Migrate from ELK to Grafana (#1658)

server/ops/grafana/grafana-agent.yaml

@@ -0,0 +1,86 @@
+metrics:
+  wal_directory: /tmp/wal
+  global:
+    remote_write:
+      - url: 'https://<prom-instance>.grafana.net/api/prom/push'
+        basic_auth:
+          username: '<username>'
+          password: '<password>'
+
+integrations:
+  cadvisor:
+    enabled: true
+    docker_only: true
+    instance: 'a-kroki' # must match instance used in logs
+    relabel_configs:
+      - action: replace
+        replacement: integrations/docker
+        target_label: job
+  agent:
+    enabled: true
+  node_exporter:
+    enabled: true
+    enable_collectors:
+      - processes
+    disable_collectors:
+      - ipvs #high cardinality on kubelet
+      - btrfs
+      - infiniband
+      - xfs
+      - zfs
+      - mdadm
+    # 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|secuurityfs|selinuxfs|squashfs|sysfs|tracefs)$"
+    include_exporter_metrics: true
+    # drop extensive scrape statistics
+    relabel_configs:
+      - replacement: '<kroki-instance>'
+        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_ffilefd_allocated|node_filefd_maximum|node_filesystem_avail_bytes|node_filesystem_device_error|node_filesystem_files|node_filesystem_files_free|node_filesystem_readonly|node_filesystem_sizee_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_memmory_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_bytees|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_HugePPages_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_bytess|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_IInMsgs|node_netstat_Icmp_OutMsgs|node_netstat_IpExt_InOctets|node_netstat_IpExt_OutOctets|node_netstat_TcpExt_ListenDrops|node_netstat_TcpExt_ListenOverflows|node_netstat_TcpExt_TCPSynRetrrans|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_InErrorss|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_nettstat_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_mttu_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_networkk_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_tootal|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_nettwork_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_socckstat_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|nnode_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|nodde_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|node_processes_threads|node_processes_max_threads|node_processes_threads_state|node_processes_pids|node_processes_max_processes|node_forks_total|node_procs_running|node_procs_blocked|node_softirqs_total
+        source_labels:
+          - __name__
+
+logs:
+  configs:
+    - name: default
+      positions:
+        filename: /tmp/positions.yaml
+      scrape_configs:
+        - job_name: varlogs
+          static_configs:
+            - targets: [localhost]
+              labels:
+                job: varlogs
+                __path__: /var/log/*log
+        - job_name: integrations/docker
+          docker_sd_configs:
+            - host: unix:///var/run/docker.sock
+              refresh_interval: 5s
+          relabel_configs:
+            - action: replace
+              replacement: integrations/docker
+              target_label: job
+            - action: replace
+              replacement: '<kroki-instance>' # must match instance used in cadvisor
+              target_label: instance
+            - source_labels:
+                - __meta_docker_container_name
+              regex: '/(.*)'
+              target_label: container
+            - source_labels:
+                - __meta_docker_container_log_stream
+              target_label: stream
+      clients:
+        - url: "https://<loki-instance>.grafana.net/api/prom/push"
+          basic_auth:
+            username: '<username>'
+            password: '<password>'