配置指南

# The global blacklist for tracing and metrics
BlackList = ["netdev_hw", "metax_gpu"]

# Log Configuration
#
# - Level
# The log level for huatuo-bamai: Debug, Info, Warn, Error, Panic.
# Default: Info
#
# - File
# Store logs to where the logging file is. If it is empty, don't write log
# to any file.
# Default: empty
#
[Log]
	# Level = "Info"
	# File = ""

# Runtime resource limit
#
# - LimitInitCPU
# During the huatuo-bamai startup, the CPU of process are restricted from use.
# Default is 0.5 CPU.
#
# - LimitCPU
# The CPU resource restricted once the process starts.
# Default is 2.0 CPU.
#
# - LimitMem
# The memory resource limitted for huatuo-bamai process.
# Default is 2048MB.
#
[RuntimeCgroup]
	# LimitInitCPU = 0.5
	# LimitCPU = 2.0
	# LimitMem = 2048

# Storage configuration
[Storage]
    # Elasticsearch Storage
    #
    # Disable ES storage if one of Address, Username, Password is empty.
    # Store the tracing and events data of linux kernel to ES.
    #
    # - Address
    # Default address is :9200 of localhost. Port 9200 is used for all API calls
    # over HTTP. This includes search and aggregations, monitoring and anything
    # else that uses a HTTP request. All client libraries will use this port to
    # talk to Elasticsearch
    # Default: :9200
    #
    # - Index
    # Elasticsearch index, a logical namespace that holds a collection of
    # documents for huatuo-bamai.
    # Default: huatuo_bamai
    #
    # - Username
    # - Password
    # There is no default username and password.
    #
    [Storage.ES]
        # Address = "http://127.0.0.1:9200"
        # Index = "huatuo_bamai"
        Username = "elastic"
        Password = "huatuo-bamai"

# LocalFile Storage
#
# Store data to local directory for troubleshooting on the host machine.
#
# - Path
# The directory for storing data. If the Path is empty, LocalFile will be disabled.
# Default: "huatuo-local"
#
# - RotationSize
# The maximum size in Megabytes of a record file before it gets rotated
# for per linux kernel tracer.
# Default: 100MB
#
# - MaxRotation
# The maximum number of old log files to retain for per tracer.
# Default: 10
#
[Storage.LocalFile]
	# Path = "huatuo-local"
	# RotationSize = 100
	# MaxRotation = 10

# Autotracing configuration 
[AutoTracing]
    # cpuidle
    #
    # For a high cpu usage all of a sudden in containers.
    #
    # - UserThreshold
    # User CPU usage threshold, when cpu usage reaches this threshold, cpu
    # performance tracing will be triggered.
    # Default: 75%
    #
    # - SysThreshold
    # System CPU usage threshold, when reaching this threshold, cpu performance
    # tracing will be triggered.
    # Default: 45%
    #
    # - UsageThreshold
    # The total cpu usage (system + user cpu usage) threshold, when reaching
    # this threshold, cpu performance tracing will be triggered.
    # Default: 45%
    #
    # - DeltaUserThreshold
    # The range of this user cpu changes within a short period of time.
    # Default: 45%
    #
    # - DeltaSysThreshold
    # The range of this system cpu changes within a short period of time.
    # Default: 20%
    #
    # - DeltaUsageThreshold
    # The range of this cpu usage changes within a short period of time.
    # Default: 55%
    #
    # - Interval
    # The sample interval of the cpu usage for all containers.
    # Default: 10s
    #
    # - IntervalTracing
    # Time since last run. Avoid frequently executing this tracing to prevent
    # damage to the system.
    # Default: 1800s
    #
    # - RunTracingToolTimeout
    # The executing time of this tracing program.
    # Default: 10s
    # 
    # NOTE:
    # Running this performance tool, when:
    # 1. UserThreshold and DeltaUserThreshold are true, or
    # 2. SysThreshold and DeltaSysThreshold are true, or
    # 3. UsageThreshold and DeltaUsageThreshold
    #
    [AutoTracing.CPUIdle]
        # UserThreshold = 75
        # SysThreshold = 45
        # UsageThreshold = 90
        # DeltaUserThreshold = 45
        # DeltaSysThreshold = 20
        # DeltaUsageThreshold = 55
        # Interval = 10
        # IntervalTracing = 1800
        # RunTracingToolTimeout = 10

# cpusys
#
# For a high system cpu usage all of a sudden on host machine.
#
# - SysThreshold
# System CPU usage threshold, when reaching this threshold, cpu performance
# tracing will be triggered.
# Default: 45%
#
# - DeltaSysThreshold
# The range of system cpu changes within a short period of time.
# Default: 20%
#
# - Interval
# The sample interval of the cpu usage for host machine.
# Default: 10s
#
# - RunTracingToolTimeout
# The executing time of this tracing program.
# Default: 10s
#
# NOTE:
# Running this performance tool, when:
# SysThreshold and DeltaSysThreshold are true.
#
[AutoTracing.CPUSys]
	# SysThreshold = 45
	# DeltaSysThreshold = 20
	# Interval = 10
	# RunTracingToolTimeout = 10

