Add tidb example

collector/tidb/examples/compose/README.md

@@ -0,0 +1,45 @@
+# Monitor TiDB with the OpenTelemetry Collector for Cloud Observability
+
+## Overview
+
+TiDB is a distributed, scalable, and highly available NewSQL database. Monitoring TiDB is crucial to ensure its
+reliability, performance, and scalability. Utilizing the OpenTelemetry Collector, you can efficiently collect and
+transmit TiDB metrics to Cloud Observability, enabling comprehensive analysis and visualization of your TiDB deployment.
+This README provides step-by-step instructions for integrating TiDB metrics with Cloud Observability using the
+OpenTelemetry Collector.
+
+## Prerequisites
+
+* Docker
+* Docker Compose
+* A Cloud Observability account
+* Cloud Observability [access token][ls-docs-access-token]
+
+## How to set it up
+
+1. **Export your Cloud Observability access token**:
+    ```bash
+    export LS_ACCESS_TOKEN=<YOUR_LIGHTSTEP_TOKEN>
+    ```
+2. **Run the docker compose example to spin up TiDB and the OpenTelemetry Collector**:
+    ```bash
+    docker-compose up -d
+    ```
+3. **Access [tidb-vision](https://github.com/pingcap/tidb-vision)** at http://localhost:8010.
+4. **Access Spark Web UI at http://localhost:8080** and access [TiSpark](https://github.com/pingcap/tispark) through
+   spark://127.0.0.1:7077
+5. **Monitor TiDB Metrics in Cloud Observability**: After setup, TiDB metrics will start populating in your Cloud
+   Observability dashboard.
+6. **Shutting down the monitoring setup**:
+    ```bash
+    docker-compose down -v
+    ```
+
+## Configuring TiDB  for Advanced Monitoring
+
+This guide assumes a standard TiDB setup. TiDB offers various configuration options that can impact the metrics it
+provides. For detailed configurations and best practices, always refer to [the official TiDB documentation][tidb-docs].
+
+[ls-docs-access-token]: https://docs.lightstep.com/docs/create-and-manage-access-tokens
+
+[tidb-docs]: https://docs.pingcap.com/tidb/stable/grafana-tidb-dashboard#tidb-monitoring-metrics

collector/tidb/examples/compose/collector.yaml

@@ -0,0 +1,27 @@
+receivers:
+  prometheus:
+    config:
+      scrape_configs:
+        - job_name: 'tidb-cluster'
+          scrape_interval: 5s
+          honor_labels: true
+          static_configs:
+            - targets: [ 'pushgateway:9091' ]
+
+processors:
+  batch:
+
+exporters:
+  logging:
+    loglevel: debug
+  otlp:
+    endpoint: ingest.lightstep.com:443
+    headers:
+      - lightstep-access-token: ${LS_ACCESS_TOKEN}
+
+service:
+  pipelines:
+    metrics:
+      receivers: [ prometheus ]
+      processors: [ batch ]
+      exporters: [ logging,otlp ]

collector/tidb/examples/compose/config/pd.toml

@@ -0,0 +1,86 @@
+# PD Configuration.
+
+name = "pd"
+data-dir = "default.pd"
+
+client-urls = "http://127.0.0.1:2379"
+# if not set, use ${client-urls}
+advertise-client-urls = ""
+
+peer-urls = "http://127.0.0.1:2380"
+# if not set, use ${peer-urls}
+advertise-peer-urls = ""
+
+initial-cluster = "pd=http://127.0.0.1:2380"
+initial-cluster-state = "new"
+
+lease = 3
+tso-save-interval = "3s"
+
+[security]
+# Path of file that contains list of trusted SSL CAs. if set, following four settings shouldn't be empty
+cacert-path = ""
+# Path of file that contains X509 certificate in PEM format.
+cert-path = ""
+# Path of file that contains X509 key in PEM format.
+key-path = ""
+
+[log]
+level = "error"
+
+# log format, one of json, text, console
+#format = "text"
+
+# disable automatic timestamps in output
+#disable-timestamp = false
+
+# file logging
+[log.file]
+#filename = ""
+# max log file size in MB
+#max-size = 300
+# max log file keep days
+#max-days = 28
+# maximum number of old log files to retain
+#max-backups = 7
+# rotate log by day
+#log-rotate = true
+
+[metric]
+# prometheus client push interval, set "0s" to disable prometheus.
+interval = "15s"
+# prometheus pushgateway address, leaves it empty will disable prometheus.
+address = "pushgateway:9091"
+
+[schedule]
+max-merge-region-size = 0
+split-merge-interval = "1h"
+max-snapshot-count = 3
+max-pending-peer-count = 16
+max-store-down-time = "30m"
+leader-schedule-limit = 4
+region-schedule-limit = 4
+replica-schedule-limit = 8
+merge-schedule-limit = 8
+tolerant-size-ratio = 5.0
+
+# customized schedulers, the format is as below
+# if empty, it will use balance-leader, balance-region, hot-region as default
+# [[schedule.schedulers]]
+# type = "evict-leader"
+# args = ["1"]
+
+[replication]
+# The number of replicas for each region.
+max-replicas = 3
+# The label keys specified the location of a store.
+# The placement priorities is implied by the order of label keys.
+# For example, ["zone", "rack"] means that we should place replicas to
+# different zones first, then to different racks if we don't have enough zones.
+location-labels = []
+
+[label-property]
+# Do not assign region leaders to stores that have these tags.
+#  [[label-property.reject-leader]]
+#  key = "zone"
+#  value = "cn1

collector/tidb/examples/compose/config/spark-defaults.conf

@@ -0,0 +1,2 @@
+spark.tispark.pd.addresses pd0:2379
+spark.sql.extensions org.apache.spark.sql.TiExtensions