<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:st1="urn:schemas-microsoft-com:office:smarttags" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii">
<meta name=Generator content="Microsoft Word 11 (filtered medium)">
<!--[if !mso]>
<style>
v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style>
<![endif]-->
<title>RE: Help needed in Building lustre using pre-packaged releases</title>
<o:SmartTagType namespaceuri="urn:schemas-microsoft-com:office:smarttags"
name="PlaceType"/>
<o:SmartTagType namespaceuri="urn:schemas-microsoft-com:office:smarttags"
name="PlaceName"/>
<o:SmartTagType namespaceuri="urn:schemas-microsoft-com:office:smarttags"
name="City"/>
<o:SmartTagType namespaceuri="urn:schemas-microsoft-com:office:smarttags"
name="place"/>
<o:SmartTagType namespaceuri="urn:schemas-microsoft-com:office:smarttags"
name="PersonName"/>
<!--[if !mso]>
<style>
st1\:*{behavior:url(#default#ieooui) }
</style>
<![endif]-->
<style>
<!--
/* Font Definitions */
@font-face
{font-family:Tahoma;
panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman";}
a:link, span.MsoHyperlink
{color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{color:blue;
text-decoration:underline;}
p
{mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:12.0pt;
font-family:"Times New Roman";}
span.EmailStyle18
{mso-style-type:personal-reply;
font-family:Arial;
color:navy;}
@page Section1
{size:8.5in 11.0in;
margin:1.0in 1.25in 1.0in 1.25in;}
div.Section1
{page:Section1;}
-->
</style>
</head>
<body lang=EN-US link=blue vlink=blue>
<div class=Section1>
<p class=MsoNormal><font size=2 color=navy face=Arial><span style='font-size:
10.0pt;font-family:Arial;color:navy'>Why you want to build Lustre when rpms are
available for your environment. You need to install the rpms( Kernel rpm,
Lustre modules rpm and Lustre rpm ),.<o:p></o:p></span></font></p>
<p class=MsoNormal><font size=2 color=navy face=Arial><span style='font-size:
10.0pt;font-family:Arial;color:navy'>The First rpm will install you kernel and
edits the grub to add your lustre kernel, after booting into this kernel you
can Configure Lustre. That’s all.<o:p></o:p></span></font></p>
<p class=MsoNormal><font size=2 color=navy face=Arial><span style='font-size:
10.0pt;font-family:Arial;color:navy'><o:p> </o:p></span></font></p>
<p class=MsoNormal><font size=2 color=navy face=Arial><span style='font-size:
10.0pt;font-family:Arial;color:navy'>Venkat<o:p></o:p></span></font></p>
<p class=MsoNormal><font size=2 color=navy face=Arial><span style='font-size:
10.0pt;font-family:Arial;color:navy'><o:p> </o:p></span></font></p>
<div>
<div class=MsoNormal align=center style='text-align:center'><font size=3
face="Times New Roman"><span style='font-size:12.0pt'>
<hr size=2 width="100%" align=center tabindex=-1>
</span></font></div>
<p class=MsoNormal><b><font size=2 face=Tahoma><span style='font-size:10.0pt;
font-family:Tahoma;font-weight:bold'>From:</span></font></b><font size=2
face=Tahoma><span style='font-size:10.0pt;font-family:Tahoma'> <st1:PersonName
w:st="on">lustre-discuss-bounces@lists.lustre.org</st1:PersonName> [mailto:<st1:PersonName
