I have done both SW and HW raid across with OSTs and MDTs.
As part of your choice, look into what happens when you have to replace a
failed disk in a sw configuration. My negatives for sw raid are all management
at this point.
When you pull a bad disk out of a linux box (/dev/sde for example)
it.
-Original Message-
From: Oleg Drokin [mailto:gr...@whamcloud.com]
Sent: Monday, March 28, 2011 3:57 PM
To: Lundgren, Andrew
Cc: Brian O'Connor; lustre-discuss@lists.lustre.org
Subject: Re: [Lustre-discuss] software raid
Hello!
On Mar 28, 2011, at 4:43 PM, Lundgren, Andrew wrote:
When you
Just as a FYI, you can set most of the bonding options in the ifcfg-bond0 file.
IE:
BONDING_OPTS=arp_ip_target=10.248.58.254 arp_interval=500 mode=active-backup
primary=eth0
Then your modprobe.conf only needs:
alias bond0 bonding
-Original Message-
From:
Are the release notes correct where they state that
Lustre 1.8.4 runs on RHEL 5.5 and
Lustre 2.0.0 runs on RHEL 5.4?
Does that mean that there is no upgrade path from 1.8.4 to 2.0.0?
--
Andrew
___
Lustre-discuss mailing list
Can you explain how to do this, or provide sample files that we can use as well
as where to place them?
-Original Message-
It should be possible to automatically create these quota files the first time
that a new OST is mounted, since we know at that point that the filesystem is
empty
I just went though something similar. When your fsck completes you may be left
with things moved to your lost+found. If that happens, you can mount the file
system using -t ldiskfs and run the ll_recover_lost_found_objs against the
lost+found directory.
--
Andrew
-Original Message-
I was also going to recommend the unlink.
We have had to do this as well, the unlink worked for us. It did need to be
run with privileges for the file. (root in our case.)
--
Andrew
-Original Message-
From: lustre-discuss-boun...@lists.lustre.org
I went back with our guys internally and reviewed the --perm parameter. It
turns out that is a parameter that was put into our wrapper scripts to simplify
the process. We are doing it today, but Brian is correct that the perm
parameter doesn't exist in the luster software. If needed, I can
On Mon, 2010-01-25 at 11:38 -0700, Lundgren, Andrew wrote:
Level 3 requested this feature be developed in 1.6. The after Sun did some
work for us, the following is the procedure that we have setup for usage.
IIRC the functionality was enabled in 1.6.7. We have tested it in 1.8.0.
Do you
: Friday, January 22, 2010 2:53 PM
To: lustre-discuss@lists.lustre.org
Subject: Re: [Lustre-discuss] Permanently delete OST
On Fri, 2010-01-22 at 14:45 -0700, Lundgren, Andrew wrote:
I might be mistaken, but I thought this exact feature was added back
in 1.6.x
Which feature exactly
I might be mistaken, but I thought this exact feature was added back in 1.6.x
-Original Message-
From: lustre-discuss-boun...@lists.lustre.org
[mailto:lustre-discuss-boun...@lists.lustre.org] On Behalf Of Brian J. Murrell
Sent: Friday, January 22, 2010 2:18 PM
To:
I noticed in the announcement that SUSE isn't support as a server in this
release? Oracle's distro seems to have taken SUSE's place.
Is that going to be the case going forward?
--
Andrew
___
Lustre-discuss mailing list
Lustre-discuss@lists.lustre.org
This sounds very much like a problem we saw before we changed the lru_size to a
fixed size from dynamic.
--
Andrew
-Original Message-
From: lustre-discuss-boun...@lists.lustre.org
[mailto:lustre-discuss-boun...@lists.lustre.org] On Behalf Of David Simas
Sent: Monday, October 12, 2009
Thanks Bernd.
For a work around, we are doing a cron every 5 minutes for now to force it down
after unmount/remounts.
--
Andrew
-Original Message-
From: Bernd Schubert [mailto:bs_li...@aakef.fastmail.fm]
Sent: Tuesday, October 13, 2009 4:15 AM
To: Andreas Dilger
Cc: Lundgren, Andrew
specifying the wrong
setting?
-Original Message-
From: Bernd Schubert [mailto:bs_li...@aakef.fastmail.fm]
Sent: Monday, October 12, 2009 11:21 AM
To: lustre-discuss@lists.lustre.org
Cc: Andreas Dilger; Lundgren, Andrew
Subject: Re: [Lustre-discuss] Is there a way to set lru_size and have
Is there a way to set the lru_size to a fixed value and have it stay that way
across mounts?
I know it can be set using:
$ lctl set_param ldlm.namespaces.*osc*.lru_size=$((NR_CPU*100))
But that isn't retained across a reboot.
Thank you.
--
Andrew
___
We have a few 1.8.0 clusters running. We have seen multiple instances now
where the clients loose connectivity to the MDT. The MDS logs indicate that
there is some sort of problem on the MDT.
The following is a typical output:
Oct 6 02:56:08 mint1502 kernel: LustreError:
Oh man, that should have read LOSING!
From: lustre-discuss-boun...@lists.lustre.org
[mailto:lustre-discuss-boun...@lists.lustre.org] On Behalf Of Lundgren, Andrew
Sent: Tuesday, October 06, 2009 11:14 AM
To: lustre-discuss
Subject: [Lustre-discuss] 1.8.0 Loosing connection to the MDT for several
I don’t believe that you need to install the client RPMs when you install the
server. I wouldn’t force install them. The client will mount with just the
server RPMs.
