update

2026-07-23 19:38:14 -04:00
parent 72272e4006
commit 84e1ead50c
283 changed files with 0 additions and 206 deletions
@@ -0,0 +1,4 @@
+logging {
+  level = "info"
+  format = "logfmt"
+}
@@ -0,0 +1,23 @@
+<%- if logs_enabled and logs_docker %>
+discovery.docker "dockerlogs" {
+  host = "unix:///var/run/docker.sock"
+}
+
+discovery.relabel "dockerlogs" {
+  targets = []
+
+  rule {
+    source_labels = ["__meta_docker_container_name"]
+    regex = "/(.*)"
+    target_label = "service_name"
+  }
+}
+
+loki.source.docker "default" {
+  host       = "unix:///var/run/docker.sock"
+  targets    = discovery.docker.dockerlogs.targets
+  labels     = {"platform" = "docker"}
+  relabel_rules = discovery.relabel.dockerlogs.rules
+  forward_to = [loki.write.default.receiver]
+}
+<%- endif %>
@@ -0,0 +1,44 @@
+<%- if logs_enabled and logs_system %>
+loki.source.journal "journal" {
+  max_age       = "24h0m0s"
+  relabel_rules = discovery.relabel.journal.rules
+  forward_to    = [loki.write.default.receiver]
+  labels        = {component = string.format("%s-journal", constants.hostname)}
+  // NOTE: This is important to fix https://github.com/grafana/alloy/issues/924
+  path          = "/var/log/journal"
+}
+
+local.file_match "system" {
+  path_targets = [{
+    __address__ = "localhost",
+    __path__    = "/var/log/{syslog,messages,*.log}",
+    instance    = constants.hostname,
+    job         = string.format("%s-logs", constants.hostname),
+  }]
+}
+
+discovery.relabel "journal" {
+  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 "system" {
+  targets    = local.file_match.system.targets
+  forward_to = [loki.write.default.receiver]
+}
+<%- endif %>
@@ -0,0 +1,23 @@
+<%- if metrics_enabled and metrics_docker %>
+prometheus.exporter.cadvisor "dockermetrics" {
+  docker_host = "unix:///var/run/docker.sock"
+  storage_duration = "5m"
+}
+
+/* Relabel component to drop container_spec metrics that often have NaN values */
+prometheus.relabel "docker_filter" {
+  forward_to = [prometheus.remote_write.default.receiver]
+  
+  rule {
+    source_labels = ["__name__"]
+    regex = "container_spec_(cpu_period|cpu_quota|cpu_shares|memory_limit_bytes|memory_swap_limit_bytes|memory_reservation_limit_bytes)"
+    action = "drop"
+  }
+}
+
+prometheus.scrape "dockermetrics" {
+  targets    = prometheus.exporter.cadvisor.dockermetrics.targets
+  forward_to = [prometheus.relabel.docker_filter.receiver]
+  scrape_interval = "10s"
+}
+<%- endif %>
@@ -0,0 +1,36 @@
+<%- if metrics_enabled and metrics_system %>
+discovery.relabel "metrics" {
+  targets = prometheus.exporter.unix.metrics.targets
+  rule {
+    target_label = "instance"
+    replacement  = constants.hostname
+  }
+  rule {
+    target_label = "job"
+    replacement = string.format("%s-metrics", constants.hostname)
+  }
+}
+
+prometheus.exporter.unix "metrics" {
+  disable_collectors = ["ipvs", "btrfs", "infiniband", "xfs", "zfs"]
+  enable_collectors = ["meminfo"]
+  rootfs_path = "/rootfs"
+  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 "metrics" {
+  scrape_interval = "15s"
+  targets    = discovery.relabel.metrics.output
+  forward_to = [prometheus.remote_write.default.receiver]
+}
+<%- endif %>
@@ -0,0 +1,20 @@
+<%- if logs_enabled  %>
+loki.write "default" {
+  endpoint {
+    url = "<< logs_loki_url >>"
+    
+    // Batching configuration to reduce request volume and prevent rate limiting
+    batch_wait = "5s"           // Wait up to 5 seconds before sending
+    batch_size = "1MiB"         // Send when batch reaches 1MB (1048576 bytes)
+  }
+  external_labels = {}
+}
+<%- endif %>
+
+<%- if metrics_enabled %>
+prometheus.remote_write "default" {
+  endpoint {
+    url = "<< metrics_prometheus_url >>"
+  }
+}
+<%- endif %>