w:st="on">lustre-discuss-bounces@lists.lustre.org</st1:PersonName>] <b><span
style='font-weight:bold'>On Behalf Of </span></b>ashok bharat bayana<br>
<b><span style='font-weight:bold'>Sent:</span></b> Friday, March 14, 2008 11:16
AM<br>
<b><span style='font-weight:bold'>To:</span></b>
lustre-discuss@lists.lustre.org; lustre-discuss@lists.lustre.org<br>
<b><span style='font-weight:bold'>Subject:</span></b> Re: [Lustre-discuss] Help
needed in Building lustre usingpre-packaged releases</span></font><o:p></o:p></p>
</div>
<p class=MsoNormal><font size=3 face="Times New Roman"><span style='font-size:
12.0pt'><o:p> </o:p></span></font></p>
<p class=MsoNormal style='margin-bottom:12.0pt'><font size=3
face="Times New Roman"><span style='font-size:12.0pt'><o:p> </o:p></span></font></p>
<p style='margin-bottom:12.0pt'><font size=2 face="Times New Roman"><span
style='font-size:10.0pt'>Hi,<br>
Can anyone guide me in building the lustre using pre-packaged lustre
release.I'm using Ubuntu 7.10 I want to build lustre using RHEL2.6 rpms
available on my system.I'm referring how_to in wiki. but in that no detailed
step by step procedure is given for building lustre using pre-packed release.<br>
<br>
I'm in need of this.<br>
<br>
Thanks and Regards,<br>
Ashok Bharat<br>
-----Original Message-----<br>
From: <st1:PersonName w:st="on">lustre-discuss-bounces@lists.lustre.org</st1:PersonName>
on behalf of lustre-discuss-request@lists.lustre.org<br>
Sent: Fri 3/14/2008 2:25 AM<br>
To: lustre-discuss@lists.lustre.org<br>
Subject: Lustre-discuss Digest, Vol 26, Issue 36<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">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: <st1:City w:st="on"><st1:place w:st="on">OSS</st1:place></st1:City>
not healty (Andreas Dilger)<br>
2. Re: e2scan for backup (Andreas Dilger)<br>
3. Howto map block devices to Lustre devices? (Chris Worley)<br>
4. Re: e2fsck mdsdb: DB_NOTFOUND (Aaron Knister)<br>
5. Re: e2fsck mdsdb: DB_NOTFOUND (Karen M. Fernsler)<br>
6. Re: Howto map block devices to Lustre devices? (Klaus Steden)<br>
<br>
<br>
----------------------------------------------------------------------<br>
<br>
Message: 1<br>
Date: Thu, 13 Mar 2008 11:11:19 -0700<br>
From: Andreas Dilger <adilger@sun.com><br>
Subject: Re: [Lustre-discuss] <st1:City w:st="on"><st1:place w:st="on">OSS</st1:place></st1:City>
not healty<br>
To: "Brian J. Murrell" <Brian.Murrell@sun.com><br>
Cc: lustre-discuss@lists.lustre.org<br>
Message-ID: <20080313181119.GB3217@webber.adilger.int><br>
Content-Type: text/plain; charset=us-ascii<br>
<br>
On Mar 13, 2008 13:44 +0100, Brian J. Murrell wrote:<br>
> On Thu, 2008-03-13 at 12:34 +0100, Frank Mietke wrote:<br>
> > Mar 13 06:17:31 chic2e24 kernel: [3068633.701448] attempt to access
beyond end of device<br>
> > Mar 13 06:17:31 chic2e24 kernel: [3068633.701454] sda: rw=1,
want=11287722456, limit=7796867072<br>
><br>
> This is pretty self-explanatory. Something tried to read beyond the
end<br>
> of the disk. Something has a misunderstanding of how big the disk
is.<br>
> Is it possible that the disk format process was misled about the disk<br>
> size during initialization?<br>
<br>
Unlikely.<br>
