[nfsv4] Re: Erasure coding vs delegations

Rick Macklem <rick.macklem@gmail.com> Thu, 05 December 2024 22:50 UTC

Return-Path: <rick.macklem@gmail.com>
X-Original-To: nfsv4@ietfa.amsl.com
Delivered-To: nfsv4@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 658F5C169423 for <nfsv4@ietfa.amsl.com>; Thu, 5 Dec 2024 14:50:19 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.107
X-Spam-Level:
X-Spam-Status: No, score=-2.107 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, FREEMAIL_FROM=0.001, RCVD_IN_DNSWL_BLOCKED=0.001, RCVD_IN_ZEN_BLOCKED_OPENDNS=0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01] autolearn=ham autolearn_force=no
Authentication-Results: ietfa.amsl.com (amavisd-new); dkim=pass (2048-bit key) header.d=gmail.com
Received: from mail.ietf.org ([50.223.129.194]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 60f9cfnwj6QV for <nfsv4@ietfa.amsl.com>; Thu, 5 Dec 2024 14:50:19 -0800 (PST)
Received: from mail-ed1-x535.google.com (mail-ed1-x535.google.com [IPv6:2a00:1450:4864:20::535]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature ECDSA (P-256) server-digest SHA256) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 07239C1654F3 for <nfsv4@ietf.org>; Thu, 5 Dec 2024 14:50:18 -0800 (PST)
Received: by mail-ed1-x535.google.com with SMTP id 4fb4d7f45d1cf-5cfa1ec3b94so1611983a12.2 for <nfsv4@ietf.org>; Thu, 05 Dec 2024 14:50:18 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1733439017; x=1734043817; darn=ietf.org; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:from:to:cc:subject:date :message-id:reply-to; bh=VVdLpDbrqsXZEMkyMxC7xLSXPxEVyZVoHD6HqJ/hgZA=; b=Dm7EaviyV6QAzSFA3q2oZ1krCkYJKJueOd/VS/mv/t97b7XXJ2zrkX5RhykSYkawl7 d8nolO1mZ4Ar3jhlLs7g9TYvpXOOb/kboIcFpTm/Trv3CI256i4G4gAPK2l3xkgVofGo qzIG7GENUiXmsqR3MCtl/G0aLFv5becb2w6XTa50bkMZyUw6WuhBUmAZaf93v9B3EghI KjNtLcEZecQ8vT6lsDLl9ysJPed28VzTHL2KqOHaGAXrdVV8jEnJUDtWjOxa96MkZWhR AKG7Ur6s5i9Ull1SbwOQHb11mtMxlN60cjXHUu13BWhs/QmOhHm5xd5ttH21qM5ydpNY fimg==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1733439017; x=1734043817; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=VVdLpDbrqsXZEMkyMxC7xLSXPxEVyZVoHD6HqJ/hgZA=; b=udkMXIclQCf+gTWZnTtos14+F85DWBhODfYnK/Ebr//nF5708jRemEnL2up0m+948K ZGyEu7W6LA8fRQEf/UzLQkdlAgajErrd4S8F2oVWMl9muxB+j8a4Q63pbitdl65542RO aN+9tzZFk36OPLx5LcSSmnbUQfumznY+ioqeuHixshvDiiKHvR9iaTF+soADmdW/IzUW 0QEq52efG2y6WpOoCkfZZWVBCDhBUaaEo6/eMOsU3kzQ4eKGj/3EScBhNLSDbYJPqTQk OrIeTDfXNCUQ74WOEVnnpMaalBW2F4a4XzQOl52gD/eHqI2vKRnUjuceehBMl0+q1zcY At1w==
X-Gm-Message-State: AOJu0Yxe/eIyz//FGBM3+yIKegpweQ7x0D8ssO1GA9PrU9yBi8wdnJSV GIAadQFBwWr7vb0X9h9Ic5QjH4NpGYm4HJsOyola2NaH++KduQWt62kgc+TH+eScTmbK8MKup9q okJLbalJeemgn65K8mgXiMx8RRg==
X-Gm-Gg: ASbGncsQ6yymL8VObGwv4+Q1yyikXIVthkuO1LkXHejQYaNn8H6+hjnfsGBaT2QcwO8 q/z1cadsXZcfotvjYDqTZtgH7FZS5huv09zEkBnF5cC3wKb8yozMg3UCPKvTrX0o=
X-Google-Smtp-Source: AGHT+IEpfbolD7bhPtebQ5wfwUFTGz+9U1DTnAv9rggWXJZwK8x1jDik84oHJqyxw8+YcBlmoyRn+KMy8S77+iKMDXI=
X-Received: by 2002:a05:6402:3884:b0:5d2:b712:fbcf with SMTP id 4fb4d7f45d1cf-5d3be7ab8c7mr463996a12.21.1733439016701; Thu, 05 Dec 2024 14:50:16 -0800 (PST)
MIME-Version: 1.0
References: <CAM5tNy55waUSdLmRFXz5OvUhSe1pok0GJ62+drPbDvp3eBjcyg@mail.gmail.com> <FFB40A59-00BF-493E-8D39-D1356F61607D@gmail.com>
In-Reply-To: <FFB40A59-00BF-493E-8D39-D1356F61607D@gmail.com>
From: Rick Macklem <rick.macklem@gmail.com>
Date: Thu, 05 Dec 2024 14:50:05 -0800
Message-ID: <CAM5tNy76VuwBypiTYrZ-n0=j7=nVRkgjU0w9wfXZNUQ42ZC3zg@mail.gmail.com>
To: Thomas Haynes <loghyr@gmail.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Message-ID-Hash: UAZO4O22Y22SLUIROKACVJXYG7MMPUTC
X-Message-ID-Hash: UAZO4O22Y22SLUIROKACVJXYG7MMPUTC
X-MailFrom: rick.macklem@gmail.com
X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; header-match-nfsv4.ietf.org-0; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header
CC: NFSv4 <nfsv4@ietf.org>
X-Mailman-Version: 3.3.9rc6
Precedence: list
Subject: [nfsv4] Re: Erasure coding vs delegations
List-Id: NFSv4 Working Group <nfsv4.ietf.org>
Archived-At: <https://mailarchive.ietf.org/arch/msg/nfsv4/GJCVEJRqMP_UawE-DGdrBHCZ9Ws>
List-Archive: <https://mailarchive.ietf.org/arch/browse/nfsv4>
List-Help: <mailto:nfsv4-request@ietf.org?subject=help>
List-Owner: <mailto:nfsv4-owner@ietf.org>
List-Post: <mailto:nfsv4@ietf.org>
List-Subscribe: <mailto:nfsv4-join@ietf.org>
List-Unsubscribe: <mailto:nfsv4-leave@ietf.org>

