From mboxrd@z Thu Jan  1 00:00:00 1970
MIME-Version: 1.0
In-Reply-To: <AANLkTikkxwva0SM+V+GQeFnpTw2Rn568+5YSwfziBwn2@mail.gmail.com>
References: <20101115032531.GB27578@opal.ai.ki>
	<AANLkTimYpajcVoFPVVRGnWqVaaO8vH4y7NGnCc+UAh7k@mail.gmail.com>
	<AANLkTikkxwva0SM+V+GQeFnpTw2Rn568+5YSwfziBwn2@mail.gmail.com>
Date: Mon, 15 Nov 2010 23:18:16 +0100
Message-ID: <AANLkTi=fPQ0iM2jTN97EA1PnBR06zQv0UxB6WhmRz6q2@mail.gmail.com>
From: Yaroslav <yarikos@gmail.com>
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Subject: Re: [9fans] 9p vs http
Topicbox-Message-UUID: 80d18d64-ead6-11e9-9d60-3106f5b1d025

> That brings up a question of interest to me. =C2=A0How do you effectively
> read ahead with the 9p protocol? =C2=A0Even if you issued many read
> requests in parallel, the server is allowed to return less data than
> was asked for. =C2=A0You'll end up with holes in your buffer that require
> at least another roundtrip to fill.

The option is to make servers obey R order for Ts with same tag - just
as Russ (right?) proposed elsewhere on the list.