[ofiwg] DS/DA - tomorrow's meeting

Bernard Metzler BMT at zurich.ibm.com
Tue Sep 22 08:06:35 PDT 2015


We cancelled.



From:	"Smith, Stan" <stan.smith at intel.com>
To:	Bernard Metzler <BMT at zurich.ibm.com>, Paul Grun <grun at cray.com>
Cc:	"ofiwg at lists.openfabrics.org" <ofiwg at lists.openfabrics.org>
Date:	09/22/2015 04:55 PM
Subject:	RE: [ofiwg] DS/DA - tomorrow's meeting



I would 2nd the cancel option.

> -----Original Message-----
> From: ofiwg-bounces at lists.openfabrics.org [
mailto:ofiwg-bounces at lists.openfabrics.org] On Behalf Of Bernard Metzler
> Sent: Tuesday, September 22, 2015 4:23 AM
> To: Paul Grun
> Cc: ofiwg at lists.openfabrics.org
> Subject: Re: [ofiwg] DS/DA - tomorrow's meeting
>
> I am not sure if I remember correctly - didn't we plan to have Chet
presenting/discussing additional use cases which he indicated
> to have on his plate?  In particular I remember he mentioned 3 more
fields of discussion - WRITE atomicity, RAS error handling
> and RDMA with pmem. As I said, I am not sure if Chet (on copy) is
available today.
>
> From the last weeks discussion on NVDIMM use cases I did not get much out
which relates to a kernel storage interface - rather
> it showed that it might be a good idea not to use a kernel interface for
storage at all. What did others hear?
>
> I am in a local conference all my afternoon, which I would leave for that
call. With that I am interested to cancel todays meeting
> in case Chet has not planned for a today's discussion/presentation (it
would be my misinterpretation to have expected that).
>
> Thanks,
> Bernard
>
>
> From:		 Paul Grun <grun at cray.com>
> To:		 "ofiwg at lists.openfabrics.org" <ofiwg at lists.openfabrics.org>
> Date:		 09/21/2015 09:59 PM
> Subject:		 [ofiwg] DS/DA - tomorrow's meeting
> Sent by:		 ofiwg-bounces at lists.openfabrics.org
>
>
>
> Greetings – I am called away unexpectedly tonight and thus cannot attend
tomorrow’s meeting.  We can choose to cancel the
> meeting, or we can press ahead and hold the meeting anyway if someone
will volunteer to serve as chair and take minutes.
>
> At last week’s meeting we made good progress in understanding some use
cases for kernel mode access to NVM, at least from a
> storage perspective.
>
> Our next step should be to focus on slides 7 & 8 from the slide deck
(attached).  We need to boil Chet’s material down into
> several bullet points illustrating the relevant kernel mode use cases,
and we need to explore why we believe that KFI is critical to
> meeting those cases.
>
> I am attaching the most recent version of the slide deck.
>
> Thoughts?  Meet tomorrow, or cancel?
>
> -Paul
>
> Ps – OFI WG WILL meet tomorrow as scheduled.  Sean is assembling an
agenda, please send him a note (or post to the list) if you
> have items you would like added to the OFI WG agenda.
>
>
>
> Cray Inc.
> Office:    (503) 620-8757
> Mobile:  (503) 703-5382
>  [attachment "kfabric-framework__2015_0908.pptx" deleted by Bernard
Metzler/Zurich/IBM]
> _______________________________________________
> ofiwg mailing list
> ofiwg at lists.openfabrics.org
> http://lists.openfabrics.org/mailman/listinfo/ofiwg
> _______________________________________________
> ofiwg mailing list
> ofiwg at lists.openfabrics.org
> http://lists.openfabrics.org/mailman/listinfo/ofiwg


More information about the ofiwg mailing list