From mboxrd@z Thu Jan  1 00:00:00 1970
X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN: AS6939 64.71.128.0/18
X-Spam-Status: No, score=-2.6 required=3.0 tests=AWL,BAYES_00,
 MSGID_FROM_MTA_HEADER,URIBL_BLOCKED shortcircuit=no autolearn=unavailable
 version=3.3.2
Path: news.gmane.org!not-for-mail
From: Eric Wong <normalperson@yhbt.net>
Newsgroups: gmane.comp.lang.ruby.kgio.general
Subject: Re: [PATCH] preliminary implementation of "smart_nopush"
Date: Sat, 29 Jan 2011 04:34:15 +0000
Message-ID: <20110129043415.GB881@dcvr.yhbt.net>
References: <20110128035142.GB10919@dcvr.yhbt.net>
 <20110128071831.GA3265@dcvr.yhbt.net> <20110128093345.GB24894@dcvr.yhbt.net>
 <20110129043038.GA881@dcvr.yhbt.net>
NNTP-Posting-Host: lo.gmane.org
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
X-Trace: dough.gmane.org 1296275681 17673 80.91.229.12 (29 Jan 2011 04:34:41
 GMT)
X-Complaints-To: usenet@dough.gmane.org
NNTP-Posting-Date: Sat, 29 Jan 2011 04:34:41 +0000 (UTC)
To: kgio@librelist.org
Original-X-From: kgio@librelist.org Sat Jan 29 05:34:34 2011
Return-path: <kgio@librelist.org>
Envelope-to: gclrkg-kgio@m.gmane.org
List-Archive: <http://librelist.com/archives/kgio/>
List-Help: <http://librelist.com/help.html>
List-Id: <kgio-public@bogomips.org>
List-Post: <mailto:kgio@librelist.org>
List-Subscribe: <mailto:kgio-subscribe@librelist.com>
List-Unsubscribe: <mailto:kgio-unsubscribe@librelist.com>
Precedence: list
Original-Sender: kgio@librelist.org
Xref: news.gmane.org gmane.comp.lang.ruby.kgio.general:4
Archived-At: <http://permalink.gmane.org/gmane.comp.lang.ruby.kgio.general/4>
Received: from zedshaw.xen.prgmr.com ([64.71.167.205]) by lo.gmane.org with
 esmtp (Exim 4.69) (envelope-from <kgio@librelist.org>) id 1Pj2WA-00079I-He
 for gclrkg-kgio@m.gmane.org; Sat, 29 Jan 2011 05:34:34 +0100
Received: from zedshaw.xen.prgmr.com (localhost [IPv6:::1]) by
 zedshaw.xen.prgmr.com (Postfix) with ESMTP id 1531721C594 for
 <gclrkg-kgio@m.gmane.org>; Sat, 29 Jan 2011 04:47:48 +0000 (UTC)

I'm thinking about reverting this patch in favor of improving
libautocork which is more general (but eventually I want this to be a
set-and-forget kernel option that's easy for app authors to use).

Here's what I posted to the Rainbows! list:

Eric Wong <normalperson@yhbt.net> wrote:
> I started working on some patches for libautocork here at the moment
>   http://bogomips.org/libautocork.git
> 
> If we can prove it works for more cases, I'll push for it to become a
> kernel option that is fire-and-forget on the listen socket so
> applications won't have to keep track of when to cork/uncork sockets
> anymore.
> 
> I'll probably revert the change to kgio since kgio can't track close()
> (nor SSL_read/SSL_write afaik if/when kgio gets SSL support)...
> 
> I will do some live testing once I get rid of the hard-coded descriptor
> limit and make it thread-safe.

-- 
Eric Wong