Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 24 Feb 1998 15:53:30 +1100
From:      "Joe Shevland" <joe.shevland@horizonti.com>
To:        <freebsd-java@FreeBSD.ORG>
Subject:   Re: Socket IO problems using Java Sockets on FreeBSD
Message-ID:  <199802240508.VAA04864@hub.freebsd.org>

next in thread | raw e-mail | index | archive | help
----------
> From: Alex Boisvert <alex@gel.usherb.ca>
> To: Iyer Mahadevan <iyer@internetdevices.com>
> Cc: java@FreeBSD.ORG; saurabh@internetdevices.com; freebsd-java@FreeBSD.ORG; java-port@FreeBSD.ORG
> Subject: Re: Socket IO problems using Java Sockets on FreeBSD
> Date: Tuesday, 24 February 1998 13:13
> 
> On Mon, 23 Feb 1998, Iyer Mahadevan wrote:
> > I noticed some serious performance problems with Java Socket I/O.
> > 
> I don't know why Nagle's algorithm is the default...  This may be
> platform-specific.  Anyway, this shows up on Windows NT as well.

I'm pretty sure Nagle's algorithm is the default for all implementations
of TCP/IP purely because of the overhead associated with the various
packet headers etc. i.e. be careful with the TCP_NODELAY flag.

Interesting to know how much data exactly was used in the benchmarks,
and whether 5 samples are enough statistically speaking.

**********************************************************************
Joe Shevland - Horizon Technologies International

Email:      joe.shevland@horizonti.com

We are all in the gutter, but some of us are looking
at the stars - Oscar Wilde

**********************************************************************

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-java" in the body of the message



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199802240508.VAA04864>