From: Joel Soete <soete.joel@tiscali.be>
To: Grant Grundler <grundler@parisc-linux.org>
Cc: parisc-linux@parisc-linux.org
Subject: Re: [parisc-linux] ipv6 problem with 2.6.7-pa1
Date: Sun, 27 Jun 2004 14:59:56 +0000 [thread overview]
Message-ID: <40DEE0EC.5040700@tiscali.be> (raw)
In-Reply-To: <20040623050009.GB27085@colo.lackof.org>
Hello all,
I find interesting to report the success of following test on my c110 with k-2.6.7-pa1 + ncr patch:
* I just tar my kernel src tree in a 'big' file of about 200Mb (previous patch that was enough to crash the system)
* I scp (ipv4 first) this file to my pc (it takes about 4:15 with a 10Mb nic that's a rate of less then 1MB/s Ok for me)
(i do this from hppa to pc because Guy's report indicates that tx stuff was the pb)
* I recompile the kernels (pc & hppa) to add just CONFIG_EXPERIMENTAL & CONFIG_IPV6 (also CONFIG_IPV6_PRIVACY don't know yet if
required)
* refering to <http://people.debian.org/~csmall/ipv6/setup.html> and with Guy's help, after reboot I choose the simplest way and
* config my second pc nic with 'ifconfig eth1 add 2001:0db8:0005:0006::79/64'
* config the buildin nic of my hppa with: 'ifconfig eth0 add 2001:db8:5:6::78/64'
* i can ping6 (added thanks to iputils-ping dpkg) each other ;)
* I just add those to ip6 address to my /etc/hosts:
2001:db8:5:6::78 hpal-ip6
2001:db8:5:6::79 sidh-ip6
* i re-launch scp of previous 200Mb file from hppa to pc and all is Ok ;)
* and do the reverse (pc to hppa) with same success (just a bit slowest: ie 4:47 min in place of 04:12)
Cheers,
Joel
Grant Grundler wrote:
> On Tue, Jun 22, 2004 at 07:09:33PM +0200, Joel Soete wrote:
>
>>Very intersecting, c3k is using a tulip as builtin nic (iirc) and
>>not ccio-dma.
>
>
> c3k is using sba_iommu.c instead.
>
>
>>OTC d250 (as well as c110) uses LASI ASIC interface.
>>
>>Grant could you let me know if this last nic also interface with ccio-dma?
>
>
> Yes. All IO goes through the IOMMU when it's part of the system.
>
>
>>even over my ncr patch on this d model?
>
>
> seems jejb would prefer to see your patch get committed and then
> move upstream.
>
>
>>Is this kind of interface also use the scatter/gather list?
>
>
> NICs don't scatter gather. They only map a single buffer at
> a time.
>
> grant
>
_______________________________________________
parisc-linux mailing list
parisc-linux@lists.parisc-linux.org
http://lists.parisc-linux.org/mailman/listinfo/parisc-linux
next parent reply other threads:[~2004-06-27 14:59 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20040622005559.GA24406@sal.ucc.ie>
[not found] ` <40BD9F050000D9F3@ocpmta1.freegates.net>
[not found] ` <20040623050009.GB27085@colo.lackof.org>
2004-06-27 14:59 ` Joel Soete [this message]
2004-06-27 16:11 ` [parisc-linux] ipv6 problem with 2.6.7-pa1 M. Grabert
2004-06-27 16:50 ` Joel Soete
[not found] ` <20040627170842.GC8740@sal.ucc.ie>
2004-06-27 17:40 ` Joel Soete
[not found] ` <40DF0BAE.2000406@tiscali.be>
[not found] ` <20040627192754.GA9095@sal.ucc.ie>
2004-06-27 20:48 ` Joel Soete
[not found] <20040621153015.596e4014.gmsoft@gentoo.org>
2004-06-21 14:24 ` Kyle McMartin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=40DEE0EC.5040700@tiscali.be \
--to=soete.joel@tiscali.be \
--cc=grundler@parisc-linux.org \
--cc=parisc-linux@parisc-linux.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.