目录
输入和输出集成概述
VMware vSphere Telegraf 插件提供了一种从 VMware vCenter 服务器收集指标的方法,从而可以全面监控和管理 vSphere 环境中的虚拟资源。
此插件允许使用 Metrics API 将指标发送到 New Relic Insights,从而实现对应用程序性能的有效监控和分析。
集成详情
VMware vSphere
此插件连接到 VMware vSphere 服务器,以收集来自虚拟环境的各种指标,从而实现对虚拟资源的高效监控和管理。它与 vSphere API 交互,以收集有关集群、主机、资源池、虚拟机、数据存储和 vSAN 实体的信息统计数据,并以适合分析和可视化的格式呈现。该插件对于管理基于 VMware 的基础设施的管理员尤其有价值,因为它有助于实时跟踪系统性能、资源使用情况和操作问题。通过聚合来自多个来源的数据,该插件使用户能够获得洞察力,从而促进有关资源分配、故障排除和确保最佳系统性能的明智决策。此外,对密钥存储集成的支持允许安全处理敏感凭据,从而促进安全和合规性评估方面的最佳实践。
New Relic
此插件利用 Metrics API 将指标写入 New Relic Insights,Metrics API 提供了一种强大的机制,用于将时间序列数据发送到 New Relic 平台。用户必须首先获取 Insights API 密钥才能验证和授权其数据提交。该插件旨在促进与 New Relic 的监控和分析功能轻松集成,支持各种指标类型并允许高效的数据处理。核心功能包括能够为指标添加前缀以更好地识别、API 请求的可自定义超时以及对代理设置的支持以增强连接性。用户必须根据自己的要求配置这些选项,以实现数据无缝流入 New Relic,从而进行全面的实时分析和洞察。
配置
VMware vSphere
[[inputs.vsphere]]
vcenters = [ "https://vcenter.local/sdk" ]
username = "[email protected]"
password = "secret"
vm_metric_include = [
"cpu.demand.average",
"cpu.idle.summation",
"cpu.latency.average",
"cpu.readiness.average",
"cpu.ready.summation",
"cpu.run.summation",
"cpu.usagemhz.average",
"cpu.used.summation",
"cpu.wait.summation",
"mem.active.average",
"mem.granted.average",
"mem.latency.average",
"mem.swapin.average",
"mem.swapinRate.average",
"mem.swapout.average",
"mem.swapoutRate.average",
"mem.usage.average",
"mem.vmmemctl.average",
"net.bytesRx.average",
"net.bytesTx.average",
"net.droppedRx.summation",
"net.droppedTx.summation",
"net.usage.average",
"power.power.average",
"virtualDisk.numberReadAveraged.average",
"virtualDisk.numberWriteAveraged.average",
"virtualDisk.read.average",
"virtualDisk.readOIO.latest",
"virtualDisk.throughput.usage.average",
"virtualDisk.totalReadLatency.average",
"virtualDisk.totalWriteLatency.average",
"virtualDisk.write.average",
"virtualDisk.writeOIO.latest",
"sys.uptime.latest",
]
host_metric_include = [
"cpu.coreUtilization.average",
"cpu.costop.summation",
"cpu.demand.average",
"cpu.idle.summation",
"cpu.latency.average",
"cpu.readiness.average",
"cpu.ready.summation",
"cpu.swapwait.summation",
"cpu.usage.average",
"cpu.usagemhz.average",
"cpu.used.summation",
"cpu.utilization.average",
"cpu.wait.summation",
"disk.deviceReadLatency.average",
"disk.deviceWriteLatency.average",
"disk.kernelReadLatency.average",
"disk.kernelWriteLatency.average",
"disk.numberReadAveraged.average",
"disk.numberWriteAveraged.average",
"disk.read.average",
"disk.totalReadLatency.average",
"disk.totalWriteLatency.average",
"disk.write.average",
"mem.active.average",
"mem.latency.average",
"mem.state.latest",
"mem.swapin.average",
"mem.swapinRate.average",
"mem.swapout.average",
"mem.swapoutRate.average",
"mem.totalCapacity.average",
"mem.usage.average",
"mem.vmmemctl.average",
"net.bytesRx.average",
"net.bytesTx.average",
"net.droppedRx.summation",
"net.droppedTx.summation",
"net.errorsRx.summation",
"net.errorsTx.summation",
"net.usage.average",
"power.power.average",
"storageAdapter.numberReadAveraged.average",
"storageAdapter.numberWriteAveraged.average",
"storageAdapter.read.average",
"storageAdapter.write.average",
"sys.uptime.latest",
]
datacenter_metric_include = [] ## if omitted or empty, all metrics are collected
datacenter_metric_exclude = [ "*" ] ## Datacenters are not collected by default.
