Ruslan, thread per core (the Scylla version is per shard, which includes
memory pinning, direct I/O,
etc) is just the beginning. There are many challenges with it. See Avi's
presentation for
C* developers:
https://github.com/ngcc/ngcc2017/blob/master/Challenges_in_Thread-per-core_Implementations.pdf

You'll have to change all of the locking, make sure the shards are balanced
and the client
connections/streams are balanced. Make sure the I/O is divided fairly and
is also balanced and more.

Lots of fun!

On Wed, Sep 2, 2020 at 9:03 PM [email protected] <
[email protected]> wrote:

> Hi there,
>
> Once in a while on twitter will pop-up with thread per core architecture
> links.
>
> The only product on the market I know who does that is ScyllaDb.
> The underlaying infrastructure behind Scylla is Seastar/C++
> http://seastar.io/
>
> I know you can isolate cores and pin threads but was wondering if there is
> something similar to Seastar in Java.
>
> Thank you,
> Ruslan
>
> --
> You received this message because you are subscribed to the Google Groups
> "mechanical-sympathy" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to [email protected].
> To view this discussion on the web, visit
> https://groups.google.com/d/msgid/mechanical-sympathy/e4d51d66-5f67-4048-bfcf-abe7d693f91dn%40googlegroups.com
> <https://groups.google.com/d/msgid/mechanical-sympathy/e4d51d66-5f67-4048-bfcf-abe7d693f91dn%40googlegroups.com?utm_medium=email&utm_source=footer>
> .
>

-- 
You received this message because you are subscribed to the Google Groups 
"mechanical-sympathy" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To view this discussion on the web, visit 
https://groups.google.com/d/msgid/mechanical-sympathy/CAJtJYieRgeF0wOtkgdzvHc02i-x3z2TqvXnimZ%2BK-Fq9UQMt0w%40mail.gmail.com.

Reply via email to