On Thu, Dec 5, 2024 at 8:11 AM Thomas Haynes <loghyr@gmail.com> wrote:
>
>
>
> > On Dec 4, 2024, at 1:04 PM, Rick Macklem <rick.macklem@gmail.com> wrote:
> >
> > Hi,
> >
> > A simple comment w.r.t. Tom's talk to-day on Erasure coding.
> >
> > I'll admit I have not read your draft, but I was wondering if
> > you have looked at the relationship between your erasure encoding
> > work and delegations?
> >
> > In particular, a write delegation issued by the MDS to a client
> > would ensure exclusive writing and, as such, issuing write
> > delegations "generously" might reduce your write contention
> > problem?
> >
> > Just a thought, rick
>
>
> Hi Rick,
>
> The problem is that we want to share the file for multiple writers. :-)
>
> In general the problem is that the applications are writing non-aligned block data.
Yes, I understand that. However, you did note that this is not a
common case (< 10% I thought?).

What I was suggesting is that a write delegation issued to a client
would indicate that this
write sharing is not going to happen and that that might allow you to
avoid some complexity
for the common, non-write shared case?

rick

>
> Client 1 is accessing 0 - 13k and client 2 is accessing 13k -> 20k. Each data block except 12-16k can be written with no expectation of collision. That edge block is different.
>
> Thanks.
> Tom