[Info-vax] Rust as a HS language, was: Re: Quiet?

[Dan Cross]

In article <624da157$0$701$14726298 at news.sunsite.dk>,
Arne Vajhøj  <arne at vajhoej.dk> wrote:
>On 4/6/2022 9:56 AM, Dan Cross wrote:
>> In article <624d911f$0$702$14726298 at news.sunsite.dk>,
>> Arne Vajhøj  <arne at vajhoej.dk> wrote:
>>> On 4/5/2022 9:30 PM, Dan Cross wrote:
>>>> Eh?  It's commonly accepted that you're going to give up some
>>>> percentage of your capacity for GC overhead.
>>>
>>> No it is not.
>> 
>> Sorry, but yes it is.
>> 
>>> With generational garbage collectors it is very fast to GC
>>> short lived objects.
>> 
>> That does not mean that you aren't going to give up some
>> percentage of your capacity for GC.  GC is not infinitely fast.
>
>No.
>
>But it does not need to use zero CPU.
>
>It just need to be faster than the manual free calls.
>
>Which it is.

Ah, but then it's dependent on workload and allocation patterns.
You seem to be making a general claim to a problem that does not
have a single, generally accepted solution.

>>> Go GC use STW. They have managed to reduce the time but it is
>>> still a STW.
>> 
>> Note that I said that, "Go's concurrent GC _mostly_ avoids
>> that unless under severe memory pressure."
>
>A GC STW is a GC STW.

I think you missed the point.  I never claimed that the Go GC
doesn't stop the world.  It just mostly avoids it.

>>> The only GC I am aware of that does not do STW is Azul Zing.
>> 
>> The LVB in Azul is basically a localized pause.  It may be true
>> that Azul doesn't STW, but that doesn't mean that it's free.
>
>Of course it is not free.
>
>It may likely use more CPU than a STW GC.

...and may even be slower than explicit allocation!

>But it avoid STW.
>
>(and it is Azul Zing - Azul Zulu is using traditional STW GC)

Which was the topic of the paper I cited.

>> Under severe memory pressure pretty much all of the threads will
>> block in the LVB and the situation will be more or less
>> indistiguishable from a STW pause.
>
>That is not what tests show.
>
>Tests show that Azul Zing avoid the GC pauses.

I think you mean _global_ GC pauses.

>Hazelcast did a test with traditional JVM and Azul JVM.
>
>Results showed that 99% percentile was 2 ms for both,
>but 99.99% percentile was 40 ms for traditional and 8 ms
>for Azul Zing.
>
>It works.

Did you read the paper I cited?

	- Dan C.