在新遗迹中发现缓慢事务时，如何排除缓存未命中？
我们使用 New Relic RPM（银牌）来监控 Rails 应用程序的性能。我们已经使用缓存来加速许多瓶颈的处理速度，但现在我们的缓慢跟踪主要是缓存未命中。有没有办法让我们排除从缓存中获取内容所花费的时间，以便我们可以看到哪些部分仍然很慢？
We use New Relic RPM (silver) to monitor performance in our rails app. We've used caching to speed up processing in a lot of our bottlenecks, but now our slow traces are mostly cache misses. Is there a way for us to exclude time spent fetching things from the cache, so we can see which parts are still slow?
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（1）
无法排除部分请求执行时间对 New Relic 测量的总执行时间的影响。您可以尝试降低事务跟踪阈值，直到开始看到确实显示缓存命中的跟踪，以便您可以获得此类请求的更完整的跟踪。
您还可以查看“Web 事务”页面，了解请求所有部分的平均响应时间是如何分解的。这将包括这些缓存未命中的贡献，但也会让您了解其他需要关注的领域。
如果您的瓶颈出现在数据库中，您还可以尝试查看慢 SQL 语句。
There isn't a way to exclude parts of request execution time from contributing to the total execution time measured with New Relic. You could try lowering the transaction trace threshold until you start to see traces that do exhibit cache hits, so you can get more complete traces for such requests.
You could also look at the Web Transactions page and see how the response time breaks down for all the parts of the request on average. That'll include the contribution from those cache misses, but will give you an idea of other areas to look at, too.
You could also try looking at Slow SQL statements if your bottleneck appears to be in the database.