<html><head><style type='text/css'>p { margin: 0; }</style><style type='text/css'>body { font-family: 'Times New Roman'; font-size: 12pt; color: #000000}</style></head><body>Try the linux commands "ls" "cd". They'll let you list files and change directories.<br><br>----- Original Message -----<br>From: "ashok bharat bayana" <ashok.bharat.bayana@iiitb.ac.in><br>To: lustre-discuss@lists.lustre.org, lustre-discuss@lists.lustre.org<br>Sent: Monday, March 3, 2008 1:37:02 AM GMT -05:00 US/Canada Eastern<br>Subject: Re: [Lustre-discuss] Root file system access though telnet<br><br>
<title>RE: Root file system access though telnet</title>
<!-- Converted from text/plain format -->
<br>
<p><font size="2">Hi,<br>
I want to know how root file system can be accessed through telnet.Actualy I connected to server through telnet and I want to access my root file system. can anyone tell me, how to access it.<br>
<br>
Thanks and Regards,<br>
Ashok Bharat<br>
<br>
<br>
-----Original Message-----<br>
From: lustre-discuss-bounces@lists.lustre.org on behalf of lustre-discuss-request@lists.lustre.org<br>
Sent: Fri 2/29/2008 1:56 PM<br>
To: lustre-discuss@lists.lustre.org<br>
Subject: Lustre-discuss Digest, Vol 25, Issue 59<br>
<br>
Send Lustre-discuss mailing list submissions to<br>
lustre-discuss@lists.lustre.org<br>
<br>
To subscribe or unsubscribe via the World Wide Web, visit<br>
<a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
or, via email, send a message with subject or body 'help' to<br>
lustre-discuss-request@lists.lustre.org<br>
<br>
You can reach the person managing the list at<br>
lustre-discuss-owner@lists.lustre.org<br>
<br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of Lustre-discuss digest..."<br>
<br>
<br>
Today's Topics:<br>
<br>
1. Re: Configuration of lustre FS on single node (Amit Sharma)<br>
2. Re: Configuration of lustre FS on single node<br>
(ashok bharat bayana)<br>
3. Re: Configuration of lustre FS on single node (Amit Sharma)<br>
<br>
<br>
----------------------------------------------------------------------<br>
<br>
Message: 1<br>
Date: Fri, 29 Feb 2008 12:17:52 +0530<br>
From: Amit Sharma <Amit.Sharma@Sun.COM><br>
Subject: Re: [Lustre-discuss] Configuration of lustre FS on single<br>
node<br>
To: ashok bharat bayana <ashok.bharat.bayana@iiitb.ac.in><br>
Cc: lustre-discuss@lists.lustre.org<br>
Message-ID: <47C7AA98.9010603@sun.com><br>
Content-Type: text/plain; format=flowed; charset=ISO-8859-1<br>
<br>
Ashok,<br>
<br>
Just looking at the command you tried :<br>
> $ mkfs.lustre --fsname spfs --mdt --mgs /dev/sda<br>
<br>
You may have wrecked your root file system. Or is /dev/sda some other<br>
device ?<br>
<br>
It may be simpler for you to try llmount.sh to get a simple setup of<br>
lustre on a single node (with loop back mounts)<br>
<br>
thanks,<br>
Amit<br>
<br>
ashok bharat bayana wrote:<br>
><br>
> Hello,<br>
> I successfully build lustre(1.6.4.2) on my system for a patchless client<br>
> But I dont know how to proceed in configuring the file system.<br>
><br>
> I'm trying to build all MDS,client and MDT's on a single node.<br>
> >From the tutorials I came to know that<br>
><br>
> First, create an MDT for the "spfs" file system that uses the /dev/sda<br>
> disk. This MDT also acts as the MGS for the site.<br>
><br>
> $ mkfs.lustre --fsname spfs --mdt --mgs /dev/sda<br>
><br>
> But by triggering this command my system crashed in which the whole data<br>
> is lost and again I need to install the OS.<br>