<br>
> Andreas, does mkfs do any bounds checking to verify the sanity of the<br>
> mkfs request? I.e. does it make sure that if/when you specify a
number<br>
> of blocks for a filesystem that that many block are available?<br>
<br>
Yes, mke2fs will zero out the last ~128kB of the device to overwrite any<br>
MD RAID signatures, and also verify that the device is as big as requested.<br>
<br>
These kind of errors are usually a result of corruption internal to the<br>
filesystem, and some garbage is interpreted as a block number beyond the<br>
end of the device.<br>
<br>
> > Mar 13 06:17:31 chic2e24 kernel: [3068633.701555] attempt to access
beyond end of device<br>
> > Mar 13 06:17:31 chic2e24 kernel: [3068633.701558] sda: rw=1,
want=25366292592, limit=7796867072<br>
> > Mar 13 06:17:31 chic2e24 kernel: [3068633.701562] Buffer I/O error on
device sda, logical block 3170786573<br>
> > Mar 13 06:17:31 chic2e24 kernel: [3068633.701785] lost page write due
to I/O error on sda<br>
> > Mar 13 06:17:31 chic2e24 kernel: [3068633.702004] Aborting journal on
device sda.<br>
><br>
> This is all just fallout error messages from the attempted read beyond<br>
> EOF.<br>
<br>
Time to unmount the filesystem and run a full e2fsck "e2fsck -fp
/dev/sdaNNN"<br>
<br>
Cheers, Andreas<br>
--<br>
Andreas Dilger<br>
Sr. Staff Engineer, Lustre Group<br>
Sun Microsystems of Canada, Inc.<br>
<br>
<br>
<br>
------------------------------<br>
<br>
Message: 2<br>
Date: Thu, 13 Mar 2008 11:22:48 -0700<br>
From: Andreas Dilger <adilger@sun.com><br>
Subject: Re: [Lustre-discuss] e2scan for backup<br>
To: Jakob Goldbach <jakob@goldbach.dk><br>
Cc: Lustre User Discussion Mailing List<br>
<lustre-discuss@lists.lustre.org><br>
Message-ID: <20080313182248.GD3217@webber.adilger.int><br>
Content-Type: text/plain; charset=us-ascii<br>
<br>
On Mar 13, 2008 12:59 +0100, Jakob Goldbach wrote:<br>
> On Wed, 2008-03-12 at 23:12 +0100, Brian J. Murrell wrote:<br>
> > On Wed, 2008-03-12 at 14:50 -0600, Lundgren, Andrew wrote:<br>
> > > How do you do the snapshot?<br>
> ><br>
> > lvcreate -s<br>
><br>
> No need to freeze the filesystem while creating the snapshot to ensure a<br>
> consistent filesystem on the snapshot ?<br>
<br>
Yes, but this is handled internally by LVM and ext3 when the snapshot<br>
is created.<br>
<br>
> (xfs has a xfs_freeze function that does just this)<br>
<br>
In fact I was just discussing this with an XFS developer and this is<br>
a source of problems for them because if you do xfs_freeze before doing<br>
the LVM snapshot it will deadlock.<br>
<br>
Cheers, Andreas<br>
--<br>
Andreas Dilger<br>
Sr. Staff Engineer, Lustre Group<br>
Sun Microsystems of Canada, Inc.<br>
<br>
<br>
<br>
------------------------------<br>
<br>
Message: 3<br>
Date: Thu, 13 Mar 2008 13:50:51 -0600<br>
From: "Chris Worley" <worleys@gmail.com><br>
Subject: [Lustre-discuss] Howto map block devices to Lustre devices?<br>
To: lustre-discuss <lustre-discuss@lists.lustre.org><br>
Message-ID:<br>
<f3177b9e0803131250n23084fd7g184ef07403a298cd@mail.gmail.com><br>
Content-Type: text/plain; charset=ISO-8859-1<br>
<br>
I'm trying to deactivate some OST's, but to find them I've been<br>
