目录
强大的性能,无限的扩展能力
收集、组织和处理大量高速数据。 当您将任何数据视为时间序列数据时,它都会更有价值。 借助 InfluxDB,排名第一的时间序列平台,旨在与 Telegraf 一起扩展。
查看入门方法
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。
Telegraf 的 SQL 插件使用简单的表架构和动态列生成将收集的指标发送到 SQL 数据库。 当配置为 ClickHouse 时,它会调整 DSN 格式和类型转换设置,以确保无缝数据集成。
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。
Clickhouse
Telegraf 的 SQL 插件旨在通过基于传入指标动态创建表和列的方式将指标数据写入 SQL 数据库。 当配置为 ClickHouse 时,它使用 clickhouse-go v1.5.4 驱动程序,该驱动程序采用独特的 DSN 格式和一组专门的类型转换规则,以将 Telegraf 的数据类型直接映射到 ClickHouse 的原生类型。 这种方法确保了高吞吐量环境中的最佳存储和检索性能,使其非常适合实时分析和大规模数据仓库。 动态架构创建和精确的类型映射支持详细的时间序列数据日志记录,这对于监控现代分布式系统至关重要。
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 = ""
Clickhouse
[[outputs.sql]]
## Database driver
## Valid options include mssql, mysql, pgx, sqlite, snowflake, clickhouse
driver = "clickhouse"
## Data source name
## For ClickHouse, the DSN follows the clickhouse-go v1.5.4 format.
## Example DSN: "tcp://localhost:9000?debug=true"
data_source_name = "tcp://localhost:9000?debug=true"
## 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 for ClickHouse.
## The conversion maps Telegraf metric types to ClickHouse native data types.
[outputs.sql.convert]
conversion_style = "literal"
integer = "Int64"
text = "String"
timestamp = "DateTime"
defaultvalue = "String"
unsigned = "UInt64"
bool = "UInt8"
real = "Float64"
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。 此方案可能涉及根据从 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:使用收集的指标来比较不同 vCenter 中集群的性能。 此基准测试提供了有关哪些集群配置可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。
Clickhouse
-
用于高容量数据的实时分析:使用该插件将来自大规模系统的流式指标馈送到 ClickHouse。 此设置支持超快的查询性能和近乎实时的分析,非常适合监控高流量应用程序。
-
时间序列数据仓库:将插件与 ClickHouse 集成以创建强大的时间序列数据仓库。 此用例允许组织存储详细的历史指标,并执行复杂的查询以进行趋势分析和容量规划。
-
分布式环境中的可扩展监控:利用该插件在 ClickHouse 中为每种指标类型动态创建表,从而更轻松地管理和查询来自大量分布式系统的数据,而无需事先定义架构。
-
物联网部署的优化存储:部署该插件以将来自物联网传感器的数据摄取到 ClickHouse 中。 其高效的架构创建和原生类型映射有助于处理海量数据,从而实现实时监控和预测性维护。
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。
强大的性能,无限的扩展能力
收集、组织和处理大量高速数据。 当您将任何数据视为时间序列数据时,它都会更有价值。 借助 InfluxDB,排名第一的时间序列平台,旨在与 Telegraf 一起扩展。
查看入门方法