netdev
[Top] [All Lists]

Re: [Ksummit-2005-discuss] Summary of 2005 Kernel Summit Proposed Topics

To: Andrea Arcangeli <andrea@xxxxxxx>
Subject: Re: [Ksummit-2005-discuss] Summary of 2005 Kernel Summit Proposed Topics
From: Andi Kleen <ak@xxxxxx>
Date: 30 Mar 2005 18:02:55 +0200
Date: Wed, 30 Mar 2005 18:02:55 +0200
Cc: jamal <hadi@xxxxxxxxxx>, Dmitry Yusupov <dmitry_yus@xxxxxxxxx>, James Bottomley <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx>, Rik van Riel <riel@xxxxxxxxxx>, mpm@xxxxxxxxxxx, michaelc@xxxxxxxxxxx, open-iscsi@xxxxxxxxxxxxxxxx, ksummit-2005-discuss@xxxxxxxxx, netdev <netdev@xxxxxxxxxxx>
In-reply-to: <20050330154418.GE32111@xxxxxxxxx>
References: <Pine.LNX.4.61.0503272245350.30885@xxxxxxxxxxxxxxxxxxxxxxxxxxx> <m1zmwn21hk.fsf@xxxxxx> <1112027284.5531.27.camel@mulgrave> <20050329152008.GD63268@xxxxxx> <1112116762.5088.65.camel@beastie> <1112130512.1077.107.camel@xxxxxxxxxxxxxxxx> <20050330152208.GB12672@xxxxxx> <20050330153313.GD32111@xxxxxxxxx> <20050330153948.GE12672@xxxxxx> <20050330154418.GE32111@xxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mutt/1.4.1i
On Wed, Mar 30, 2005 at 05:44:18PM +0200, Andrea Arcangeli wrote:
> On Wed, Mar 30, 2005 at 05:39:48PM +0200, Andi Kleen wrote:
> > An unsolveable one IMHO. You can just try to be good enough. For that
> 
> I think it's solvable with an algorithm I outlined several emails ago.

The problem with you algorithm is that you cannot control
how to NIC puts incoming packets into RX rings (and then 
actually if the packets you are interested in do actually arrive from
the net ,-)

While some NICs have hardware support to get high priority
packets into different queues these tend to add nasty limits
on the max number of connections. Which IMHO is not acceptable.

"We have an enterprise class OS with iSCSI which can only
support four swap devices"

-Andi

<Prev in Thread] Current Thread [Next in Thread>