We cancelled.
From: "Smith, Stan" <[email protected]> To: Bernard Metzler <[email protected]>, Paul Grun <[email protected]> Cc: "[email protected]" <[email protected]> Date: 09/22/2015 04:55 PM Subject: RE: [ofiwg] DS/DA - tomorrow's meeting I would 2nd the cancel option. > -----Original Message----- > From: [email protected] [ mailto:[email protected]] On Behalf Of Bernard Metzler > Sent: Tuesday, September 22, 2015 4:23 AM > To: Paul Grun > Cc: [email protected] > 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 <[email protected]> > To: "[email protected]" <[email protected]> > Date: 09/21/2015 09:59 PM > Subject: [ofiwg] DS/DA - tomorrow's meeting > Sent by: [email protected] > > > > 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 > [email protected] > http://lists.openfabrics.org/mailman/listinfo/ofiwg > _______________________________________________ > ofiwg mailing list > [email protected] > http://lists.openfabrics.org/mailman/listinfo/ofiwg _______________________________________________ ofiwg mailing list [email protected] http://lists.openfabrics.org/mailman/listinfo/ofiwg
