# Ray service profiling **URL:** \ **Category:** Ray Serve\ **Created:** [February 10, 2023, 6:36am UTC](https://discuss.ray.io/t/ray-service-profiling/9328 "2023-02-10T06:36:58Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![lanmcc](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/lanmcc/32/3399_2.png) [@lanmcc](https://discuss.ray.io/u/lanmcc)\ **Post date:** [February 10, 2023, 6:36am UTC](https://discuss.ray.io/t/ray-service-profiling/9328/1 "2023-02-10T06:36:58Z")
**How severe does this issue affect your experience of using Ray?** - High: It blocks me to complete my task. Using ray serve to deploy some model services, about the time-consuming of each function and how to find hot functions, see ray timeline in the official documents ray timeline：[Profiling — Ray 2.2.0](https://docs.ray.io/en/latest/ray-observability/monitoring-debugging/profiling.html) but it does not seem to be used for ray service, I would like to ask what tools can be used for hot spot analysis，time-consuming statistics at the function level ---
**Author:** ![Huaiwei\_Sun](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/huaiwei_sun/32/1316_2.png) [@Huaiwei\_Sun](https://discuss.ray.io/u/Huaiwei_Sun)\ **Post date:** [March 30, 2023, 3:03am UTC](https://discuss.ray.io/t/ray-service-profiling/9328/2 "2023-03-30T03:03:48Z")
@lanmcc If ray timeline works for ray serve (e.g., last 24 hours’ ray tasks created by serve), is that enough for you? ---
**Author:** ![sangcho](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/sangcho/32/425_2.png) [@sangcho](https://discuss.ray.io/u/sangcho)\ **Post date:** [March 30, 2023, 4:15am UTC](https://discuss.ray.io/t/ray-service-profiling/9328/3 "2023-03-30T04:15:32Z")
what do you mean by “but it does not seem to be used for ray service”? You mean you cannot see more fine grained breakdown of function calls?