> I want help in proceeding of mounting a lustre file system.<br>
><br>
> Thanks and Regards,<br>
> Ashok Bharat<br>
><br>
> -----Original Message-----<br>
> From: lustre-discuss-bounces@lists.lustre.org on behalf of<br>
> lustre-discuss-request@lists.lustre.org<br>
> Sent: Wed 2/27/2008 10:30 PM<br>
> To: lustre-discuss@lists.lustre.org<br>
> Subject: Lustre-discuss Digest, Vol 25, Issue 56<br>
><br>
> Send Lustre-discuss mailing list submissions to<br>
> lustre-discuss@lists.lustre.org<br>
><br>
> To subscribe or unsubscribe via the World Wide Web, visit<br>
> <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
> or, via email, send a message with subject or body 'help' to<br>
> lustre-discuss-request@lists.lustre.org<br>
><br>
> You can reach the person managing the list at<br>
> lustre-discuss-owner@lists.lustre.org<br>
><br>
> When replying, please edit your Subject line so it is more specific<br>
> than "Re: Contents of Lustre-discuss digest..."<br>
><br>
><br>
> Today's Topics:<br>
><br>
> 1. Multiple NICs per OST (Joshua Bower-Cooley)<br>
> 2. obd error on MGS/MDT node (Jeremy Mann)<br>
><br>
><br>
> ----------------------------------------------------------------------<br>
><br>
> Message: 1<br>
> Date: Tue, 26 Feb 2008 11:55:19 -0800<br>
> From: Joshua Bower-Cooley <jbowercooley@lcogt.net><br>
> Subject: [Lustre-discuss] Multiple NICs per OST<br>
> To: lustre-discuss@lists.lustre.org<br>
> Message-ID: <200802261155.19907.jbowercooley@lcogt.net><br>
> Content-Type: text/plain; charset="utf-8"<br>
><br>
> Hi-<br>
> I've had lustre running happily for some time over a single 10g ethernet NIC<br>
> per node. After switching to dual 10g and creating a new filesystem<br>
> (1.6.4.2), I'm seeing nothing but keep-alive packets with bad checksums.<br>
><br>
> What is the current "correct" way to do this now? The manual suggest not<br>
> using<br>
> bonding, but several list postings now reccommend it. Without bonding, do I<br>
> need to have my 2 switches stacked, or will Lustre recognize the division in<br>
> my subnet?<br>
><br>
> LNET module options I've tried are:<br>
> 1) networks="tcp0(eth2,eth3)"<br>
> 2) ip2nets="tcp(eth2,eth3); tcp(eth2) 10.9.[1-4].*; tcp(eth3) 10.9.[5-8].*;"<br>
> and many other variations<br>
><br>
> All other services are functional on both interfaces.<br>
><br>
> Thanks in advance,<br>
> J Bower-Cooley<br>
> Scientific Systems Engineer<br>
> Las Cumbres Observatory Global Telescope<br>
><br>
><br>
> ------------------------------<br>
><br>
> Message: 2<br>
> Date: Wed, 27 Feb 2008 09:50:08 -0600 (CST)<br>
> From: "Jeremy Mann" <jeremy@biochem.uthscsa.edu><br>
> Subject: [Lustre-discuss] obd error on MGS/MDT node<br>
> To: lustre-discuss@lists.lustre.org<br>
> Message-ID:<br>
> <62901.24.173.62.147.1204127408.squirrel@biochem.uthscsa.edu><br>
> Content-Type: text/plain;charset=iso-8859-1<br>
><br>
> Today we are starting to see obd_change_cbdata errors on our MGS/MDT node.<br>
> What does this error mean?<br>
><br>
> Version of lustre and kernel is:<br>
><br>
> 2.6.9-42.0.10.EL_lustre-1.6.0.1smp X86_64<br>
><br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> previous similar message<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> previous similar message<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 2<br>
> previous similar messages<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 4<br>
> previous similar messages<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 5<br>