# dload
#
# linux tasks D state profiling for containers.
#
# - ThresholdLoad
# The loadavg threshold value, when reaching this threshold, dload profiling
# is triggered.
# Defalut: 5
#
# - Interval
# The sample interval of the load for all containers.
# Default: 10s
#
# - IntervalTracing
# Time since last run. Avoid frequently executing this tracing to prevent
# damage to the system.
# Default: 1800s
#
[AutoTracing.Dload]
	# ThresholdLoad = 5
	# Interval = 10
	# IntervalTracing = 1800

# iotracing
#
# io profiling for containers.
#
# - WbpsThreshold
# Max write bytes per second, when reaching this threshold, iotracing is triggered.
# Please note that if it is an NVMe device, it must also meet the UtilThreshold.
# Defalut: 1500 MB/s
#
# - RbpsThreshold
# Max read bytes per second, when reaching this threshold, iotracing is triggered.
# Please note that if it is an NVMe device, it must also meet the UtilThreshold.
# Defalut: 2000 MB/s
#
# - UtilThreshold
# Disk utilization, Percentage of time the disk is busy. If this is consistently
# above 80-90%, the disk may be a bottleneck.
# Defalut: 90%
#
# - AwaitThreshold
# Await (Average IO wait time in ms): High values indicate slow disk response times.
# Defalut: 100ms
#
# - RunTracingToolTimeout
# The executing time of this tracing tool.
# Default: 10s
#
# - MaxProcDump
# The number of processes displayed by iotracing tool.
# Defalut: 10
#
# - MaxFilesPerProcDump
# The number of files per process displayed by iotracing tool.
# Defalut: 5
#
[AutoTracing.IOTracing]
	# WbpsThreshold = 1500
	# RbpsThreshold = 2000
	# UtilThreshold = 90
	# AwaitThreshold = 100
	# RunTracingToolTimeout = 10
	# MaxProcDump = 10
	# MaxFilesPerProcDump = 5

# memory burst
#
# If there is a memory used burst on the host, capture this kernel context.
#
# - Interval
# The sample interval of the memory used.
# Default: 10s
#
# - DeltaMemoryBurst
# A certain percentage of memory burst used. 100% that means, e.g.,
# memory used increased from 200MB to 400MB.
# Default: 100%
#
# - DeltaAnonThreshold
# A certain percentage of anon memory burst used. 100% that means, e.g.,
# anon memory used increased from 200MB to 400MB.
# Default: 70%
#
# - IntervalTracing
# Time since last run. Avoid frequently executing this tracing
# to prevent damage to the system.
# Default: 1800s
#
# - DumpProcessMaxNum
# How many processes to dump when this event is triggered.
# Default: 10
#
[AutoTracing.MemoryBurst]
	# DeltaMemoryBurst = 100
	# DeltaAnonThreshold = 70
	# Interval = 10
	# IntervalTracing = 1800
	# SlidingWindowLength = 60
	# DumpProcessMaxNum = 10

# linux kernel events capturing configuration
[EventTracing]
	# softirq
	#
	# tracing the softirq disabled events of linux kernel.
	#
	# - DisabledThreshold
	# When the disable duration of softirq exceeds the threshold, huatuo-bamai
	# will collect kernel context.
	# Defalut: 10000000 in nanoseconds, 10ms
	#
	[EventTracing.Softirq]
		# DisabledThreshold = 10000000

# memreclaim
#
# The memory reclaim may block the process, if one process is blocked
# for a long time, reporting the events to userspace.
#
# - BlockedThreshold
# The blocked time when memory reclaiming.
# Default: 900000000ns, 900ms
#
[EventTracing.MemoryReclaim]
	# BlockedThreshold = 900000000

# networking rx latency
#
# linux net stack rx latency for every tcp skbs.
#
# - Driver2NetRx
# The latency from driver to net rx, e.g., netif_receive_skb.
# Default: 5ms
#
# - Driver2TCP
# The latency from driver to tcp rx, e.g., tcp_v4_rcv.
# Default: 10ms
#
# - Driver2Userspace
# The latency from driver to userspace copy data, e.g., skb_copy_datagram_iovec.
# Default: 115ms
#
# - ExcludedContainerQos
# Don't care the containers which qos level is in ExcludedContainerQos.
# This is a string slice in vendor/k8s.io/api/core/v1/types.go
# - PodQOSGuaranteed = "Guaranteed"
# - PodQOSBurstable = "Burstable"
# - PodQOSBestEffort = "BestEffort"
#
# Default: []
#
# - ExcludedHostNetnamespace
# Don't care the skbs, packets in the host net namespace.
# Default: true
#
[EventTracing.NetRxLatency]
	# Driver2NetRx = 5
	# Driver2TCP = 10
	# Driver2Userspace = 115
	# ExcludedContainerQos = []
	ExcludedContainerQos = ["bestEffort"]
	# ExcludedHostNetnamespace = true

# netdev events
#
# monitor the net device events.
#
# - DeviceList
# The net devices we take care of.
# Default: [] is empty, meaning no devices.
#
[EventTracing.Netdev]
	DeviceList = ["eth0", "eth1", "bond4", "lo"]

