Menu
▾
▴
Re: [E1000-devel] Bug report E1000 driver bonding in 802.3ad mode can not go beyond 1GB/s throughput
|
From: Support T. <su...@ca...> - 2009-03-27 21:17:44
|
Hi John, Thanks for your help. Our kernel version is 2.4.36.9, may be in the process moving to 2.4.37 soon. If you could send us the patch for the change, we can try to apply it to our kernel code. Thanks! RD -----Original Message----- From: Ronciak, John [mailto:joh...@in...] Sent: Friday, March 27, 2009 2:00 PM To: su...@ca...; 'Jay Vosburgh' Cc: e10...@li... Subject: [work] RE: [E1000-devel] Bug report E1000 driver bonding in 802.3ad mode can not go beyond 1GB/s throughput 802.3ad is not part of the e1000 or e1000e driver. That's why he was asking about what kernel version you are using. He needs to know the exact kernel version to be able to tell. Cheers, John ----------------------------------------------------------- "...that your people will judge you on what you can build, not what you destroy.", B. Obama, 2009 >-----Original Message----- >From: Support Team [mailto:su...@ca...] >Sent: Friday, March 27, 2009 1:55 PM >To: Ronciak, John; 'Jay Vosburgh' >Cc: e10...@li... >Subject: RE: [E1000-devel] Bug report E1000 driver bonding in >802.3ad mode can not go beyond 1GB/s throughput > >Hi John, > >On the e1000.sf.net, there is only E1000 driver 8.0.6 >September 8, 2008, >which is the same we >are using. Jay said he fixed a big in 802.3ad couple weeks ago. that >version driver is not on >the site. Where can we get that updated driver? > >Thx so much, > >RD > >-----Original Message----- >From: Ronciak, John [mailto:joh...@in...] >Sent: Friday, March 27, 2009 1:38 PM >To: su...@ca...; 'Jay Vosburgh' >Cc: e10...@li... >Subject: [work] RE: [E1000-devel] Bug report E1000 driver >bonding in 802.3ad >mode can not go beyond 1GB/s throughput > >Our (Intel) latest drivers are on our http://e1000.sf.net site >including he >igb driver. When you ask about the driver below I assume you >are talking >about bonding right? > >Please let us know how this goes. I haven't found our testing >lead to ask >about this since our last mail but I track him down and ask. > >Cheers, >John >----------------------------------------------------------- >"...that your people will judge you on what you can build, not what you >destroy.", B. Obama, 2009 > > >>-----Original Message----- >>From: Support Team [mailto:su...@ca...] >>Sent: Friday, March 27, 2009 1:25 PM >>To: 'Jay Vosburgh' >>Cc: Ronciak, John; e10...@li... >>Subject: Re: [E1000-devel] Bug report E1000 driver bonding in >>802.3ad mode can not go beyond 1GB/s throughput >> >>Hi Jay, >> >>Thanks for writing back regarding this matter. We use latest >>2.4 kernel >>from kernel.org. For E1000 driver, >>we download it from Intel web site. If you have newer driver >>somewhere we >>can download. We will download that >>and give it a try. >> >>Basically in our setup, both 82546 NIC based setup and 82573 >>based setup >>using the same os and same kernel, >>bonding configuration. the only difference in software is the >>driver: E1000E >>vs. E1000. E1000E driver >>working well, E1000 does not. We also plan to test igb driver >>bonding for >>the newest Intel NIC chip. >> >>Thanks for your help! >>Wayne >> >>-----Original Message----- >>From: Jay Vosburgh [mailto:fu...@us...] >>Sent: Friday, March 27, 2009 12:44 PM >>To: su...@ca... >>Cc: 'Ronciak, John'; e10...@li... >>Subject: [work] Re: [E1000-devel] Bug report E1000 driver >>bonding in 802.3ad >>mode can not go beyond 1GB/s throughput >> >>Support Team <su...@ca...> wrote: >> >>>Yes, same VLAN setup in the software does not work for 82546 >>chip. The >>>setup in software are identical, >>>other than 82546 load E1000 driver and 82573 load E1000E >>driver, nothing >>>else changed in software or >>>test environment. If we can see 82546/MT adapter can get >>2GB/s in bond >>>mode, we will be happy. >> >> Some bonding things to check: >> >>ip route show >> >> Make sure no interfaces (the slaves) have routes that supercede >>the route for the bond itself. >> >>cat /proc/net/bonding/bond0 [or whatever bond device you have] >> >> Make sure the options you think you have match what bonding is >>seeing (particularly the xmit_hash_policy if your throughput test is >>many connections but not many discrete peers). >> >> Also in the proc file, make sure the 802.3ad is aggregating >>properly; are all of the slaves in the active aggregator? >> >> Lastly, what distro (cat /etc/issue) and kernel version are you >>running (uname -a)? >> >> I fixed a bug in 802.3ad related to aggregator assignments a >>couple of weeks ago. If you've got a sufficiently recent kernel (the >>bug was introduced late last year), you might be seeing that (if the >>slaves don't aggregate properly). I observed the bug messing >>up 802.3ad >>aggregations with my e1000 devices, so it might be that. >> >> -J >> >>--- >> -Jay Vosburgh, IBM Linux Technology Center, fu...@us... >> >> >> > > |
