From Daniel.Ellard at netapp.com Thu Aug 2 08:44:50 2007 From: Daniel.Ellard at netapp.com (Ellard, Daniel) Date: Thu, 2 Aug 2007 11:44:50 -0400 Subject: [Federated-fs] Namespace design and fault tolerance Message-ID: Last week I presented an overview of the requirements doc at the IETF NFS working group. My slides are here: http://www3.ietf.org/proceedings/07jul/slides/nfsv4-1.pdf The minutes are here: https://datatracker.ietf.org/meeting/69/materials.html One of the comments that came up during the presentation was that AFS, with its everything-branches-off-the-afs-root namespace, had a nice property in the face of cell failures -- if a cell fails, then everything in the namespace that is NOT implemented in that cell is still accessible. The current spec permits the construction of namespaces that don't have this property. For example, if /a is implemented in member x, and /a/b is implemented in member y, and /a/b/c is implemented in member z (and there aren't any other ways to get to /a/b/c) then if y is misbehaving, then /a/b/c is inaccessible. However, the current spec doesn't force anyone to build their namespace in this manner: it's perfectly fine to have everything branch off the root. It's also possible to have more than one way to get to something, so you could have an intuitive namespace hierarchy and a fallback AFS-like namespace living side by side. The general rule is: if you don't have faith that you'll be able to traverse any of the paths you know about to reach the members you're interested in, then make your own path. AFS took this to one extreme: there's only one path to each cell, and everyone implements their own copy of this path locally. The current spec permits members to trust each other, but doesn't require that they do. We think that this trust will be useful for members that already have close trust relationships, but it shouldn't be used recklessly. -Dan From Daniel.Ellard at netapp.com Mon Aug 6 09:04:58 2007 From: Daniel.Ellard at netapp.com (Ellard, Daniel) Date: Mon, 6 Aug 2007 12:04:58 -0400 Subject: [Federated-fs] Reminder - conf call today Message-ID: Reminder: federated-fs conf call today 4-5pm EST. Dial-in info: 1-888-765-3653, conf id 6206056 The discussion today centers on defining a protocol that satisfies the requirements we've been discussing. Renu Tewari and Manoj Naik from IBM/Almaden are going to draft a protocol based on an extension of their "Glamour" protocol. (The draft won't be finished today, but there's still plenty to talk about.) -Dan From Daniel.Ellard at netapp.com Wed Aug 15 07:15:45 2007 From: Daniel.Ellard at netapp.com (Ellard, Daniel) Date: Wed, 15 Aug 2007 10:15:45 -0400 Subject: [Federated-fs] Plan and schedule for the next few months Message-ID: Here's the tentative plan and schedule for the "federated-fs" drafts for the next few months, leading up to the next meeting of the IETF NFSv4 WG. Please let me know if you have any comments or suggestions. If you're interested in participating in the conference calls, please note that the schedule has been bumped one week (to avoid some holidays and other conflicts). The most important aspect of the plan is that I'm assuming that the requirements doc is essentially done, except for wordsmithing and fine tuning. Therefore, it's time to start working on the next step -- drafting a protocol that statisfies the requirements. Renu Tewari is taking the lead on preparing a spec, based on Glamour, and should have a preliminary draft prepared in time to discuss at the next conference call. The tentative schedule, assuming we don't hit any bumps in the road: 8/27 - Federated-fs conf call 9/6 - Federated-fs conf call 9/24 - Federated-fs conf call 9/28 - MILESTONE: first "complete" protocol spec, IETF internet draft 10/8 - Federated-fs conf call 10/22 - Federated-fs conf call 10/31 - MILESTONE: second IETF internet draft November: more discussion, fleshing out the draft, etc. Possibly another internet draft, if there are enough things we need to change, but maybe hold off until the IETF meeting in Vancouver. Early December: present draft to NFSv4 WG. Late December: wrap-up internet draft. Try to get it and the requirements draft taken up as RFCs. Thanks, -Dan From tewarir at us.ibm.com Mon Aug 27 00:29:39 2007 From: tewarir at us.ibm.com (Renu Tewari) Date: Mon, 27 Aug 2007 03:29:39 -0400 Subject: [Federated-fs] Early Draft of the protocol for Monday's call Message-ID: I am attaching the working draft of the fed-fs protocol that we can discuss during Monday's call. The draft is in its early stages so please join the discussions to help shape it better. Reminder: federated-fs conf call Monday 8/27 4-5pm EST. Dial-in info: 1-888-765-3653, conf id 6206056 -------------- next part -------------- An HTML attachment was scrubbed... URL: https://lists.sdsc.edu/pipermail/federated-fs/attachments/20070827/eab04386/attachment.html -------------- next part -------------- A non-text attachment was scrubbed... Name: fed-fs-draft-new.doc Type: application/octet-stream Size: 220160 bytes Desc: not available Url : https://lists.sdsc.edu/pipermail/federated-fs/attachments/20070827/eab04386/fed-fs-draft-new.doc