vsan_metric_include = [] ## if omitted or empty, all metrics are collected
vsan_metric_exclude = [ "*" ] ## vSAN are not collected by default.
separator = "_"
max_query_objects = 256
max_query_metrics = 256
collect_concurrency = 1
discover_concurrency = 1
object_discovery_interval = "300s"
timeout = "60s"
use_int_samples = true
custom_attribute_include = []
custom_attribute_exclude = ["*"]
metric_lookback = 3
ssl_ca = "/path/to/cafile"
ssl_cert = "/path/to/certfile"
ssl_key = "/path/to/keyfile"
insecure_skip_verify = false
historical_interval = "5m"
disconnected_servers_behavior = "error"
use_system_proxy = true
http_proxy_url = ""
New Relic
[[outputs.newrelic]]
## The 'insights_key' parameter requires a NR license key.
## New Relic recommends you create one
## with a convenient name such as TELEGRAF_INSERT_KEY.
## reference: https://docs.newrelic.com/docs/apis/intro-apis/new-relic-api-keys/#ingest-license-key
# insights_key = "New Relic License Key Here"
## Prefix to add to add to metric name for easy identification.
## This is very useful if your metric names are ambiguous.
# metric_prefix = ""
## Timeout for writes to the New Relic API.
# timeout = "15s"
## HTTP Proxy override. If unset use values from the standard
## proxy environment variables to determine proxy, if any.
# http_proxy = "http://corporate.proxy:3128"
## Metric URL override to enable geographic location endpoints.
# If not set use values from the standard
# metric_url = "https://metric-api.newrelic.com/metric/v1"
输入和输出集成示例
VMware vSphere
-
动态资源分配:利用此插件监控虚拟机群的资源使用情况,并根据性能指标自动调整资源分配。这种情况可能涉及根据从 vSphere API 收集的 CPU 和内存使用率指标实时触发扩展操作,从而确保最佳性能和成本效益。
-
容量规划和预测:利用从 vSphere 收集的历史指标进行容量规划。分析 CPU、内存和存储使用率随时间变化的趋势,有助于管理员预测何时需要额外资源,从而避免停机并确保虚拟基础设施能够应对增长。
-
自动化警报和事件响应:将此插件与警报工具集成,以根据收集的指标设置自动化通知。例如,如果主机上的 CPU 使用率超过指定阈值,则可以触发警报并自动启动预定义的补救步骤,例如将虚拟机迁移到利用率较低的主机。
-
跨集群的性能基准测试:使用收集的指标比较不同 vCenter 中集群的性能。此基准测试提供了有关哪些集群配置产生最佳资源效率的见解,并可以指导未来的基础设施增强。
New Relic
-
应用程序性能监控:使用 New Relic Telegraf 插件将 Web 服务的应用程序性能指标发送到 New Relic Insights。通过集成此插件,开发人员可以收集响应时间、错误率和吞吐量等数据,使团队能够实时监控应用程序健康状况,并在问题影响用户之前快速解决问题。此设置促进了应用程序性能和用户体验的主动管理。
-
基础设施指标聚合:利用此插件聚合和发送来自各种服务器的系统级指标(CPU 使用率、内存消耗等)到 New Relic。这有助于系统管理员维护基础设施性能的全面视图,从而促进容量规划并识别潜在瓶颈。通过将指标集中在 New Relic 中,团队可以可视化随时间变化的趋势,并就资源分配做出明智的决策。
-
多租户应用程序的动态指标命名:使用 metric_prefix 选项实现动态前缀,以区分多租户应用程序中的不同租户。通过配置插件以在指标名称中包含每个租户的唯一标识符,团队可以分析每个租户的使用模式和性能指标。这提供了对租户行为的宝贵见解,支持定制优化并提高不同客户群的服务质量。
-
实时异常检测:将 New Relic 插件与警报机制结合使用,以根据异常指标模式触发通知。通过发送请求计数和响应时间等指标,团队可以在 New Relic 中设置阈值,当阈值被突破时,将自动提醒相关方。这种用户驱动的方法支持对潜在问题做出即时响应,防止问题升级为更大的事件。
反馈
感谢您成为我们社区的一份子!如果您有任何一般性反馈或在这些页面上发现任何错误,我们欢迎并鼓励您提出意见。请在 InfluxDB 社区 Slack 中提交您的反馈。