searching through /var/log/messages, as in:<br>
<br>
# ssh io2 grep -e sde -e sdf -e sdj -e sdk -e sdd
/var/log/messages"*"<br>
| grep Server<br>
/var/log/messages:Mar 10 13:27:54 io2 kernel: Lustre: Server<br>
ddnlfs-OST0035 on device /dev/sdf has started<br>
/var/log/messages.1:Mar 4 16:02:13 io2 kernel: Lustre: Server<br>
ddnlfs-OST0030 on device /dev/sdf has started<br>
/var/log/messages.1:Mar 6 14:34:44 io2 kernel: Lustre: Server<br>
ddnlfs-OST002e on device /dev/sdd has started<br>
/var/log/messages.1:Mar 6 14:34:55 io2 kernel: Lustre: Server<br>
ddnlfs-OST002f on device /dev/sde has started<br>
/var/log/messages.1:Mar 6 14:35:16 io2 kernel: Lustre: Server<br>
ddnlfs-OST0030 on device /dev/sdf has started<br>
/var/log/messages.1:Mar 6 15:20:48 io2 kernel: Lustre: Server<br>
ddnlfs-OST002f on device /dev/sde has started<br>
/var/log/messages.1:Mar 6 16:08:38 io2 kernel: Lustre: Server<br>
ddnlfs-OST002e on device /dev/sdd has started<br>
/var/log/messages.1:Mar 6 16:08:43 io2 kernel: Lustre: Server<br>
ddnlfs-OST0030 on device /dev/sdf has started<br>
/var/log/messages.1:Mar 6 16:08:53 io2 kernel: Lustre: Server<br>
ddnlfs-OST0034 on device /dev/sdj has started<br>
<br>
Note that there isn't an entry for sdk (probably rotated out), and sdf<br>
has two different names.<br>
<br>
Is there a better way to find the right Lustre device name map to<br>
Linux block device?<br>
<br>
I'm trying to cull-out slow disks. I'm hoping that just by<br>
"deactivating" the device in lctl, it'll quit using it, and that's
the<br>
best way to get rid of a slow drive... correct?<br>
<br>
Thanks,<br>
<br>
Chris<br>
<br>
<br>
------------------------------<br>
<br>
Message: 4<br>
Date: Thu, 13 Mar 2008 16:50:04 -0400<br>
From: Aaron Knister <aaron@iges.org><br>
Subject: Re: [Lustre-discuss] e2fsck mdsdb: DB_NOTFOUND<br>
To: Michelle Butler <mbutler@ncsa.uiuc.edu><br>
Cc: Andreas Dilger <adilger@sun.com>, lustre-discuss@clusterfs.com,<br>
abe-admin@ncsa.uiuc.edu,
ckerner@ncsa.uiuc.edu, alex parga<br>
<aparga@ncsa.uiuc.edu>,
set@ncsa.uiuc.edu<br>
Message-ID: <85E6EB25-EC03-4D93-BD8B-B267F65A5400@iges.org><br>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed; delsp=yes<br>
<br>
What version of lustre/kernel is running on the problematic server?<br>
<br>
On Mar 13, 2008, at 11:02 AM, Michelle Butler wrote:<br>
<br>
> We got past that point by e2fsck the individual partitions first.<br>
><br>
> But we are still having problems.. I'm sorry to<br>
> say. we have an I/O server that is fine until<br>
> we start Lustre. It starts spewing lustre call traces :<br>
><br>
> Call<br>
> Trace:<ffffffffa02fa089>{:libcfs:lcw_update_time+22}<br>
> <ffffffffa03e06e3>{:ptlrpc:ptlrpc_main+1408}<br>
>
<ffffffff8013327d>{default_wake_function+0}<br>
> <ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
>
<ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> <ffffffff80110ebb>{child_rip+8}<br>
>
<ffffffffa03e0163>{:ptlrpc:ptlrpc_main+0}<br>
> <ffffffff80110eb3>{child_rip+0}<br>
><br>
> ll_ost_io_232 S 000001037d6bbee8 0
26764 1
26765 <br>
> 26763 (L-TLB)<br>
> 000001037d6bbe58 0000000000000046 0000000100000246 0000000000000003<br>
