname
|
|
}
|
|
|
|
rule {
|
|
target_label = "job"
|
|
replacement = "integrations/alloy"
|
|
}
|
|
}
|
|
|
|
// Scrape Alloy metrics and forward them to the remote write component.
|
|
prometheus.scrape "integrations_alloy_health" {
|
|
targets = array.concat(
|
|
discovery.relabel.integrations_alloy_health.output,
|
|
)
|
|
forward_to = [prometheus.relabel.integrations_alloy_health.receiver]
|
|
job_name = "integrations/alloy"
|
|
}
|
|
|
|
// Select only the metrics that are relevant to the Alloy Health Integrations.
|
|
prometheus.relabel "integrations_alloy_health" {
|
|
forward_to = [prometheus.remote_write.default.receiver]
|
|
|
|
rule {
|
|
source_labels = ["__name__"]
|
|
regex = "alloy_build_info|alloy_component_controller_running_components|alloy_component_dependencies_wait_seconds|alloy_component_dependencies_wait_seconds_bucket|alloy_component_evaluation_seconds|alloy_component_evaluation_seconds_bucket|alloy_component_evaluation_seconds_count|alloy_component_evaluation_seconds_sum|alloy_component_evaluation_slow_seconds|alloy_config_hash|alloy_resources_machine_rx_bytes_total|alloy_resources_machine_tx_bytes_total|alloy_resources_process_cpu_seconds_total|alloy_resources_process_resident_memory_bytes|cluster_node_gossip_health_score|cluster_node_gossip_proto_version|cluster_node_gossip_received_events_total|cluster_node_info|cluster_node_lamport_time|cluster_node_peers|cluster_node_update_observers|cluster_transport_rx_bytes_total|cluster_transport_rx_packet_queue_length|cluster_transport_rx_packets_failed_total|cluster_transport_rx_packets_total|cluster_transport_stream_rx_bytes_total|cluster_transport_stream_rx_packets_failed_total|cluster_transport_stream_rx_packets_total|cluster_transport_stream_tx_bytes_total|cluster_transport_stream_tx_packets_failed_total|cluster_transport_stream_tx_packets_total|cluster_transport_streams|cluster_transport_tx_bytes_total|cluster_transport_tx_packet_queue_length|cluster_transport_tx_packets_failed_total|cluster_transport_tx_packets_total|go_gc_duration_seconds_count|go_goroutines|go_memstats_heap_inuse_bytes|otelcol_exporter_send_failed_spans_total|otelcol_exporter_sent_spans_total|otelcol_processor_batch_batch_send_size_bucket|otelcol_processor_batch_metadata_cardinality|otelcol_processor_batch_timeout_trigger_send_total|otelcol_receiver_accepted_spans_total|otelcol_receiver_refused_spans_total|prometheus_remote_storage_bytes_total|prometheus_remote_storage_highest_timestamp_in_seconds|prometheus_remote_storage_metadata_bytes_total|prometheus_remote_storage_queue_highest_sent_timestamp_seconds|prometheus_remote_storage_samples_failed_total|prometheus_remote_storage_samples_retried_total|prometheus_remote_storage_samples_total|prometheus_remote_storage_sent_batch_duration_seconds_bucket|prometheus_remote_storage_sent_batch_duration_seconds_count|prometheus_remote_storage_sent_batch_duration_seconds_sum|prometheus_remote_storage_shards|prometheus_remote_storage_shards_max|prometheus_remote_storage_shards_min|prometheus_remote_write_wal_samples_appended_total|prometheus_remote_write_wal_storage_active_series|rpc_server_duration_milliseconds_bucket|scrape_duration_seconds|up"
|
|
action = "keep"
|
|
}
|
|
}
|
|
|
|
// Write metrics to your Grafana Cloud Prometheus instance.
|
|
prometheus.remote_write "default" {
|
|
endpoint {
|
|
url = "https://prometheus-prod-24-prod-eu-west-2.grafana.net/api/prom/push"
|
|
|
|
basic_auth {
|
|
username = "1257735"
|
|
password = sys.env("GCLOUD_RW_API_KEY")
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
self_monitoring_metrics "default" { }
|