<html><head><META http-equiv="Content-Type" content="text/html;charset=utf-8"></head><body><div id="content" contenteditable="true" spellcheck="true" autocorrect="true" autocapitalize="true" style="font-family: Helvetica;">I wholeheartedly agree with Sven here.<div>The Request for Engineering (RFE) is a powerful feedback mechanism to help steer the product's direction.</div><div><br></div><div>On the topic of GNR, the (free) alternative to compete with GNR is ZFS. Although not yet used in any production GPFS system, it is widely used under Lustre. It would however take some work to optimise ZFS for GPFS as has already been done for Lustre. Hence a good reason to lobby IBM to maintain a GPFS Software Raid in the face of possible future competition from ZFS.<br><br>Daniel<br><br>IBM Spectrum Storage Software<br><a dir="ltr" href="tel:+44%207818%20522266" x-apple-data-detectors="true" x-apple-data-detectors-type="telephone" x-apple-data-detectors-result="0">+44 (0)7818 522266</a><br>Sent from my iPad using IBM Verse<br><br><br><hr>On 29 Sep 2016, 04:28:33, oehmes@us.ibm.com wrote:<br><br>From: oehmes@us.ibm.com<br>To: gpfsug-discuss@spectrumscale.org<br>Cc: <br>Date: 29 Sep 2016 04:28:33<br>Subject: Re: [gpfsug-discuss] gpfs native raid<br><br><div id="MaaS360PIMSDKOriginalMessageId"><p>Hi Aaron,<br><br>the best way to express this 'need' is to vote and leave comments in the RFE's : <br><br>this is an RFE for GNR as SW : <a href="http://www.ibm.com/developerworks/rfe/execute?use_case=viewRfe&CR_ID=95090">http://www.ibm.com/developerworks/rfe/execute?use_case=viewRfe&CR_ID=95090</a><br><br>everybody who wants this to be one should vote for it and leave comments on what they expect.<br><br>Sven<br><br><br><img width="16" height="16" src="cid:D970904D-A57E-4142-8D83-207D7F77393B" border="0" alt="Inactive hide details for Aaron Knister ---09/28/2016 06:44:25 PM---Thanks Everyone for your replies! (Quick disclaimer, these "><font color="#424282">Aaron Knister ---09/28/2016 06:44:25 PM---Thanks Everyone for your replies! (Quick disclaimer, these opinions are my own, and not those of my</font><br><br><font size="2" color="#5F5F5F">From: </font><font size="2">Aaron Knister <aaron.knister@gmail.com></font><br><font size="2" color="#5F5F5F">To: </font><font size="2">gpfsug-discuss@spectrumscale.org</font><br><font size="2" color="#5F5F5F">Date: </font><font size="2">09/28/2016 06:44 PM</font><br><font size="2" color="#5F5F5F">Subject: </font><font size="2">Re: [gpfsug-discuss] gpfs native raid</font><br><font size="2" color="#5F5F5F">Sent by: </font><font size="2">gpfsug-discuss-bounces@spectrumscale.org</font><br></p><hr width="100%" size="2" align="left" noshade="" style="color:#8091A5; "><br><br><br><tt>Thanks Everyone for your replies! (Quick disclaimer, these opinions are <br>my own, and not those of my employer or NASA).<br><br>Not knowing what's coming at the NDA session, it seems to boil down to <br>"it ain't gonna happen" because of:<br><br>- Perceived difficulty in supporting whatever creative hardware <br>solutions customers may throw at it.<br><br>I understand the support concerns, but I naively thought that assuming <br>the hardware meets a basic set of requirements (e.g. redundant sas <br>paths, x type of drives) it would be fairly supportable with GNR. The <br>DS3700 shelves are re-branded NetApp E-series shelves and pretty vanilla <br>I thought.<br><br>- IBM would like to monetize the product and compete with the likes of <br>DDN/Seagate<br><br>This is admittedly a little disappointing. GPFS as long as I've known it <br>has been largely hardware vendor agnostic. To see even a slight shift <br>towards hardware vendor lockin and certain features only being supported <br>and available on IBM hardware is concerning. It's not like the software <br>itself is free. Perhaps GNR could be a paid add-on license for non-IBM <br>hardware? Just thinking out-loud.<br><br>The big things I was looking to GNR for are:<br><br>- end-to-end checksums<br>- implementing a software RAID layer on (in my case enterprise class) JBODs<br><br>I can find a way to do the second thing, but the former I cannot. <br>Requiring IBM hardware to get end-to-end checksums is a huge red flag <br>for me. That's something Lustre will do today with ZFS on any hardware <br>ZFS will run on (and for free, I might add). I would think GNR being <br>openly available to customers would be important for GPFS to compete <br>with Lustre. Furthermore, I had opened an RFE (#84523) a while back to <br>implement checksumming of data for non-GNR environments. The RFE was <br>declined because essentially it would be too hard and it already exists <br>for GNR. Well, considering I don't have a GNR environment, and hardware <br>vendor lock in is something many sites are not interested in, that's <br>somewhat of a problem.<br><br>I really hope IBM reconsiders their stance on opening up GNR. The <br>current direction, while somewhat understandable, leaves a really bad <br>taste in my mouth and is one of the (very few, in my opinion) features <br>Lustre has over GPFS.<br><br>-Aaron<br><br><br>On 9/1/16 9:59 AM, Marc A Kaplan wrote:<br>> I've been told that it is a big leap to go from supporting GSS and ESS<br>> to allowing and supporting native raid for customers who may throw<br>> together "any" combination of hardware they might choose.<br>><br>> In particular the GNR "disk hospital" functions...<br>> </tt><tt><a href="https://www.ibm.com/support/knowledgecenter/SSFKCN_3.5.0/com.ibm.cluster.gpfs.v3r5.gpfs200.doc/bl1adv_introdiskhospital.htm">https://www.ibm.com/support/knowledgecenter/SSFKCN_3.5.0/com.ibm.cluster.gpfs.v3r5.gpfs200.doc/bl1adv_introdiskhospital.htm</a></tt><tt><br>> will be tricky to support on umpteen different vendor boxes -- and keep<br>> in mind, those will be from IBM competitors!<br>><br>> That said, ESS and GSS show that IBM has some good tech in this area and<br>> IBM has shown with the Spectrum Scale product (sans GNR) it can support<br>> just about any semi-reasonable hardware configuration and a good slew of<br>> OS versions and architectures... Heck I have a demo/test version of GPFS<br>> running on a 5 year old Thinkpad laptop.... And we have some GSSs in the<br>> lab... Not to mention Power hardware and mainframe System Z (think 360,<br>> 370, 290, Z)<br>><br>><br>><br>><br>> _______________________________________________<br>> gpfsug-discuss mailing list<br>> gpfsug-discuss at spectrumscale.org<br>> </tt><tt><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a></tt><tt><br>><br>_______________________________________________<br>gpfsug-discuss mailing list<br>gpfsug-discuss at spectrumscale.org<br></tt><tt><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a></tt><tt><br><br></tt><br><br><br>
</div></div></div>Unless stated otherwise above:<BR>
IBM United Kingdom Limited - Registered in England and Wales with number 741598. <BR>
Registered office: PO Box 41, North Harbour, Portsmouth, Hampshire PO6 3AU<BR>
<BR>
</body></html>