Editor: Tom Dewan
TiKV is a distributed key-value database. It has higher performance requirements than a regular application, so tracing tools must have minimal impact. This article describes
how we achieved tracing all requests time consumption in TiKV with less than 5% performance impact.
Background knowledge
Logs, metrics, and traces are the three pillars of system observability. The following figure shows their relationship: Logs, metrics, and traces
Metrics record and present aggregatable data.
Traces are a series of events for a single request.
TiKV has a complete log and metric system, but lacks traces. Therefore, when we troubleshoot TiKV and TiKV s SQL layer, TiDB, we may encounter these issues:
Using a GPU Boosts TiDB Analytics Performance by 10 to 150 Times pingcap.com - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from pingcap.com Daily Mail and Mail on Sunday newspapers.