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。
Loki 插件允许用户将日志发送到 Loki 进行聚合和查询,从而利用 Loki 高效的存储能力。
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,从而实现虚拟资源的高效监控和管理。它与 vSphere API 接口,收集关于集群、主机、资源池、虚拟机、数据存储和 vSAN 实体统计信息,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,该插件使用户能够深入了解资源分配、故障排除以及确保最佳系统性能,从而促进明智的决策。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。
Loki
此 Loki 插件与 Grafana Loki 集成,Grafana Loki 是一个强大的日志聚合系统。通过以与 Loki 兼容的格式发送日志,此插件可以高效地存储和查询日志。每个日志条目都以键值格式结构化,其中键表示字段名称,值表示相应的日志信息。按时间戳对日志进行排序可确保通过 Loki 查询时,日志流保持时间顺序。此插件对密钥的支持使安全管理身份验证参数变得更加容易,而 HTTP 标头、gzip 编码和 TLS 配置选项增强了日志传输的适应性和安全性,从而满足各种部署需求。
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 = ""
Loki
[[outputs.loki]]
## The domain of Loki
domain = "https://loki.domain.tld"
## Endpoint to write api
# endpoint = "/loki/api/v1/push"
## Connection timeout, defaults to "5s" if not set.
# timeout = "5s"
## Basic auth credential
# username = "loki"
# password = "pass"
## Additional HTTP headers
# http_headers = {"X-Scope-OrgID" = "1"}
## If the request must be gzip encoded
# gzip_request = false
## Optional TLS Config
# tls_ca = "/etc/telegraf/ca.pem"
# tls_cert = "/etc/telegraf/cert.pem"
# tls_key = "/etc/telegraf/key.pem"
## Sanitize Tag Names
## If true, all tag names will have invalid characters replaced with
## underscores that do not match the regex: ^[a-zA-Z_:][a-zA-Z0-9_:]*.
# sanitize_label_names = false
## Metric Name Label
## Label to use for the metric name to when sending metrics. If set to an
## empty string, this will not add the label. This is NOT suggested as there
## is no way to differentiate between multiple metrics.
# metric_name_label = "__name"
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。此场景可能涉及根据从 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,从而避免中断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通知。例如,如果主机上的 CPU 使用率超过指定阈值,则可能会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:使用收集的指标来比较不同 vCenter 中集群的性能。此基准测试提供了关于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。
Loki
-
微服务集中式日志记录:利用 Loki 插件收集 Kubernetes 集群中运行的多个微服务的日志。通过将日志定向到集中式 Loki 实例,开发人员可以在一个位置监控、搜索和分析来自所有服务的日志,从而更轻松地进行故障排除和性能监控。此设置简化了操作,并支持对分布式应用程序中的问题进行快速响应。
-
实时日志异常检测:将 Loki 与监控工具结合使用,实时分析日志输出中可能指示系统错误或安全威胁的异常模式。在日志流上实施异常检测使团队能够主动识别和响应事件,从而提高系统可靠性并增强安全态势。
-
通过 Gzip 压缩增强日志处理:配置 Loki 插件以利用 gzip 压缩进行日志传输。这种方法可以减少带宽使用并提高传输速度,在网络带宽可能受限的环境中尤其有利。它对于高容量日志记录应用程序尤其有用,在这些应用程序中,每个字节都很重要,并且性能至关重要。
-
通过自定义标头支持多租户:利用添加自定义 HTTP 标头的功能,在多租户应用程序环境中隔离来自不同租户的日志。通过使用 Loki 插件为每个租户发送不同的标头,运营商可以确保正确的日志管理并符合数据隔离要求,使其成为 SaaS 应用程序的通用解决方案。
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。