Hi Stefan, Thanks for replying. First time got rejected and then resent it after subscribing to the group. Not sure how this happened. I am attaching again. Please do check. Thanks, Amit Pawar On Fri, Aug 21, 2020 at 1:29 PM <stefan.johansson@oracle.com> wrote:

Hi Amit,

Your patch did not make it to the list. It might have been stripped. Are you subscribed to the list? That might be required to attach patches.

Thanks, Stefan

On 2020-08-20 19:33, amith pawar wrote:

...

Hi,

Currently AlwaysPreTouch for ParallelGC is done with a single thread and this attached patch converts it to multithreaded similar to other GCs.

All JTREG tests passed without new failures.

Time taken for pretouch on EPYC server with 1TB memory and 128 threads Before fix: ~107 s After fix : ~14 s

Please review this attached patch and give your feedback.

Thanks, Amit Pawar

-- With best regards, amit pawar

Hi Amit, I've now created a webrev and JBS entry for your proposal. Here are the links: Webrev: http://cr.openjdk.java.net/~sjohanss/sponsor/amit.pawar/8252221/00/ JBS: https://bugs.openjdk.java.net/browse/JDK-8252221 Thanks, Stefan On 2020-08-21 13:48, stefan.johansson@oracle.com wrote:

Hi Amit,

Now the patch made it through =)

Me or somebody else from the GC-team will provide feedback once we find time to look at the patch.

Thanks for reaching out, Stefan

On 2020-08-21 13:39, amith pawar wrote:

...

Hi Stefan,

Thanks for replying. First time got rejected and then resent it after subscribing to the group. Not sure how this happened.

I am attaching again. Please do check.

Thanks, Amit Pawar

On Fri, Aug 21, 2020 at 1:29 PM <stefan.johansson@oracle.com <mailto:stefan.johansson@oracle.com>> wrote:

    Hi Amit,

    Your patch did not make it to the list. It might have been stripped.     Are     you subscribed to the list? That might be required to attach patches.

    Thanks,     Stefan

    On 2020-08-20 19:33, amith pawar wrote:      >   Hi,      >      > Currently AlwaysPreTouch for ParallelGC is done with a single     thread and      > this attached patch converts it to multithreaded similar to other     GCs.      >      > All JTREG tests passed without new failures.      >      > Time taken for pretouch on EPYC server with 1TB memory and 128     threads      > Before fix: ~107 s      > After fix   :  ~14 s      >      > Please review this attached patch and give your feedback.      >      > Thanks,      > Amit Pawar      >

-- With best regards, amit pawar

Hi Amit, A short heads up =) We are in the middle of transitioning OpenJDK to git and GitHub, see JEP 369 [1]. We will not have time to complete this review before the move takes place. Instead it will have to be restarted using GitHub. An introduction and great source of information on how to get started with the new workflow can be found on the project Skara wiki [2]. The move is scheduled for tomorrow [3], so starting next week you should be able to create your own PR on GitHub for this change. Thanks, Stefan [1] https://openjdk.java.net/jeps/369 [2] https://wiki.openjdk.java.net/display/SKARA/ [3] https://mail.openjdk.java.net/pipermail/jdk-dev/2020-August/004588.html On 2020-08-25 07:28, amith pawar wrote:

Hello everyone,

Looks like due to some issue nobody received my patch earlier sent to this group. Stefan created Webrev and JBS for this patch. Thanks Stefan for all your help.

This patch improve ParallelGC pretouch time similar to other GCs.

Please reivew this change.

Thanks, Amit

On Tue, Aug 25, 2020 at 3:04 AM <stefan.johansson@oracle.com <mailto:stefan.johansson@oracle.com>> wrote:

Hi Amit,

I've now created a webrev and JBS entry for your proposal. Here are the links: Webrev: http://cr.openjdk.java.net/~sjohanss/sponsor/amit.pawar/8252221/00/ JBS: https://bugs.openjdk.java.net/browse/JDK-8252221

Thanks, Stefan

On 2020-08-21 13:48, stefan.johansson@oracle.com <mailto:stefan.johansson@oracle.com> wrote: > Hi Amit, > > Now the patch made it through =) > > Me or somebody else from the GC-team will provide feedback once we find > time to look at the patch. > > Thanks for reaching out, > Stefan > > On 2020-08-21 13:39, amith pawar wrote: >> Hi Stefan, >> >> Thanks for replying. First time got rejected and then resent it after >> subscribing to the group. Not sure how this happened. >> >> I am attaching again. Please do check. >> >> Thanks, >> Amit Pawar >> >> On Fri, Aug 21, 2020 at 1:29 PM <stefan.johansson@oracle.com <mailto:stefan.johansson@oracle.com> >> <mailto:stefan.johansson@oracle.com <mailto:stefan.johansson@oracle.com>>> wrote: >> >>     Hi Amit, >> >>     Your patch did not make it to the list. It might have been stripped. >>     Are >>     you subscribed to the list? That might be required to attach patches. >> >>     Thanks, >>     Stefan >> >>     On 2020-08-20 19:33, amith pawar wrote: >>      >   Hi, >>      > >>      > Currently AlwaysPreTouch for ParallelGC is done with a single >>     thread and >>      > this attached patch converts it to multithreaded similar to other >>     GCs. >>      > >>      > All JTREG tests passed without new failures. >>      > >>      > Time taken for pretouch on EPYC server with 1TB memory and 128 >>     threads >>      > Before fix: ~107 s >>      > After fix   :  ~14 s >>      > >>      > Please review this attached patch and give your feedback. >>      > >>      > Thanks, >>      > Amit Pawar >>      > >> >> >> >> -- >> With best regards, >> amit pawar

-- With best regards, amit pawar