Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 12 Jun 1996 04:48:39 -0700
From:      David Greenman <davidg@Root.COM>
To:        bill@twwells.com (T. William Wells)
Cc:        freebsd-questions@FreeBSD.ORG
Subject:   Re: weird transfer rates 
Message-ID:  <199606121148.EAA00840@Root.COM>
In-Reply-To: Your message of "12 Jun 1996 01:55:31 EDT." <4plm4j$3k6@twwells.com> 

next in thread | previous in thread | raw e-mail | index | archive | help
>I have three machines, ux1, admin, and news, all on the same
>ethernet. Ux1 is running 2.1-RELEASE and is our shell account
>server; it also runs a web server (wn). Admin is used for general
>administrative functions and also serves as a mail gateway. News
>is for our news machine. Admin and news are our primary and
>secondary nameservers.  Ux1 and news are running 2.1-release;
>admin is running the first 2.1-stable. None of these machines are
>horribly loaded. (Disk rates are reasonable and load averages
>rarely above 2.)
>
>Transfers between ux1 and admin are normal.
>Transfers between news and admin are normal.
>FTP *from* ux1 to news is normal.
>FTP *to* ux1 from news is slow, like <10k/sec.
>
>The question is: since it isn't a matter of load, where should I
>begin looking to find the problem?

   It sounds like input packets are getting dropped on ux1. What type of
ethernet card is in that machine? What do the TCP statistics (netstat -s)
have to say about the problem? How about the interface stats (netstat -i)?

-DG

David Greenman
Core-team/Principal Architect, The FreeBSD Project



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199606121148.EAA00840>