> 0000000000000016
0000000000000001 00000104100bcb20 <br>
> 0000000300000246<br>
> 00000103f5470030
000000000001d381<br>
> Call<br>
> Trace:<ffffffffa02fa089>{:libcfs:lcw_update_time+22}<br>
> <ffffffffa03e06e3>{:ptlrpc:ptlrpc_main+1408}<br>
>
<ffffffff8013327d>{default_wake_function+0}<br>
> <ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
>
<ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> <ffffffff80110ebb>{child_rip+8}<br>
>
<ffffffffa03e0163>{:ptlrpc:ptlrpc_main+0}<br>
> <ffffffff80110eb3>{child_rip+0}<br>
><br>
> ll_ost_io_233 S 00000103de847ee8 0
26765
1 26766 <br>
> 26764 (L-TLB)<br>
> 00000103de847e58 0000000000000046 0000000100000246 0000000000000001<br>
> 0000000000000016
0000000000000001 000001040f83c620 <br>
> 0000000100000246<br>
> 00000103e627e030
000000000001d487<br>
> Call<br>
> Trace:<ffffffffa02fa089>{:libcfs:lcw_update_time+22}<br>
> <ffffffffa03e06e3>{:ptlrpc:ptlrpc_main+1408}<br>
> <ffffffff8013327d>{default_wake_function+0}<br>
> <ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
>
<ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> <ffffffff80110ebb>{child_rip+8}<br>
>
<ffffffffa03e0163>{:ptlrpc:ptlrpc_main+0}<br>
> <ffffffff80110eb3>{child_rip+0}<br>
><br>
> ll_ost_io_234 S 00000100c4353ee8 0
26766
1 26767 <br>
> 26765 (L-TLB)<br>
> 00000100c4353e58 0000000000000046 0000000100000246 0000000000000003<br>
> 0000000000000016
0000000000000001 00000104100bcc60 <br>
> 0000000300000246<br>
> 00000103de81b810
000000000001d945<br>
> Call<br>
> Trace:<ffffffffa02fa089>{:libcfs:lcw_update_time+22}<br>
> <ffffffffa03e06e3>{:ptlrpc:ptlrpc_main+1408}<br>
>
<ffffffff8013327d>{default_wake_function+0}<br>
> <ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> <br>
> <ffffffffa03e0156>{:ptlrpc:ptlrpc_retr???f?????????c?????????c??????<br>
> <br>
> Ks[F????????????<br>
> <ffffffff8013327d>{default_wake_function+0}<br>
> <ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> <ffffffffa03e0156>{:ptl<br>
><br>
> It then panic's the kernel.. ??<br>
><br>
> Michelle Butler<br>
><br>
> At 02:39 AM 3/13/2008, Andreas Dilger wrote:<br>
>> On Mar 12, 2008 06:44 -0500, Karen M. Fernsler wrote:<br>
>>> I'm running:<br>
>>><br>
>>> e2fsck -y -v --mdsdb mdsdb --ostdb osth3_1 /dev/mapper/27l4<br>
>>><br>
>>> and getting:<br>
>>><br>
>>> Pass 6: Acquiring information for lfsck<br>
>>> error getting mds_hdr (3685469441:8) in<br>
>> /post/cfg/mdsdb: DB_NOTFOUND: No matching key/data pair found<br>
>>> e2fsck: aborted<br>
>>><br>
>>> Any ideas how to get around this?<br>
>><br>
>> Does "mdsdb" actually exist? This should be created by
first <br>
>> running:<br>
>><br>
>> e2fsck --mdsdb mdsdb /dev/{mdsdevicename}<br>
>><br>
>> before running your above command on the OST.<br>
>><br>
>> Please also try specifying the absolute pathname for the mdsdb
and <br>
>> ostdb<br>
>> files.<br>
>><br>
>> Cheers, Andreas<br>
>> --<br>
>> Andreas Dilger<br>
>> Sr. Staff Engineer, Lustre Group<br>
>> Sun Microsystems of Canada, Inc.<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">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
<br>
Aaron Knister<br>