> previous similar messages<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> previous similar message<br>
><br>
> --<br>
> Jeremy Mann<br>
> jeremy@biochem.uthscsa.edu<br>
><br>
> University of Texas Health Science Center<br>
> Bioinformatics Core Facility<br>
> <a href="http://www.bioinformatics.uthscsa.edu" target="_blank">http://www.bioinformatics.uthscsa.edu</a><br>
> Phone: (210) 567-2672<br>
><br>
><br>
><br>
> ------------------------------<br>
><br>
> _______________________________________________<br>
> Lustre-discuss mailing list<br>
> Lustre-discuss@lists.lustre.org<br>
> <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
><br>
><br>
> End of Lustre-discuss Digest, Vol 25, Issue 56<br>
> **********************************************<br>
><br>
><br>
> ------------------------------------------------------------------------<br>
><br>
> _______________________________________________<br>
> Lustre-discuss mailing list<br>
> Lustre-discuss@lists.lustre.org<br>
> <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
<br>
<br>
--<br>
Amit Sharma<br>
Lustre Engineering<br>
Sun Microsystems, Bangalore.<br>
<br>
<br>
------------------------------<br>
<br>
Message: 2<br>
Date: Fri, 29 Feb 2008 12:51:31 +0530<br>
From: "ashok bharat bayana" <ashok.bharat.bayana@iiitb.ac.in><br>
Subject: Re: [Lustre-discuss] Configuration of lustre FS on single<br>
node<br>
To: "Amit Sharma" <Amit.Sharma@Sun.COM><br>
Cc: lustre-discuss@lists.lustre.org<br>
Message-ID: <8626C1B7EB748940BCDD7596134632BE85022B@jal.iiitb.ac.in><br>
Content-Type: text/plain; charset="iso-8859-1"<br>
<br>
hi,<br>
/dev/sda is a non ext3 FS, that's the reason i think, my system crashed.<br>
my linux fs is on /dev/sda8 and an ext3 one So should I go with<br>
<br>
$ mkfs.lustre --fsname spfs --mdt --mgs /dev/sda8<br>
<br>
and proceed?<br>
<br>
and Moreover, to run the llmount.sh or local.sh we should have lmc,lconf and lctl utilities, but these are not provided in lustre1.6.4.2, so that's why I'm going in this way.<br>
<br>
Thanks and Regards,<br>
Ashok Bharat<br>
<br>
<br>
-----Original Message-----<br>
From: Amit Sharma [<a href="mailto:Amit.Sharma@Sun.COM" target="_blank">mailto:Amit.Sharma@Sun.COM</a>]<br>
Sent: Fri 2/29/2008 12:17 PM<br>
To: ashok bharat bayana<br>
Cc: lustre-discuss@lists.lustre.org<br>
Subject: Re: [Lustre-discuss] Configuration of lustre FS on single node<br>
<br>
Ashok,<br>
<br>
Just looking at the command you tried :<br>
> $ mkfs.lustre --fsname spfs --mdt --mgs /dev/sda<br>
<br>
You may have wrecked your root file system. Or is /dev/sda some other<br>
device ?<br>
<br>
It may be simpler for you to try llmount.sh to get a simple setup of<br>
lustre on a single node (with loop back mounts)<br>
<br>
thanks,<br>
Amit<br>
<br>
ashok bharat bayana wrote:<br>
><br>
> Hello,<br>
> I successfully build lustre(1.6.4.2) on my system for a patchless client<br>
> But I dont know how to proceed in configuring the file system.<br>
><br>
> I'm trying to build all MDS,client and MDT's on a single node.<br>
> >From the tutorials I came to know that<br>
><br>
> First, create an MDT for the "spfs" file system that uses the /dev/sda<br>
> disk. This MDT also acts as the MGS for the site.<br>
><br>
> $ mkfs.lustre --fsname spfs --mdt --mgs /dev/sda<br>
><br>
> But by triggering this command my system crashed in which the whole data<br>
> is lost and again I need to install the OS.<br>
> I want help in proceeding of mounting a lustre file system.<br>
