BYPASS SHELL BY ./RAZORGANZ
Server: nginx/1.20.1
System: Linux iZdzfnv9mwfppeZ 5.10.134-19.2.al8.x86_64 #1 SMP Wed Oct 29 22:47:09 CST 2025 x86_64
User: apache (48)
PHP: 8.2.30
Disabled: NONE
Upload Files
File: //etc/sysak/lingjun.yaml
config:
  freq: 30 # unit second
  port: 8405 # bind port
  bind_addr: 0.0.0.0 # bind ip
  backlog: 32 # listen backlog
  # daemon: true
  # url_safe: close
  identity:   # support hostip, curl(need url arg), hostname, file(need path arg), specify(need name arg)
    #    mode: curl
    #    url: "http://100.100.100.200/latest/meta-data/instance-id"
    #    name: test_specify
    mode: hostip
  #  real_timestamps: true
  #  unix_socket: "/tmp/sysom_unity.sock"
  proc_path: / # in container mode, like -v /:/mnt/host , should use /mnt/host/
  db:
    rotate: 7 # tsdb file retention time, unit day
    budget: 200 # max query buffer from tsdb.
  limit:
    cpu: 300 # unit %
    mem: 500 # unit mb
    tasks: 10 # monitor 10 pid max.
    cellLimit: -1 # set guard limit time. guard time is unlimit when cellLimit is -1,default is 50(ms)

# forkRun:
#   - cmd: "../../../ioMonitor"
#     args:
#       ["-y", "/etc/sysak/base.yaml", "-s", "await=5,iops=1000,diagIolat=on"]
# #  - cmd: "../../../prof/app/run.sh"
# #    args:
# #      []

# cec: "http://localhost"

outline:
  - /var/sysom/outline

container:
  mode: "pods"
  runtime: ["cri_containerd"]
  nsBlacklist: ["kube-system", "arms-prom", "kube-public", "kube-node-lease", "logging", "sls-monitoring"]
  podPlugin: ["cg_pmu_events"]

# # cgroupv2:
# #   directPaths: ["kubepods/besteffort", "kubepods.slice/kubepods-besteffort.slices"]
# #   luaPlugin: ["cg_sched_cfs_stat_v2","cg_cpu_stat_v2"]

# luaPlugins: ["proc_buddyinfo", "proc_diskstats", "proc_meminfo", "proc_mounts", "proc_netdev",
#              "proc_snmp_stat", "proc_sockstat", "proc_stat", "proc_statm", "proc_vmstat",
#              "proc_uptime", "proc_arp", "proc_cgroups", "proc_softirqs", "proc_softnet_stat",
#              "proc_fd"]

resctrl:
  path: "sys/fs/resctrl"
  monLuaPlugin: ["rdt_llc_occupancy", "rdt_local_mem_bw", "rdt_total_mem_bw"]
  resLuaPlugin: ["rdt_size"]
  auto: true # search all mon-groups and res-group, it will ignore config arg group

#   # group:
#   #   - name: ""
#   #   - name: "LS"
#   #     # monitor: ["mon1", "mon2"]
#   #   - name: "BE"
#   #     monitor: ["pod3#con3"]

luaPlugins:
  [
    "proc_buddyinfo",
    "proc_diskstats",
    "proc_meminfo",
    "proc_snmp_stat",
    "proc_sockstat",
    "proc_stat",
    "proc_statm",
    "proc_vmstat",
    "proc_uptime",
    "proc_arp",
    "proc_cgroups",
    "proc_netdev",
    "vscagent",
    "sys_hugepages"
  ]

plugins:
  # - so: kmsg
  #   description: "collect dmesg info."
  # -
  #   so: proc_schedstat
  #   description: "collect schedule stat info of percpu"
  - so: proc_loadavg
    description: "collect load avg"
  - so: net_health
    description: "tcp net health."
  - so: net_retrans
    description: "tcp retrans monitor."
  # - so: unity_nosched
  #   description: "nosched:sys hold cpu and didn't scheduling"
  # irqoff may eat up the perf_event_fd ,so pmu_events will fail;
  # so we close it temporarily
  #  - so: unity_irqoff
  #    description: "irqoff:detect irq turned off and can't response"
  # - so: gpuinfo
  #   description: "collect gpuinfo"
  - so: uncore_imc
    description: "IMC latency and bandwidth"
  # - so: pmu_events
  #   description: "collect pmu events"
  # - so: cpufreq
  #   description: "collect cpu frequence of perf cpu"
  - so: cpudist
    description: "sched delay"
  # - so: numainfo
  #   description: "numainfo"
  - so: agent_version
    description: "sysom agent version"
  # - so: ntopo
  #   description: "collect network topology."
  # - so: sql-obs
  #   description: "collect db observ."

