[v8-users] Re: Performance regression
I've submitted a bug with a repro here: https://bugs.chromium.org/p/v8/issues/detail?id=13714 Thanks, Chris On Friday, February 3, 2023 at 7:15:06 AM UTC-5 dinf...@chromium.org wrote: > Hi, > > I am not aware of performance regressions with this feature. You can open > an issue with a repro so we can take a look at. > > Performance is monitored quite heavily with V8 but maybe something slipped > through. > > Best, > Dominik > > On Friday, February 3, 2023 at 12:02:25 PM UTC+1 crdu...@gmail.com wrote: > This specific commit disabled map space by default, and later commits seem > to have totally removed map space from the code. > Can anyone provide any details or insights as to what kind of code could > be impacted (performance-wise) by this change? > > On Tuesday, January 31, 2023 at 9:58:09 AM UTC-5 crdu...@gmail.com wrote: > I'm seeing a significant performance regression running some JavaScript > workloads in an application that embeds V8. There isn't much going on in > terms of native code integration in this workload, it's mostly doing some > CryptoJS stuff. > > Doing a `git bisect` I've isolated the change to this commit: > https://chromium.googlesource.com/v8/v8/+/0ff080d1f7f6b1a0fdaedc6e150ac93a8ce962ec > > I'm wondering if anyone has any thoughts on this. > - Is anyone else seeing this performance change? > - Would a performance regression have been noticed in regular V8 release > testing? > - Does anyone have any thoughts on how to mitigate the performance impact? > The changes to the map space in that commit don't appear to have build > options to control them, that I can see. > -- -- v8-users mailing list v8-users@googlegroups.com http://groups.google.com/group/v8-users --- You received this message because you are subscribed to the Google Groups "v8-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to v8-users+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/v8-users/699e4054-72ab-43cb-aebf-0fd3cbc02ebcn%40googlegroups.com.
[v8-users] Re: Performance regression
This specific commit disabled map space by default, and later commits seem to have totally removed map space from the code. Can anyone provide any details or insights as to what kind of code could be impacted (performance-wise) by this change? On Tuesday, January 31, 2023 at 9:58:09 AM UTC-5 crdu...@gmail.com wrote: > I'm seeing a significant performance regression running some JavaScript > workloads in an application that embeds V8. There isn't much going on in > terms of native code integration in this workload, it's mostly doing some > CryptoJS stuff. > > Doing a `git bisect` I've isolated the change to this commit: > https://chromium.googlesource.com/v8/v8/+/0ff080d1f7f6b1a0fdaedc6e150ac93a8ce962ec > > I'm wondering if anyone has any thoughts on this. > - Is anyone else seeing this performance change? > - Would a performance regression have been noticed in regular V8 release > testing? > - Does anyone have any thoughts on how to mitigate the performance impact? > The changes to the map space in that commit don't appear to have build > options to control them, that I can see. > -- -- v8-users mailing list v8-users@googlegroups.com http://groups.google.com/group/v8-users --- You received this message because you are subscribed to the Google Groups "v8-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to v8-users+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/v8-users/aae6ed61-560b-41d8-acbc-67ae4f9d677dn%40googlegroups.com.
[v8-users] Performance regression
I'm seeing a significant performance regression running some JavaScript workloads in an application that embeds V8. There isn't much going on in terms of native code integration in this workload, it's mostly doing some CryptoJS stuff. Doing a `git bisect` I've isolated the change to this commit: https://chromium.googlesource.com/v8/v8/+/0ff080d1f7f6b1a0fdaedc6e150ac93a8ce962ec I'm wondering if anyone has any thoughts on this. - Is anyone else seeing this performance change? - Would a performance regression have been noticed in regular V8 release testing? - Does anyone have any thoughts on how to mitigate the performance impact? The changes to the map space in that commit don't appear to have build options to control them, that I can see. -- -- v8-users mailing list v8-users@googlegroups.com http://groups.google.com/group/v8-users --- You received this message because you are subscribed to the Google Groups "v8-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to v8-users+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/v8-users/06cc0084-0e06-4272-b6b1-0d403061b9adn%40googlegroups.com.
[v8-users] changelog between V8 versions?
I'm trying to figure out the easiest way to get a summary or detailed list of changes from one version of V8 to another. In particular I'm interested in the differences between V8 10.7.198.22 and V8 10.8.168.24. My motivation for this is that I'm seeing some significant performance differences between these two versions when running some JavaScript workloads. Thanks, Chris -- -- v8-users mailing list v8-users@googlegroups.com http://groups.google.com/group/v8-users --- You received this message because you are subscribed to the Google Groups "v8-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to v8-users+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/v8-users/48a5e536-c346-4ec3-8e75-16d9efd45a5fn%40googlegroups.com.