><br>
> Thanks and Regards,<br>
> Ashok Bharat<br>
><br>
> -----Original Message-----<br>
> From: lustre-discuss-bounces@lists.lustre.org on behalf of<br>
> lustre-discuss-request@lists.lustre.org<br>
> Sent: Wed 2/27/2008 10:30 PM<br>
> To: lustre-discuss@lists.lustre.org<br>
> Subject: Lustre-discuss Digest, Vol 25, Issue 56<br>
><br>
> Send Lustre-discuss mailing list submissions to<br>
> lustre-discuss@lists.lustre.org<br>
><br>
> To subscribe or unsubscribe via the World Wide Web, visit<br>
> <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
> or, via email, send a message with subject or body 'help' to<br>
> lustre-discuss-request@lists.lustre.org<br>
><br>
> You can reach the person managing the list at<br>
> lustre-discuss-owner@lists.lustre.org<br>
><br>
> When replying, please edit your Subject line so it is more specific<br>
> than "Re: Contents of Lustre-discuss digest..."<br>
><br>
><br>
> Today's Topics:<br>
><br>
> 1. Multiple NICs per OST (Joshua Bower-Cooley)<br>
> 2. obd error on MGS/MDT node (Jeremy Mann)<br>
><br>
><br>
> ----------------------------------------------------------------------<br>
><br>
> Message: 1<br>
> Date: Tue, 26 Feb 2008 11:55:19 -0800<br>
> From: Joshua Bower-Cooley <jbowercooley@lcogt.net><br>
> Subject: [Lustre-discuss] Multiple NICs per OST<br>
> To: lustre-discuss@lists.lustre.org<br>
> Message-ID: <200802261155.19907.jbowercooley@lcogt.net><br>
> Content-Type: text/plain; charset="utf-8"<br>
><br>
> Hi-<br>
> I've had lustre running happily for some time over a single 10g ethernet NIC<br>
> per node. After switching to dual 10g and creating a new filesystem<br>
> (1.6.4.2), I'm seeing nothing but keep-alive packets with bad checksums.<br>
><br>
> What is the current "correct" way to do this now? The manual suggest not<br>
> using<br>
> bonding, but several list postings now reccommend it. Without bonding, do I<br>
> need to have my 2 switches stacked, or will Lustre recognize the division in<br>
> my subnet?<br>
><br>
> LNET module options I've tried are:<br>
> 1) networks="tcp0(eth2,eth3)"<br>
> 2) ip2nets="tcp(eth2,eth3); tcp(eth2) 10.9.[1-4].*; tcp(eth3) 10.9.[5-8].*;"<br>
> and many other variations<br>
><br>
> All other services are functional on both interfaces.<br>
><br>
> Thanks in advance,<br>
> J Bower-Cooley<br>
> Scientific Systems Engineer<br>
> Las Cumbres Observatory Global Telescope<br>
><br>
><br>
> ------------------------------<br>
><br>
> Message: 2<br>
> Date: Wed, 27 Feb 2008 09:50:08 -0600 (CST)<br>
> From: "Jeremy Mann" <jeremy@biochem.uthscsa.edu><br>
> Subject: [Lustre-discuss] obd error on MGS/MDT node<br>
> To: lustre-discuss@lists.lustre.org<br>
> Message-ID:<br>
> <62901.24.173.62.147.1204127408.squirrel@biochem.uthscsa.edu><br>
> Content-Type: text/plain;charset=iso-8859-1<br>
><br>
> Today we are starting to see obd_change_cbdata errors on our MGS/MDT node.<br>
> What does this error mean?<br>
><br>
> Version of lustre and kernel is:<br>
><br>
> 2.6.9-42.0.10.EL_lustre-1.6.0.1smp X86_64<br>
><br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> previous similar message<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> previous similar message<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 2<br>
> previous similar messages<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 4<br>
> previous similar messages<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 5<br>