Associate Systems Analyst<br>
Center for Ocean-Land-Atmosphere Studies<br>
<br>
(301) 595-7000<br>
aaron@iges.org<br>
<br>
<br>
<br>
<br>
<br>
<br>
------------------------------<br>
<br>
Message: 5<br>
Date: Thu, 13 Mar 2008 15:51:22 -0500<br>
From: "Karen M. Fernsler" <fernsler@ncsa.uiuc.edu><br>
Subject: Re: [Lustre-discuss] e2fsck mdsdb: DB_NOTFOUND<br>
To: Aaron Knister <aaron@iges.org><br>
Cc: Andreas Dilger <adilger@sun.com>, lustre-discuss@clusterfs.com,<br>
Michelle Butler
<mbutler@ncsa.uiuc.edu>, abe-admin@ncsa.uiuc.edu,<br>
ckerner@ncsa.uiuc.edu, alex parga
<aparga@ncsa.uiuc.edu>,<br>
set@ncsa.uiuc.edu<br>
Message-ID: <20080313205122.GA17635@ncsa.uiuc.edu><br>
Content-Type: text/plain; charset=iso-8859-1<br>
<br>
2.6.9-42.0.10.EL_lustre-1.4.10.1smp<br>
<br>
This is a 2.6.9-42.0.10.E kernel with lustre-1.4.10.1.<br>
<br>
This has been working ok for almost a year. We did try to<br>
export this filesystem to another cluster over nfs before<br>
we started seeing problems, but I don't know how related if<br>
at all that is.<br>
<br>
We are now trying to dissect the problem by inspecting<br>
the switch logs these nodes are connected to.<br>
<br>
thanks,<br>
-k<br>
<br>
On Thu, Mar 13, 2008 at 04:50:04PM -0400, Aaron Knister wrote:<br>
> What version of lustre/kernel is running on the problematic server?<br>
><br>
> On Mar 13, 2008, at 11:02 AM, Michelle Butler wrote:<br>
><br>
> >We got past that point by e2fsck the individual partitions first.<br>
> ><br>
> >But we are still having problems.. I'm sorry to<br>
> >say. we have an I/O server that is fine until<br>
> >we start Lustre. It starts spewing lustre call traces :<br>
> ><br>
> >Call<br>
> >Trace:<ffffffffa02fa089>{:libcfs:lcw_update_time+22}<br>
> ><ffffffffa03e06e3>{:ptlrpc:ptlrpc_main+1408}<br>
> >
<ffffffff8013327d>{default_wake_function+0}<br>
> ><ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> >
<ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> ><ffffffff80110ebb>{child_rip+8}<br>
> >
<ffffffffa03e0163>{:ptlrpc:ptlrpc_main+0}<br>
> ><ffffffff80110eb3>{child_rip+0}<br>
> ><br>
> >ll_ost_io_232 S 000001037d6bbee8 0
26764
1 26765 <br>
> >26763 (L-TLB)<br>
> >000001037d6bbe58 0000000000000046 0000000100000246 0000000000000003<br>
> > 0000000000000016 0000000000000001
00000104100bcb20 <br>
> >0000000300000246<br>
> > 00000103f5470030 000000000001d381<br>
> >Call<br>
> >Trace:<ffffffffa02fa089>{:libcfs:lcw_update_time+22}<br>
> ><ffffffffa03e06e3>{:ptlrpc:ptlrpc_main+1408}<br>
> >
<ffffffff8013327d>{default_wake_function+0}<br>
> ><ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> > <ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> ><ffffffff80110ebb>{child_rip+8}<br>
> >
<ffffffffa03e0163>{:ptlrpc:ptlrpc_main+0}<br>
> ><ffffffff80110eb3>{child_rip+0}<br>
> ><br>
> >ll_ost_io_233 S 00000103de847ee8 0
26765
1 26766 <br>
> >26764 (L-TLB)<br>
> >00000103de847e58 0000000000000046 0000000100000246 0000000000000001<br>
> > 0000000000000016 0000000000000001
000001040f83c620 <br>
> >0000000100000246<br>
> > 00000103e627e030 000000000001d487<br>
> >Call<br>
> >Trace:<ffffffffa02fa089>{:libcfs:lcw_update_time+22}<br>