metrics:
  # - title: sysom_java_app
  #   from: sysom_java_app
  #   head: value
  #   help: "java application observe."
  #   type: "gauge"
  # - title: sysom_observe
  #   from: observe
  #   head: value
  #   help: "application observe."
  #   type: "gauge"
  - title: sysom_proc_cpu_total
    from: cpu_total
    head: mode
    help: "cpu usage info for total."
    type: "gauge"
    discrete: true # datas are discrete.default is false
  # - title: sysom_proc_cpus
  #   from: cpus
  #   head: mode
  #   help: "cpu usage info for per-cpu."
  #   type: "gauge"
  - title: sysom_proc_sirq
    from: sirq
    head: type
    help: "system soft irq times."
    type: "gauge"
  - title: sysom_proc_stat_counters
    from: stat_counters
    head: counter
    help: "system state counter."
    type: "gauge"
  - title: sysom_proc_meminfo
    from: meminfo
    head: value
    help: "meminfo from /proc/meminfo."
    type: "gauge"
  - title: sysom_proc_vmstat
    from: vmstat
    head: value
    help: "vmstat info from /proc/vmstat."
    type: "gauge"
  - title: sysom_proc_self_statm
    from: self_statm
    head: value
    help: "statm info from /proc/self/statm."
    type: "gauge"
  - title: sysom_proc_networks
    from: networks
    head: counter
    help: "networks info from /proc/net/dev."
    type: "gauge"
  - title: sysom_proc_disks
    from: disks
    head: counter
    help: "disk info from /proc/diskstats."
    type: "gauge"
  - title: sysom_proc_pkt_status
    from: pkt_status
    head: counter
    help: "net status info from /proc/net/snmp and /proc/net/status."
    type: "gauge"
  # - title: sysom_fs_stat
  #   from: fs_stat
  #   head: counter
  #   help: "file system information."
  #   type: "gauge"
  - title: sysom_file_descriptor
    from: procfd
    head: type
    help: "used file descriptor number."
    type: "gauge"
  - title: sysom_sock_stat
    from: sock_stat
    head: value
    help: "sock stat counters from /proc/net/sockstat"
    type: "gauge"
  # - title: sysom_proc_schedstat
  #   from: proc_schedstat
  #   head: value
  #   help: "schedule state of percpu."
  #   type: "gauge"
  - title: sysom_proc_loadavg
    from: proc_loadavg
    head: value
    help: "loadavg of system from /proc/loadavg"
    type: "gauge"
  - title: sysom_proc_buddyinfo
    from: buddyinfo
    head: value
    help: "buddyinfo of system from /proc/buddyinfo"
    type: "gauge"
  - title: sysom_sys_hugepages
    from: sys_hugepages
    head: type
    help: "sys_hugepages from /sys/kernel/mm/hugepages"
    type: "gauge"
  # - title: sysom_IOMonIndForDisksIO
  #   from: IOMonIndForDisksIO
  #   head: value
  #   help: "Disk IO indicators and abnormal events"
  #   type: "gauge"
  # - title: sysom_IOMonIndForSystemIO
  #   from: IOMonIndForSystemIO
  #   head: value
  #   help: "System indicators and abnormal events about IO"
  #   type: "gauge"
  # - title: sysom_IOMonDiagLog
  #   from: IOMonDiagLog
  #   head: value
  #   help: "Diagnose log for IO exception"
  #   type: "gauge"
  # - title: sched_moni_jitter
  #   from: sched_moni_jitter
  #   head: value
  #   help: "nosched/irqoff:sys and irqoff hold cpu and didn't scheduling"
  #   type: "gauge"
  - title: sysom_cpu_dist
    from: cpu_dist
    head: value
    help: "task cpu sched dist."
    type: "gauge"
  - title: sysom_net_health_hist
    from: net_health_hist
    head: value
    help: "net_health_hist"
    type: "gauge"
  - title: sysom_net_health_count
    from: net_health_count
    head: value
    help: "net_health_count"
    type: "gauge"
  - title: sysom_net_retrans_count
    from: net_retrans_count
    head: value
    help: "net_retrans_count"
    type: "gauge"
  # - title: sysom_gpuinfo
  #   from: gpuinfo
  #   head: value
  #   help: "gpuinfo of system from nvidia-smi"
  #   type: "gauge"
  - title: sysom_uname
    from: uname
