crail-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Patrick Stuedi <>
Subject Re: [zrlio-users] Getting Crail to work over TCP
Date Wed, 21 Aug 2019 05:42:54 GMT
There is a bug currently in NaRPC which increases the likelyhood of hangs
in Crail/TCP as the data sizes increase. We have identified the actual
problem in NaRPC but didn't get to fixing it so far. I can look into this.


On Wed, Aug 21, 2019 at 12:35 AM 'Ben Sidhom' via zrlio-users <> wrote:

> I've been experimenting with getting Crail over TCP to work with the
> crail-spark-io <> shuffle
> extensions.
> It seems to work fine for small shuffle sizes (up to about 10 gigabytes),
> but anything larger than that seems to hang. I've investigated this and the
> hangs seem to happen due to a few reasons, mostly contained to the NaRPC
> layer.
> The benchmark numbers here
> <> seem
> to imply that this has worked for at least 200 gigabyte shuffles (I'm not
> certain because that second experiment does not explicitly give the test
> parameters). Has anybody had success with Crail over TCP or were pretty
> much all of the tests run over RDMA/NVMe?
> --
> -Ben
> --
> You received this message because you are subscribed to the Google Groups
> "zrlio-users" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to
> To view this discussion on the web visit
> <>
> .

  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message