> ><ffffffffa03e06e3>{:ptlrpc:ptlrpc_main+1408}<br>
> >
<ffffffff8013327d>{default_wake_function+0}<br>
> ><ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> >
<ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> ><ffffffff80110ebb>{child_rip+8}<br>
> > <ffffffffa03e0163>{:ptlrpc:ptlrpc_main+0}<br>
> ><ffffffff80110eb3>{child_rip+0}<br>
> ><br>
> >ll_ost_io_234 S 00000100c4353ee8 0
26766
1 26767 <br>
> >26765 (L-TLB)<br>
> >00000100c4353e58 0000000000000046 0000000100000246 0000000000000003<br>
> > 0000000000000016 0000000000000001
00000104100bcc60 <br>
> >0000000300000246<br>
> > 00000103de81b810 000000000001d945<br>
> >Call<br>
> >Trace:<ffffffffa02fa089>{:libcfs:lcw_update_time+22}<br>
> ><ffffffffa03e06e3>{:ptlrpc:ptlrpc_main+1408}<br>
> >
<ffffffff8013327d>{default_wake_function+0}<br>
> ><ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> > <br>
>
><ffffffffa03e0156>{:ptlrpc:ptlrpc_retr???f?????????c?????????c??????<br>
>
> <br>
> >Ks[F????????????<br>
> ><ffffffff8013327d>{default_wake_function+0}<br>
> ><ffffffffa03e0156>{:ptlrpc:ptlrpc_retry_rqbds+0}<br>
> > <ffffffffa03e0156>{:ptl<br>
> ><br>
> >It then panic's the kernel.. ??<br>
> ><br>
> >Michelle Butler<br>
> ><br>
> >At 02:39 AM 3/13/2008, Andreas Dilger wrote:<br>
> >>On Mar 12, 2008 06:44 -0500, Karen M. Fernsler wrote:<br>
> >>>I'm running:<br>
> >>><br>
> >>>e2fsck -y -v --mdsdb mdsdb --ostdb osth3_1 /dev/mapper/27l4<br>
> >>><br>
> >>>and getting:<br>
> >>><br>
> >>>Pass 6: Acquiring information for lfsck<br>
> >>>error getting mds_hdr (3685469441:8) in<br>
> >>/post/cfg/mdsdb: DB_NOTFOUND: No matching key/data pair found<br>
> >>>e2fsck: aborted<br>
> >>><br>
> >>>Any ideas how to get around this?<br>
> >><br>
> >>Does "mdsdb" actually exist? This should be
created by first <br>
> >>running:<br>
> >><br>
> >>e2fsck --mdsdb mdsdb /dev/{mdsdevicename}<br>
> >><br>
> >>before running your above command on the OST.<br>
> >><br>
> >>Please also try specifying the absolute pathname for the mdsdb
and <br>
> >>ostdb<br>
> >>files.<br>
> >><br>
> >>Cheers, Andreas<br>
> >>--<br>
> >>Andreas Dilger<br>
> >>Sr. Staff Engineer, Lustre Group<br>
> >>Sun Microsystems of Canada, Inc.<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">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
><br>
> Aaron Knister<br>
> Associate Systems Analyst<br>
> Center for Ocean-Land-Atmosphere Studies<br>
><br>
> (301) 595-7000<br>
> aaron@iges.org<br>
><br>
><br>
><br>
<br>
--<br>
Karen Fernsler Systems Engineer<br>
<st1:place w:st="on"><st1:PlaceName w:st="on">National</st1:PlaceName> <st1:PlaceType
w:st="on">Center</st1:PlaceType></st1:place> for Supercomputing Applications<br>
ph: (217) 265 5249<br>
email: fernsler@ncsa.uiuc.edu<br>
<br>
<br>
------------------------------<br>
<br>
Message: 6<br>
Date: Thu, 13 Mar 2008 13:55:45 -0700<br>
From: Klaus Steden <klaus.steden@thomson.net><br>
Subject: Re: [Lustre-discuss] Howto map block devices to Lustre<br>
devices?<br>
To: Chris Worley <worleys@gmail.com>, lustre-discuss<br>
<lustre-discuss@lists.lustre.org><br>
Message-ID: <C3FEE2E1.59E7%klaus.steden@thomson.net><br>
Content-Type: text/plain;