> previous similar messages<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> obd_change_cbdata: NULL export<br>
> LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> previous similar message<br>
><br>
> --<br>
> Jeremy Mann<br>
> jeremy@biochem.uthscsa.edu<br>
><br>
> University of Texas Health Science Center<br>
> Bioinformatics Core Facility<br>
> <a href="http://www.bioinformatics.uthscsa.edu" target="_blank">http://www.bioinformatics.uthscsa.edu</a><br>
> Phone: (210) 567-2672<br>
><br>
><br>
><br>
> ------------------------------<br>
><br>
> _______________________________________________<br>
> Lustre-discuss mailing list<br>
> Lustre-discuss@lists.lustre.org<br>
> <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
><br>
><br>
> End of Lustre-discuss Digest, Vol 25, Issue 56<br>
> **********************************************<br>
><br>
><br>
> ------------------------------------------------------------------------<br>
><br>
> _______________________________________________<br>
> Lustre-discuss mailing list<br>
> Lustre-discuss@lists.lustre.org<br>
> <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
<br>
<br>
--<br>
Amit Sharma<br>
Lustre Engineering<br>
Sun Microsystems, Bangalore.<br>
<br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <a href="http://lists.lustre.org/pipermail/lustre-discuss/attachments/20080229/b7713b02/attachment-0001.html" target="_blank">http://lists.lustre.org/pipermail/lustre-discuss/attachments/20080229/b7713b02/attachment-0001.html</a><br>
<br>
------------------------------<br>
<br>
Message: 3<br>
Date: Fri, 29 Feb 2008 13:56:31 +0530<br>
From: Amit Sharma <Amit.Sharma@Sun.COM><br>
Subject: Re: [Lustre-discuss] Configuration of lustre FS on single<br>
node<br>
To: ashok bharat bayana <ashok.bharat.bayana@iiitb.ac.in><br>
Cc: lustre-discuss@lists.lustre.org<br>
Message-ID: <47C7C1B7.8050806@sun.com><br>
Content-Type: text/plain; format=flowed; charset=ISO-8859-1<br>
<br>
Ashok,<br>
<br>
If you are trying to setup lustre (with all the servers MDS, OSS.. etc)<br>
building only the patchless client wont help you.<br>
<br>
You will have to build lustre as described here :<br>
<a href="http://wiki.lustre.org/index.php?title=Lustre_Howto" target="_blank">http://wiki.lustre.org/index.php?title=Lustre_Howto</a><br>
<br>
thanks,<br>
Amit.<br>
<br>
ashok bharat bayana wrote:<br>
><br>
> Hi,<br>
> the kernel version I used is 2.6.20.15 and the distro is Ubuntu 7.10<br>
> The steps so far I have done are:<br>
> 1)I have downloaded the sources lustre(1.6.4.2) from CFS<br>
> 2)I tried to build lustre for a patchless client in which i triggered<br>
> the command,<br>
> [lustre]$ ./configure --with-linux=/unpatched/kernel/source<br>
> 3)then I build it using make and then installed the modules using make<br>
> install commands<br>
> (I'm not sure whether the modules are installed correctly or not.Isn't<br>
> the modules are installed using make install cmd)<br>
> 4)Now in /usr/lib there is a lustre folder created.<br>
> (Can we setup all MDS,client and OST's on a single system? my system<br>
> configuration is Intel Pentium 512 MB RAM 1.6 GHz)<br>
> Could you please tell me how to mount lustre fs in my laptop.<br>
><br>
> Thanks and Regards,<br>
> Ashok Bharat<br>
> -----Original Message-----<br>
> From: Amit Sharma [<a href="mailto:Amit.Sharma@Sun.COM" target="_blank">mailto:Amit.Sharma@Sun.COM</a>]<br>
> Sent: Fri 2/29/2008 12:03 PM<br>
> To: ashok bharat bayana<br>
> Cc: lustre-discuss@lists.lustre.org<br>
