[3877] in arla-drinkers
Re: is cache-only-prefixes an nnpfs limitation?
daemon@ATHENA.MIT.EDU (=?iso-8859-1?q?Niels_M=F6ller?=)
Mon Apr 10 09:30:03 2006
From arla-drinkers-bounces@stacken.kth.se Mon Apr 10 13:30:02 2006
Return-Path: <arla-drinkers-bounces@stacken.kth.se>
Delivered-To: arla-drinkers-mtg@bloom-picayune.mit.edu
Received: (qmail 21851 invoked from network); 10 Apr 2006 13:30:02 -0000
Received: from mx3.kth.se (130.237.48.97)
by charon.mit.edu with SMTP; 10 Apr 2006 13:30:02 -0000
Received: from localhost (localhost.localdomain [127.0.0.1])
by mx3.kth.se (Postfix) with ESMTP id 4AE95140992;
Mon, 10 Apr 2006 15:30:01 +0200 (CEST)
Received: from mx3.kth.se ([127.0.0.1])
by localhost (mx3.kth.se [127.0.0.1]) (amavisd-new, port 10024) with LMTP
id 13787-01-25; Mon, 10 Apr 2006 15:29:56 +0200 (CEST)
Received: from tapas.stacken.kth.se (tapas.stacken.kth.se [130.237.234.140])
by mx3.kth.se (Postfix) with ESMTP id 4EA9C14080C;
Mon, 10 Apr 2006 15:29:56 +0200 (CEST)
Received: from tapas.stacken.kth.se (localhost [127.0.0.1])
by tapas.stacken.kth.se (Postfix) with ESMTP id 12BE3534F3;
Mon, 10 Apr 2006 15:29:56 +0200 (CEST)
X-Original-To: arla-drinkers@tapas.stacken.kth.se
Delivered-To: arla-drinkers@tapas.stacken.kth.se
Received: from brev.stacken.kth.se (brev.stacken.kth.se [130.237.234.84])
by tapas.stacken.kth.se (Postfix) with ESMTP id 130C0534F3
for <arla-drinkers@tapas.stacken.kth.se>;
Mon, 10 Apr 2006 15:29:53 +0200 (CEST)
Received: from mx2.kth.se (mx2.kth.se [130.237.48.98])
by brev.stacken.kth.se (8.12.10/8.12.10) with ESMTP id k3ADTqla009499;
Mon, 10 Apr 2006 15:29:53 +0200 (MET DST)
Received: from localhost (localhost.localdomain [127.0.0.1])
by mx2.kth.se (Postfix) with ESMTP id B2B98140CCC;
Mon, 10 Apr 2006 15:29:52 +0200 (CEST)
Received: from mx2.kth.se ([127.0.0.1])
by localhost (mx2.kth.se [127.0.0.1]) (amavisd-new,
port 10024) with LMTP
id 31983-01-65; Mon, 10 Apr 2006 15:29:50 +0200 (CEST)
Received: from mail.lysator.liu.se (mail.lysator.liu.se [130.236.254.3])
by mx2.kth.se (Postfix) with ESMTP id 2C896140CC4;
Mon, 10 Apr 2006 15:29:50 +0200 (CEST)
Received: from localhost (localhost.localdomain [127.0.0.1])
by mail.lysator.liu.se (Postfix) with ESMTP id D6DD8200A218;
Mon, 10 Apr 2006 15:29:47 +0200 (CEST)
Received: from mail.lysator.liu.se ([127.0.0.1])
by localhost (lenin.lysator.liu.se [127.0.0.1]) (amavisd-new,
port 10024)
with LMTP id 28145-01-2; Mon, 10 Apr 2006 15:29:47 +0200 (CEST)
Received: from sellafield.lysator.liu.se (sellafield.lysator.liu.se
[130.236.254.103])
(using TLSv1 with cipher EDH-RSA-DES-CBC3-SHA (168/168 bits))
(No client certificate requested)
by mail.lysator.liu.se (Postfix) with ESMTP id 27F01200A1FB;
Mon, 10 Apr 2006 15:29:47 +0200 (CEST)
Received: from sellafield.lysator.liu.se (localhost [127.0.0.1])
by sellafield.lysator.liu.se (8.13.4+Sun/8.13.4) with ESMTP id
k3ADTh92029693; Mon, 10 Apr 2006 15:29:44 +0200 (MEST)
Received: (from nisse@localhost)
by sellafield.lysator.liu.se (8.13.4+Sun/8.12.8/Submit) id
k3ADTbk5029690; Mon, 10 Apr 2006 15:29:38 +0200 (MEST)
X-Authentication-Warning: sellafield.lysator.liu.se: nisse set sender to
nisse@lysator.liu.se using -f
To: Tomas Olsson <tol@stacken.kth.se>
Subject: Re: is cache-only-prefixes an nnpfs limitation?