# dropwatch
#
# monitor packets dropped events in the Linux kernel.
#
# - ExcludedNeighInvalidate
# Don't care of neigh_invalidate drop events.
# Default: true
#
[EventTracing.Dropwatch]
	# ExcludedNeighInvalidate = true

# Metric Collector
[MetricCollector]
	# Netdev statistic
	#
	# - EnableNetlink
	# Use netlink instead of procfs net/dev to get netdev statistic.
	# Only support the host environment to use `netlink` now.
	# Default is "false".
	#
	# - DeviceIncluded
	# Accept special devices in netdev statistic.
	# Default: [] is empty, meaning include all.
	#
	# - DeviceExcluded
	# Exclude special devices in netdev statistic. 'DeviceExcluded' has higher
	# priority than 'DeviceIncluded'.
	# Default: [] is empty, meaning ignore nothing.
	#
	[MetricCollector.NetdevStats]
		# EnableNetlink = false
		# DeviceIncluded = ""
		DeviceExcluded = "^(lo)|(docker\\w*)|(veth\\w*)$"

# netdev dcb, DCB (Data Center Bridging)
#
# Collecting the DCB PFC (Priority-based Flow Control).
#
# - DeviceList
# The net devices we take care of.
# Default: [] is empty, meaning no devices.
#
[MetricCollector.NetdevDCB]
	DeviceList = ["eth0", "eth1"]

# netdev hardware statistic
#
# Collecting the hardware statistic of net devices, e.g, rx_dropped.
#
# - DeviceList
# The net devices we take care of.
# Default: [] is empty, meaning no devices.
#
[MetricCollector.NetdevHW]
	DeviceList = ["eth0", "eth1"]

# Qdisc
#
# - DeviceIncluded
# - DeviceExcluded same as above.
#
[MetricCollector.Qdisc]
	# DeviceIncluded = ""
	DeviceExcluded = "^(lo)|(docker\\w*)|(veth\\w*)$"

# vmstat
#
# This metric supports host vmstat and cgroup vmstat.
# - IncludedOnHost
# - ExcludedOnHost same as above, for the host /proc/vmstat.
#
# - IncludedOnContainer
# - ExcludedOnContainer as above, for the cgroup, containers memory.stat.
#
[MetricCollector.Vmstat]
	IncludedOnHost = "allocstall|nr_active_anon|nr_active_file|nr_boost_pages|nr_dirty|nr_free_pages|nr_inactive_anon|nr_inactive_file|nr_kswapd_boost|nr_mlock|nr_shmem|nr_slab_reclaimable|nr_slab_unreclaimable|nr_unevictable|nr_writeback|numa_pages_migrated|pgdeactivate|pgrefill|pgscan_direct|pgscan_kswapd|pgsteal_direct|pgsteal_kswapd"
	ExcludedOnHost = "total"
	IncludedOnContainer = "active_anon|active_file|dirty|inactive_anon|inactive_file|pgdeactivate|pgrefill|pgscan_direct|pgscan_kswapd|pgsteal_direct|pgsteal_kswapd|shmem|unevictable|writeback|pgscan_globaldirect|pgscan_globalkswapd|pgscan_cswapd|pgsteal_cswapd|pgsteal_globaldirect|pgsteal_globalkswapd"
	ExcludedOnContainer = "total"

# MemoryEvents/Netstat/MountPointStat
#
# - Included
# - Excluded same as above, DeviceInclude, DeviceExclude.
#
[MetricCollector.MemoryEvents]
	Included = "watermark_inc|watermark_dec"
	# Excluded = ""
[MetricCollector.Netstat]
	# Excluded = ""
	# Included = ""

# MountPointStat
[MetricCollector.MountPointStat]
	MountPointsIncluded = "(^/home$)|(^/$)|(^/boot$)"

# Pod Configuration
#
# Configure these parameters for fetching pods from kubelet.
#
# - KubeletReadOnlyPort
# The KubeletReadOnlyPort is kubelet read-only port for the Kubelet to serve on with
# no authentication/authorization. The port number must be between 1 and 65535, inclusive.
# Setting this field to 0 disables fetching pods from kubelet read-only service.
# Default: 10255
#
# - KubeletAuthorizedPort
# The port is the HTTPs port of the kubelet. The port number must be between 1 and 65535,
# inclusive. Setting this field to 0 disables fetching pods from kubelet HTTPS port.
# Default: 10250
#
# - KubeletClientCertPath
# https://kubernetes.io/docs/setup/best-practices/certificates/
#
# Client certificate and private key file name. One file or two files:
# "/path/to/xxx-kubelet-client.crt,/path/to/xxx-kubelet-client.key",
# "/path/to/kubelet-client-current.pem"
#
# You can disable this kubelet fetching pods, for bare metal service, by
# KubeletReadOnlyPort = 0, and KubeletAuthorizedPort = 0.
#
[Pod]
	KubeletClientCertPath = "/etc/kubernetes/pki/apiserver-kubelet-client.crt,/etc/kubernetes/pki/apiserver-kubelet-client.key"