> Subject: Re: [Lustre-discuss] Configuration of lustre FS on single node<br>
><br>
> Ashok,<br>
><br>
> Could you let us know what are the modules that you have installed on<br>
> the system. The linux version on your system. And the steps that you<br>
> have done so far.<br>
><br>
> thanks,<br>
> Amit<br>
> ashok bharat bayana wrote:<br>
> ><br>
> > Hello,<br>
> > I successfully build lustre(1.6.4.2) on my system for a patchless client<br>
> > But I dont know how to proceed in configuring the file system.<br>
> ><br>
> > I'm trying to build all MDS,client and MDT's on a single node.<br>
> > >From the tutorials I came to know that<br>
> ><br>
> > First, create an MDT for the "spfs" file system that uses the /dev/sda<br>
> > disk. This MDT also acts as the MGS for the site.<br>
> ><br>
> > $ mkfs.lustre --fsname spfs --mdt --mgs /dev/sda<br>
> ><br>
> > But by triggering this command my system crashed in which the whole data<br>
> > is lost and again I need to install the OS.<br>
> > I want help in proceeding of mounting a lustre file system.<br>
> ><br>
> > Thanks and Regards,<br>
> > Ashok Bharat<br>
> ><br>
> > -----Original Message-----<br>
> > From: lustre-discuss-bounces@lists.lustre.org on behalf of<br>
> > lustre-discuss-request@lists.lustre.org<br>
> > Sent: Wed 2/27/2008 10:30 PM<br>
> > To: lustre-discuss@lists.lustre.org<br>
> > Subject: Lustre-discuss Digest, Vol 25, Issue 56<br>
> ><br>
> > Send Lustre-discuss mailing list submissions to<br>
> > lustre-discuss@lists.lustre.org<br>
> ><br>
> > To subscribe or unsubscribe via the World Wide Web, visit<br>
> > <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
> > or, via email, send a message with subject or body 'help' to<br>
> > lustre-discuss-request@lists.lustre.org<br>
> ><br>
> > You can reach the person managing the list at<br>
> > lustre-discuss-owner@lists.lustre.org<br>
> ><br>
> > When replying, please edit your Subject line so it is more specific<br>
> > than "Re: Contents of Lustre-discuss digest..."<br>
> ><br>
> ><br>
> > Today's Topics:<br>
> ><br>
> > 1. Multiple NICs per OST (Joshua Bower-Cooley)<br>
> > 2. obd error on MGS/MDT node (Jeremy Mann)<br>
> ><br>
> ><br>
> > ----------------------------------------------------------------------<br>
> ><br>
> > Message: 1<br>
> > Date: Tue, 26 Feb 2008 11:55:19 -0800<br>
> > From: Joshua Bower-Cooley <jbowercooley@lcogt.net><br>
> > Subject: [Lustre-discuss] Multiple NICs per OST<br>
> > To: lustre-discuss@lists.lustre.org<br>
> > Message-ID: <200802261155.19907.jbowercooley@lcogt.net><br>
> > Content-Type: text/plain; charset="utf-8"<br>
> ><br>
> > Hi-<br>
> > I've had lustre running happily for some time over a single 10g<br>
> ethernet NIC<br>
> > per node. After switching to dual 10g and creating a new filesystem<br>
> > (1.6.4.2), I'm seeing nothing but keep-alive packets with bad checksums.<br>
> ><br>
> > What is the current "correct" way to do this now? The manual suggest not<br>
> > using<br>
> > bonding, but several list postings now reccommend it. Without<br>
> bonding, do I<br>
> > need to have my 2 switches stacked, or will Lustre recognize the<br>
> division in<br>
> > my subnet?<br>
> ><br>
> > LNET module options I've tried are:<br>
> > 1) networks="tcp0(eth2,eth3)"<br>
> > 2) ip2nets="tcp(eth2,eth3); tcp(eth2) 10.9.[1-4].*; tcp(eth3)<br>
> 10.9.[5-8].*;"<br>
> > and many other variations<br>
> ><br>
> > All other services are functional on both interfaces.<br>
> ><br>
> > Thanks in advance,<br>
> > J Bower-Cooley<br>
