Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 26 Jun 1997 16:54:03 +0900
From:      Kenjiro Cho <kjc@csl.sony.co.jp>
To:        Bill Fenner <fenner@parc.xerox.com>
Cc:        Chris Csanady <ccsanady@friley01.res.iastate.edu>, hackers@FreeBSD.ORG
Subject:   Re: TCP/IP bug? Unnecessary fragmentation... 
Message-ID:  <199706260754.QAA13876@hotaka.csl.sony.co.jp>
In-Reply-To: Your message of "Wed, 25 Jun 1997 13:13:43 PDT." <97Jun25.131348pdt.177513@crevenia.parc.xerox.com> 

next in thread | previous in thread | raw e-mail | index | archive | help

Bill Fenner wrote:
>> Kenjiro Cho <kjc@csl.sony.co.jp> wrote:
  >I think, considering the wide use of TCP, the socket layer should try
  >to call tcp_usr_send all at once when possible.

>> That would be going backwards, to some extent.  Van Jacobson wrote
>> in a 1988 message about upping TCP stack performance:

Hmmm, was the Nagle algorithm already implemented back then?

The modified sosend ends up with a long delay when divided chunks
trigger the Nagle Algorithm.
It seems worse than the possible gain by parallelism.

--kj

---
Kenjiro Cho
Sony Computer Science Laboratory Inc.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199706260754.QAA13876>