Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 7 Aug 2002 01:12:07 +0400 (MSD)
From:      "."@babolo.ru
To:        friar_josh@webwarrior.net (Josh Paetzel)
Cc:        spock@tkb.pl, hackers@FreeBSD.ORG
Subject:   Re: FreeBSD performing worse than Linux?
Message-ID:  <200208062112.BAA19069@aaz.links.ru>
In-Reply-To: <200208060848.53601.friar_josh@webwarrior.net> from "Josh Paetzel" at "Aug 6, 2 08:48:53 am"

next in thread | previous in thread | raw e-mail | index | archive | help
Josh Paetzel writes:
[Charset iso-8859-1 unsupported, filtering to ASCII...]
> On Tuesday 06 August 2002 05:48, Marcin Jurczuk wrote:
> > On Wed, 28 Nov 2001, Josh Paetzel wrote:
> > > Well, I am seeing dismal ftp performance on my 4.x boxes.  I have a
> > > network of 4 machines, three of which are running -STABLE from Nov
> > > 22.  The other machine is running NetBSD 1.5.2 Release.  One of the
> > > FreeBSD machines has a  base 10 cards in it and has reasonable
> > > performace with ftp transfer rates around 1.1Megs/sec.  The NetBSD
> > > machine is a sparcstation 10 with an onboard intel base 10 adapter,
> > > and it too sees reasonable ftp performance.  The other two -STABLE
> > > boxes have 100tx cards in them.  One is a Linksys LNE100TX, and the
> > > other is an intel Pro 10/100B/100+.  The hub for this network is an 8
> > > port SOHOware autosensing affair.  Both of the 100 cards
> > > auto-negotiate to 100tx half-duplex.  I can get appoximately
> > > 1.5Megs/sec out of them using ftp.  I have tried swapping cables,
> > > swapping ports, and replacing the hub with a crossover cable and
> > > manually configuring the cards for either full or half duplex
> > > operation.  None of these steps makes any difference at all.  I can
> > > reliably duplicate my transfer speeds on a 600 meg file with a std.
> > > deviation of less than a half a second no matter what network
> > > configuration I use.  My next step will be to try some different NICs,
> > > but I don't have anything here that is 100tx based to swap with.  I
> > > have gotten proper transfer rates out of these machines in the past,
> > > but I don't remember if the network cards have changed since then.  I
> > > rarely move large files around at all, and so only looked into this as
> > > a curiosity when seeing this thread.  I also intend to try some NFS
> > > mounts out to see if this is a protocol issue or not.
> > 
> > I have two 4.6 servers, and one 4.5 firewall with mostly two type cards:
> > Intel Pro 10/100 and Intelinet 10/100 (rtl8139C).
> > Two segments of network, one is on Cisco Catalyst 2900 second built on
> > ATI 8224 10/100 switch. On both solutions transfers are around 8-9 MB/s
> > betwen FBSD-> FSDB, FBSD->Linux, Linux-FBSD.
> > All of those cards work on 100 Mbps/Full Duplex mode..
> > 
> > I didn't notice any strange behavior on FreeBSD, only Linux show messeges
> > like:
> > eth0: card reports no resources.
> > eth0: card reports no resources.
> > but there is no slow down because of this message...
> > 
> > Best regards.
> > 
> > -- 
> > Marcin Jurczuk -> spock@tkb.pl
> > UNIX/Network Administrator
> > Bialystok Cable Television
> > 
> 
> I administrate some machines on two subnets, connected via a Catalyst 1900.  
> All of the cards on all of the machines loop up at 100tx full-duplex.  There 
> are 3 different w2k boxes, and 5 FreeBSD -STABLE boxes from two weeks ago.  
> My ftp performance is completely bizzare.  Between each FBSD machine, there 
> is a different level of performance, and it's directional, too.  Machine A to 
> Machine B might be 10Megs/sec, while the reverse is only 6Megs/sec.  then A 
> to C will be totally different, and C to A different again, and so on and so 
> forth.  About half the connections are in a reasonable transfer rate 
> (8-10Megs/sec)  the other half range from 4Megs/sec-7Megs/sec.  The cards are 
> a grab bag of realtek 8139s, intel pros, 3com905s and so forth.  swapping 
> cards makes no difference.  I've tried different switches and it makes to 
> difference.  I compared ALL of the sysctl knobs on all the machines and they 
> were all identical (save what you would expect to be different).  My network 
> at home has an SGI box, a sparc, and  3 PCs running irix, solaris 9, and 
> FreeBSD STABLE from today.  I can do 10Megs/sec all day long from one machine 
> to another in either direction, and yeah, the sysctl knobs are the same as 
> the "sick" network.  
> 
> I intend to reinstall as many of the machines as I can this weekend to see if 
> it makes any difference....oh yeah, one last tidbit.  On the "sick" network, 
> the Windows machines can do 10Megs/sec between each other, but only 4-6 to 
> the FreeBSD machines.  As the previous poster noted, the speeds are 
> repeatable.  If a machine does 6M/sec to another machine, it will repeat that 
> endlessly, regardless of port, nic, switch, cable, or anything else I can 
> think of to change.
What about difference
in communications with 127.0.0.1
?

-- 
@BABOLO      http://links.ru/

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




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200208062112.BAA19069>