charset="US-ASCII"<br>
<br>
<br>
Hi Chris,<br>
<br>
Don't your Lustre volumes have a label on them?<br>
<br>
On the one cluster I've got, the physical storage is shared with a number of<br>
other systems, so the device information can change over time ... so I use<br>
device labels in my /etc/fstab and friends.<br>
<br>
Something like 'lustre-OST0000', 'lustre-OST00001' ... although when the<br>
devices are actually mounted, they show up with their /dev node names.<br>
<br>
Look through /proc/fs/lustre for Lustre volume names (they show up when<br>
they're mounted), and you can winnow your list down by mounting by name,<br>
checking the device ID, and removing it that way.<br>
<br>
If you have a lot of devices on the same bus, it will likely take a bit for<br>
the right one to be found, but it's there.<br>
<br>
hth,<br>
Klaus<br>
<br>
On 3/13/08 12:50 PM, "Chris Worley" <worleys@gmail.com>did etch
on stone<br>
tablets:<br>
<br>
> I'm trying to deactivate some OST's, but to find them I've been<br>
> searching through /var/log/messages, as in:<br>
><br>
> # ssh io2 grep -e sde -e sdf -e sdj -e sdk -e sdd
/var/log/messages"*"<br>
> | grep Server<br>
> /var/log/messages:Mar 10 13:27:54 io2 kernel: Lustre: Server<br>
> ddnlfs-OST0035 on device /dev/sdf has started<br>
> /var/log/messages.1:Mar 4 16:02:13 io2 kernel: Lustre: Server<br>
> ddnlfs-OST0030 on device /dev/sdf has started<br>
> /var/log/messages.1:Mar 6 14:34:44 io2 kernel: Lustre: Server<br>
> ddnlfs-OST002e on device /dev/sdd has started<br>
> /var/log/messages.1:Mar 6 14:34:55 io2 kernel: Lustre: Server<br>
> ddnlfs-OST002f on device /dev/sde has started<br>
> /var/log/messages.1:Mar 6 14:35:16 io2 kernel: Lustre: Server<br>
> ddnlfs-OST0030 on device /dev/sdf has started<br>
> /var/log/messages.1:Mar 6 15:20:48 io2 kernel: Lustre: Server<br>
> ddnlfs-OST002f on device /dev/sde has started<br>
> /var/log/messages.1:Mar 6 16:08:38 io2 kernel: Lustre: Server<br>
> ddnlfs-OST002e on device /dev/sdd has started<br>
> /var/log/messages.1:Mar 6 16:08:43 io2 kernel: Lustre: Server<br>
> ddnlfs-OST0030 on device /dev/sdf has started<br>
> /var/log/messages.1:Mar 6 16:08:53 io2 kernel: Lustre: Server<br>
> ddnlfs-OST0034 on device /dev/sdj has started<br>
><br>
> Note that there isn't an entry for sdk (probably rotated out), and sdf<br>
> has two different names.<br>
><br>
> Is there a better way to find the right Lustre device name map to<br>
> Linux block device?<br>
><br>
> I'm trying to cull-out slow disks. I'm hoping that just by<br>
> "deactivating" the device in lctl, it'll quit using it, and
that's the<br>
> best way to get rid of a slow drive... correct?<br>
><br>
> Thanks,<br>
><br>
> Chris<br>
> _______________________________________________<br>
> Lustre-discuss mailing list<br>
> Lustre-discuss@lists.lustre.org<br>
> <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><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">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
<br>
<br>
End of Lustre-discuss Digest, Vol 26, Issue 36<br>
**********************************************</span></font><o:p></o:p></p>
</div>
</body>
</html>