    head: value
    help: "uname info"
    type: "gauge"
  - title: sysom_uptime
    from: uptime
    head: value
    help: "uptime from /proc/uptime"
    type: "gauge"
  - title: sysom_system_release
    from: system_release
    head: value
    help: "system_release from /etc/os-release"
    type: "gauge"
  - title: sysom_cgroups
    from: cgroups
    head: value
    help: "cgroup number."
    type: "gauge"
  # - title: sysom_per_sirqs
  #   from: per_sirqs
  #   head: value
  #   help: "per_sirqs."
  #   type: "gauge"
  # - title: sysom_softnets
  #   from: softnets
  #   head: value
  #   help: "cgroup number."
  #   type: "gauge"
  # - title: sysom_interrupts
  #   from: interrupts
  #   head: value
  #   help: "interrupts."
  #   type: "gauge"
  - title: sysom_net_ip_count
    from: net_ip_count
    head: value
    help: "net snmp net_ip_count"
    type: "gauge"
  - title: sysom_net_icmp_count
    from: net_icmp_count
    head: value
    help: "net snmp net_icmp_count"
    type: "gauge"
  - title: sysom_net_udp_count
    from: net_udp_count
    head: value
    help: "net snmp net_udp_count"
    type: "gauge"
  - title: sysom_net_tcp_count
    from: net_tcp_count
    head: value
    help: "net snmp net_tcp_count"
    type: "gauge"
  - title: sysom_net_tcp_ext_count
    from: net_tcp_ext_count
    head: value
    help: "net stat net_tcp_ext_count"
    type: "gauge"
  # - title: sysom_ntopo_node
  #   from: sysom_metrics_ntopo_node
  #   head: mode
  #   help: "net topology node"
  #   type: "gauge"
  # - title: sysom_ntopo_edge
  #   from: sysom_metrics_ntopo_edge
  #   head: mode
  #   help: "net topology edge"
  #   type: "gauge"
  # - title: sysom_obser_app_rt_ntopo
  #   from: sysom_metrics_ntopo_request
  #   head: value
  #   help: rt and req/resp bytes of apps
  #   type: "gauge"
  #   discrete: true
  # - title: sysom_obser_mysqld_os
  #   from: sysom_obser_metrics_mysqld_os
  #   head: value
  #   help: "os level metrics of mysqld"
  #   type: "gauge"
  # - title: sysom_obser_mysqld_process
  #   from: sysom_obser_metrics_mysqld_process
  #   head: value
  #   help: "process level metrics of mysqld"
  #   type: "gauge"
  # - title: sysom_obser_mysqld_innodb
  #   from: sysom_obser_metrics_mysqld_innodb
  #   head: value
  #   help: "innodb metrics of mysqld"
  #   type: "gauge"
  # - title: sysom_obser_mysqld_alarm
  #   from: sysom_obser_mysqld_alarm
  #   head: value
  #   help: "alarm on process exception of mysqld"
  #   type: "gauge"
  # - title: sysom_obser_os_alarm
  #   from: sysom_obser_os_alarm
  #   head: value
  #   help: "alarm on os exception of mysqld"
  #   type: "gauge"
  # - title: sysom_podmem
  #   from: podmem
  #   head: value
  #   help: "file cache for pod"
  #   type: "gauge"
  # - title: sysom_container_memfail_cnt
  #   from: cg_memfail_cnt
  #   head: value
  #   help: "sysom_container_memFail_cnt"
  #   type: "gauge"
  # - title: sysom_container_memory_oomcnt
  #   from: cg_memoom_cnt
  #   head: value
  #   help: "container oom event count"
  #   type: "counter"
  # - title: sysom_container_memUtil
  #   from: cg_memory_util
  #   head: value
  #   help: "sysom_container_memory_util"
  #   type: "gauge"
  # - title: sysom_container_memgdrcm_latency
  #   from: cgGlbDrcmLatency
  #   head: value
  #   help: "sysom global memory latency"
  #   type: "gauge"
  # - title: sysom_container_memdrcm_latency
  #   from: cg_memdrcm_latency
  #   head: value
  #   help: "sysom_container_memdrcm_latency"
  #   type: "gauge"
  # - title: sysom_container_memmcmp_latency
  #   from: cg_memmcmp_latency
  #   head: value
  #   help: "sysom_container_memmcmp_latency"
  #   type: "gauge"
  # - title: sysom_container_cpu_stat
  #   from: cg_cpu_stat
  #   head: value
  #   help: "sysom_container_cpu_stat"
  #   type: "gauge"
  # - title: sysom_container_cpuacct_stat
  #   from: cg_cpuacct_stat
  #   head: value
  #   help: "cpuacct/cpuacct.stat"
  #   type: "gauge"
  # - title: sysom_container_proc_stat
  #   from: cg_proc_stat
  #   head: value
  #   help: "container cpuacct proc stat"
  #   type: "gauge"
  # - title: sysom_container_cfs_quota
  #   from: cgCpuQuota
  #   head: value
  #   help: "cfs quota"
  #   type: "gauge"
  # - title: sysom_container_network_stat
  #   from: con_net_stat
  #   head: value
  #   help: "network stat of containers"
  #   type: "gauge"
  # - title: sysom_container_blkio_stat
  #   from: cg_blkio_stat
  #   head: value
  #   help: "io stat from blkio cgroup"
  #   type: "gauge"
  # - title: sysom_container_cpuacct_wait_latency
  #   from: cg_wait_latency
  #   head: value
  #   help: "wait_latency of cgroups"
  #   type: "gauge"
  - title: sysom_imc_channel_event
    from: imc_channel_event
    head: value
    help: "imc latency and bw for channels"
    type: "gauge"
    blacklist:
      type: ["^wlat"]
  - title: sysom_imc_socket_event
    from: imc_socket_event
    head: value
    help: "imc latency and bw for socket"
    type: "gauge"
    blacklist:
      type: ["^wlat"]
  - title: sysom_imc_node_event
    from: imc_node_event
    head: value
    help: "imc latency and bw for node"
    type: "gauge" 
    blacklist:
      type: ["^wlat"]
  - title: sysom_rdt_usage
    from: rdt_usage
    head: value
    help: "RDT LLC and memory bandwidth usage"
    type: "gauge"
  - title: sysom_rdt_alloc_policy
    from: rdt_alloc_policy
    head: value
    help: "RDT LLC and memory bandwidth allocation policy"
    type: "gauge"
  # - title: sysom_pmu_events
  #   from: pmu_events
  #   head: value
  #   help: "pmu events, such as  cycles/instructions, llc events"
  #   type: "gauge"
  # - title: sysom_pmu_events_percpu
  #   from: pmu_events_percpu
  #   head: value
  #   help: "pmu events of percpu"
  #   type: "gauge"
  # - title: sysom_imc_socket_latency
  #   from: imc_socket_latency
  #   head: value
  #   help: "imc socket level latency"
  #   type: "gauge"
  # - title: sysom_imc_channel_latency
  #   from: imc_channel_latency
  #   head: value
  #   help: "imc channel level latency"
  #   type: "gauge"
  # - title: sysom_cpu_freq
  #   from: cpufreq
  #   head: value
  #   help: "the frequence of percpu"
  #   type: "gauge"
  # - title: sysom_numainfo
  #   from: numainfo
  #   head: value
  #   help: "numainfo of system from /sys/devices/system/"
  #   type: "gauge"
  # - title: sysom_cg_sched_cfs_stat_v2
  #   from: cg_sched_cfs_stat_v2
  #   head: value
  #   help: "cgroupv2 cg_sched_cfs_stat_v2 info"
  #   type: "gauge"
  # - title: sysom_cg_cpu_stat_v2
  #   from: cg_cpu_stat_v2
  #   head: value
  #   help: "cgroupv2 cg_cpu_stat_v2 info"
  #   type: "gauge"
  # - title: sysom_container_cpuacct_block_lat
  #   from: cg_block_latency
  #   head: value
  #   help: "cpuacct_block of cgroups"
  #   type: "gauge"
  # - title: sysom_container_cpuacct_ioblock_lat
  #   from: cg_ioblock_latency
  #   head: value
  #   help: "cpuacct_ioblock of cgroups"
  #   type: "gauge"
  # - title: sysom_container_cfs_statis
  #   from: cfs_statistics
  #   head: value
  #   help: "cpuacct/cpuacct.sched_cfs_statistics"
  #   type: "gauge"
  - title: sysom_agent_version
    from: agent_version
    head: value
    help: "sysom agent version"
    type: "gauge"
  # - title: sysom_iolatency
  #   from: sysom_iolatency
  #   head: value
  #   help: "IO average processing latency information"
  #   type: "gauge"
  - title: sysom_vscagent
    from: vscagent
    head: counter
    help: "vscagent process counter."
    type: "gauge"
  - title: sysom_cg_pmu_events
    from: pmu_cg_events
    head: value
    help: "pmu events of cgroups"
    type: "gauge"

# observe:
#   comms:
#     java: "cgroup"
#     mysqld: "cgroup"
#   period: 20000