References: <x3mzf1bugb.fsf@nowhere.com> <lsrpsjxtyim.fsf@kashyyyk.ite.kth.se>
<x33bgskjcm.fsf@nowhere.com> <lsrpsjwsbe8.fsf@kashyyyk.ite.kth.se>
<x38xqetym2.fsf@nowhere.com> <lsrfykmpliu.fsf@kashyyyk.ite.kth.se>
<x364li48qs.fsf@nowhere.com> <lsry7ydoow0.fsf@kashyyyk.ite.kth.se>
From: nisse@lysator.liu.se (=?iso-8859-1?q?Niels_M=F6ller?=)
Date: 10 Apr 2006 15:29:30 +0200
In-Reply-To: <lsry7ydoow0.fsf@kashyyyk.ite.kth.se>
Message-ID: <nnlkud7e4l.fsf@sellafield.lysator.liu.se>
Lines: 26
User-Agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.3
MIME-Version: 1.0
X-Virus-Scanned: by amavisd-new-20030616-p10 (Debian) at lysator.liu.se
X-Virus-Scanned: by amavisd-new at kth.se
X-Spam-Status: No, hits=-4.9 tagged_above=-200.0 required=5.0 tests=BAYES_00
X-Spam-Level:
Cc: Adam Megacz <megacz@cs.berkeley.edu>,
arla-drinkers@stacken.kth.se
X-BeenThere: arla-drinkers@stacken.kth.se
X-Mailman-Version: 2.1.6
Precedence: list
List-Id: Arla discussions <arla-drinkers.stacken.kth.se>
List-Unsubscribe: <https://lists.stacken.kth.se/mailman/listinfo/arla-drinkers>,
<mailto:arla-drinkers-request@stacken.kth.se?subject=unsubscribe>
List-Archive: <http://lists.stacken.kth.se/pipermail/arla-drinkers>
List-Post: <mailto:arla-drinkers@stacken.kth.se>
List-Help: <mailto:arla-drinkers-request@stacken.kth.se?subject=help>
List-Subscribe: <https://lists.stacken.kth.se/mailman/listinfo/arla-drinkers>,
<mailto:arla-drinkers-request@stacken.kth.se?subject=subscribe>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: arla-drinkers-bounces@stacken.kth.se
Errors-To: arla-drinkers-bounces@stacken.kth.se
X-Virus-Scanned: by amavisd-new at kth.se
Tomas Olsson <tol@stacken.kth.se> writes:
> Currently arlad takes care of all cache replacement things, on a node
> level. The problem is that it's really nnpfs that gets all the syscalls and
> knows what nodes are used, so arlad just somes up with nodes that it
> *thinks* are not recently used, and says "can these be dropped?".
>
> For blocks (especially when we start talking about files larger than your
> cache) things get more complicated. So we figured it's time for nnpfs to
> use the information available to it, and assume responsibility for the LRU.
One possibly naive idea:
1. Let arlad keep the responsibility for cache management.
2. Let nnpfs keep track of the 1000 most recent operations (or most
recently accessed blocks, whatever). When the buffer with
information about 1000 operations is full, dump that information on
arlad and forget it.
The idea is that one call from nnpfs to arlad per 1000 file operations
should be a fairly small overhead, and then most of the complexity and
data structures can stay in userspace.
Regards,
/Niels
_______________________________________________
Arla-drinkers mailing list
Arla-drinkers@stacken.kth.se
https://lists.stacken.kth.se/mailman/listinfo/arla-drinkers