> > Scientific Systems Engineer<br>
> > Las Cumbres Observatory Global Telescope<br>
> ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > Message: 2<br>
> > Date: Wed, 27 Feb 2008 09:50:08 -0600 (CST)<br>
> > From: "Jeremy Mann" <jeremy@biochem.uthscsa.edu><br>
> > Subject: [Lustre-discuss] obd error on MGS/MDT node<br>
> > To: lustre-discuss@lists.lustre.org<br>
> > Message-ID:<br>
> > <62901.24.173.62.147.1204127408.squirrel@biochem.uthscsa.edu><br>
> > Content-Type: text/plain;charset=iso-8859-1<br>
> ><br>
> > Today we are starting to see obd_change_cbdata errors on our MGS/MDT<br>
> node.<br>
> > What does this error mean?<br>
> ><br>
> > Version of lustre and kernel is:<br>
> ><br>
> > 2.6.9-42.0.10.EL_lustre-1.6.0.1smp X86_64<br>
> ><br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> > previous similar message<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> > obd_change_cbdata: NULL export<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> > previous similar message<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> > obd_change_cbdata: NULL export<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 2<br>
> > previous similar messages<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> > obd_change_cbdata: NULL export<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 4<br>
> > previous similar messages<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> > obd_change_cbdata: NULL export<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 5<br>
> > previous similar messages<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata())<br>
> > obd_change_cbdata: NULL export<br>
> > LustreError: 65:0:(obd_class.h:1171:obd_change_cbdata()) Skipped 1<br>
> > previous similar message<br>
> ><br>
> > --<br>
> > Jeremy Mann<br>
> > jeremy@biochem.uthscsa.edu<br>
> ><br>
> > University of Texas Health Science Center<br>
> > Bioinformatics Core Facility<br>
> > <a href="http://www.bioinformatics.uthscsa.edu" target="_blank">http://www.bioinformatics.uthscsa.edu</a><br>
> > Phone: (210) 567-2672<br>
> ><br>
> ><br>
> ><br>
> > ------------------------------<br>
> ><br>
> > _______________________________________________<br>
> > Lustre-discuss mailing list<br>
> > Lustre-discuss@lists.lustre.org<br>
> > <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
> ><br>
> ><br>
> > End of Lustre-discuss Digest, Vol 25, Issue 56<br>
> > **********************************************<br>
> ><br>
> ><br>
> > ------------------------------------------------------------------------<br>
> ><br>
> > _______________________________________________<br>
> > Lustre-discuss mailing list<br>
> > Lustre-discuss@lists.lustre.org<br>
> > <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
><br>
><br>
> --<br>
> Amit Sharma<br>
> Lustre Engineering<br>
> Sun Microsystems, Bangalore.<br>
><br>
<br>
<br>
--<br>
Amit Sharma<br>
Lustre Engineering<br>
Sun Microsystems, Bangalore.<br>
<br>
<br>
------------------------------<br>
<br>
_______________________________________________<br>
Lustre-discuss mailing list<br>
Lustre-discuss@lists.lustre.org<br>
<a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
<br>
<br>
End of Lustre-discuss Digest, Vol 25, Issue 59<br>
**********************************************<br>
<br>
</font>
</p>
<br>_______________________________________________
Lustre-discuss mailing list
Lustre-discuss@lists.lustre.org
http://lists.lustre.org/mailman/listinfo/lustre-discuss
</body></html>