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,从而可以对 vSphere 环境中的虚拟资源进行全面监控和管理。
Telegraf 的 SQL 输出插件通过为每种指标类型动态创建表,将指标存储在 SQL 数据库中。当配置为 SQLite 时,它使用基于文件的 DSN 和为轻量级嵌入式数据库使用量身定制的最小 SQL 模式。
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,收集关于集群、主机、资源池、虚拟机、数据存储和 vSAN 实体的信息,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,该插件使用户能够获得洞察力,从而有助于就资源分配、故障排除和确保最佳系统性能做出明智的决策。此外,对 secret-store 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。
SQLite
SQL 输出插件使用动态模式将 Telegraf 指标写入 SQL 数据库,其中每种指标类型对应一个表。对于 SQLite,该插件使用 modernc.org/sqlite 驱动程序,并且需要文件 URI 格式的 DSN(例如,“file:/path/to/telegraf.db?cache=shared”)。此配置利用标准 ANSI SQL 进行表创建和数据插入,确保与 SQLite 的功能兼容。
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 = ""
SQLite
[[outputs.sql]]
## Database driver
## Valid options: mssql (Microsoft SQL Server), mysql (MySQL), pgx (Postgres),
## sqlite (SQLite3), snowflake (snowflake.com), clickhouse (ClickHouse)
driver = "sqlite"
## Data source name
## For SQLite, the DSN is a filename or URL with the scheme "file:".
## Example: "file:/path/to/telegraf.db?cache=shared"
data_source_name = "file:/path/to/telegraf.db?cache=shared"
## Timestamp column name
timestamp_column = "timestamp"
## Table creation template
## Available template variables:
## {TABLE} - table name as a quoted identifier
## {TABLELITERAL} - table name as a quoted string literal
## {COLUMNS} - column definitions (list of quoted identifiers and types)
table_template = "CREATE TABLE {TABLE} ({COLUMNS})"
## Table existence check template
## Available template variables:
## {TABLE} - table name as a quoted identifier
table_exists_template = "SELECT 1 FROM {TABLE} LIMIT 1"
## Initialization SQL (optional)
init_sql = ""
## Maximum amount of time a connection may be idle. "0s" means connections are never closed due to idle time.
connection_max_idle_time = "0s"
## Maximum amount of time a connection may be reused. "0s" means connections are never closed due to age.
connection_max_lifetime = "0s"
## Maximum number of connections in the idle connection pool. 0 means unlimited.
connection_max_idle = 2
## Maximum number of open connections to the database. 0 means unlimited.
connection_max_open = 0
## Metric type to SQL type conversion
## The values on the left are the data types Telegraf has and the values on the right are the SQL types used when writing to SQLite.
#[outputs.sql.convert]
# integer = "INT"
# real = "DOUBLE"
# text = "TEXT"
# timestamp = "TIMESTAMP"
# defaultvalue = "TEXT"
# unsigned = "UNSIGNED"
# bool = "BOOL"
输入和输出集成示例
VMware vSphere
-
动态资源分配:使用此插件来监控 VM 集群的资源使用情况,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、内存和存储使用情况随时间变化的趋势,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 VM 迁移到利用率较低的主机。
-
跨集群性能基准测试: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。
SQLite
- 本地监控存储:配置插件以将指标写入本地 SQLite 数据库文件。这非常适合不需要设置全规模数据库服务器的轻量级部署。
- 嵌入式应用:使用 SQLite 作为嵌入在边缘设备中的应用程序的后端,受益于其基于文件的架构和最低资源需求。
- 快速设置进行测试:利用 SQLite 的易用性来快速设置 Telegraf 指标收集的测试环境,而无需外部数据库服务。
- 自定义模式管理:如果您需要特定的列类型或索引,请调整表创建模板以预定义您的模式,从而确保与您的应用程序需求兼容。
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了任何错误,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。