I don't know what "work" of mine you're referring to (I never claimed to have a GC that can do the impossible either?), but what I'm taking issue with is the clearly bogus sentence from their summary [1], which was repeated at the top here:
> Pause times with Shenandoah are independent of heap size, meaning you will have the same consistent pause times whether your heap is 200 MB or 200 GB.
You can't just write an unconditional "summary" like that with a straight face. It's practically dishonest to present it as if the giant asterisk isn't there. And this has nothing to do with the quality of the GC... I'm sure they've done great work, and if they're proud of it they probably very well should be, but that doesn't give us (or them) an excuse to advertise it as doing something it admits it doesn't do.
Re:Java 12
by chrisseaton on Tuesday March 19, 2019 @07:21PM
(#19437201)
If you know the claim is bogus then you must have done the work to prove that. Show that work to them and stop being so unpleasant to me.
I thought we already established this. It was the GC documentation itself [1] that admitted the summary was bogus. Specifically:
> Usual latency induced: >100 ms, but can be more, especially on a very occupied heap
[1] https://wiki.openjdk.java.net/display/shenandoah/Main#Main-F...
Re:Java 12
by chrisseaton on Tuesday March 19, 2019 @07:36PM
(#19437323)
In a failure mode! When you have deployed it outside its system requirements!
How do you know if allocation is slower than collection? The logs tell you. This is the same as any performance requirement - you need to test it empirically.
If you think there's an issue with the claims of Shenandoah then you should publish your work rather than just abuse.