We have seen cases when clients will cause you to have to reboot a machine
because of bugs or other issues. When that
Does this need to be run on EACH OSS? Is there a central way to do it on the
MDS?
You recommend disabling the read and the write as the settings indicate or just
the read as the text indicates?
-Original Message-
A patch is under testing and will be included in 1.8.1.1.
Until 1.8.1.1
It is very difficult to find relevant documentation for heartbeat 1/2. I just
finished configuring a heartbeat system and would not recommend it because of
the documentation. (They seem to have removed portions the heartbeat
documentation from the site.)
Pacemaker is not a simple solution
.
--
Andrew
-Original Message-
From: Jim Garlick [mailto:garl...@llnl.gov]
Sent: Monday, July 13, 2009 2:21 PM
To: Lundgren, Andrew
Cc: Carlos Santana; lustre-discuss@lists.lustre.org
Subject: Re: [Lustre-discuss] failover software - heartbeat
We recently put heartbeat v1 in production
Are you doing anything if the network fails to one mds?
How about if your fiber path fails?
-Original Message-
From: Jim Garlick [mailto:garl...@llnl.gov]
Sent: Monday, July 13, 2009 2:39 PM
To: Lundgren, Andrew
Cc: Carlos Santana; lustre-discuss@lists.lustre.org
Subject: Re
Look at doing a --writeconf with tunefs.lustre on all of your OSTs and MDTs.
Then remount them with the correct settings.
-Original Message-
From: lustre-discuss-boun...@lists.lustre.org [mailto:lustre-discuss-
boun...@lists.lustre.org] On Behalf Of Michael Di Domenico
Sent:
I am trying to configure pingd in heartbeat 2.1.3 (comes with RHEL 5) to shift
my MDS to its peer when the MDS is no longer able to ping its gateway. I
haven't been able to get the syntax in the XML correct to get it to shift when
pingd detects the problem. Anyone else using it?
--
Andrew
What is the current version of the lustre-diagnostics rpm? The newest one I
have been able to find is lustre-diagnostics-1.4-cfs1.noarch.rpm from here:
http://downloads.lustre.org/public/tools/lustre-diagnostics/
Is there a new one or is that deprecated?
--
Andrew
The parameter is called dirty, is that write cache, or is it read-write?
Current Lustre does not cache on OSTs at all. All IO is direct.
Future Lustre releases will provide an OST cache.
For now, you can increase the amount of data cached on clients, which
might help a little. Client
Has this problem only been seen in 1.6.7? We are currently running on 1.6.4.3.
-Original Message-
This happened a day after upgrading to Lustre 1.6.7. We have since
downgraded our servers to 1.6.6.
___
Lustre-discuss mailing list
Will this be dropped as a 1.6.7.1 release or a later 1.6.8 release?
-Original Message-
From: lustre-discuss-boun...@lists.lustre.org [mailto:lustre-discuss-
boun...@lists.lustre.org] On Behalf Of Johann Lombardi
Sent: Thursday, April 02, 2009 3:13 PM
To:
Is there a way to enable logging of UID and host for creation/deletion of
files/directories within the cluster?
--
Andrew
___
Lustre-discuss mailing list
Lustre-discuss@lists.lustre.org
http://lists.lustre.org/mailman/listinfo/lustre-discuss
/deletion of files?
On Thu, 2009-01-15 at 18:41 -0700, Lundgren, Andrew wrote:
Is there a way to enable logging of UID and host for
creation/deletion
of files/directories within the cluster?
The feature you are looking for is called audit logs. It used to
exist on code branch for the Hendrix
Having read though the lustre manual, it appears that to add additional OSTs to
a cluster there should be no I/O. (Page 17.) I would like to confirm that
this is no Reads as well as no writes? Do we need to disconnect all of our
cleints? (No really possible to make sure that no one on does
We are experiencing the same problem with 1.6.4.2. We thought it was the
statahead problems. After turning off the statahead code, we experienced the
same problem again. I had hoped going to 1.6.5 would resolve the issue. If
you open a bug, would you mind sending the bug number to the list?
Is there a place where the networks options are thoroughly discussed? I have
read though the manual and not found a lot on it.
I would like to understand exactly what the different options and behaviors are.
Thanks!
--
Andrew
-Original Message-
From: [EMAIL PROTECTED]
Are you suggesting he use machines with 40G of RAM to work with 10G files?
We have many 800-900G files... I am not sure that is a realistic number.
--
Andrew
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of
Kumaran Rajaram
Sent: Friday, May 30,
I get it.
Thanks!
-Original Message-
From: Kumaran Rajaram [mailto:[EMAIL PROTECTED]
Sent: Friday, May 30, 2008 3:07 PM
To: Lundgren, Andrew
Cc: Roger Spellman; lustre-discuss@lists.lustre.org
Subject: RE: [Lustre-discuss] Performance Drop creating big files
I meant use file
We seem to be having a problem with lustre 1.6.4.3 and clients getting
disconnected.
We currently have a situation where a box that just does maintenance work on
the cluster (du/stats other work) has some directories it cannot enter. (The
shell just hangs and doesn't timeout.)
An lfs check
unmounting MDT/MGS but im not sure .
Cheers .
- Original Message -
From: Lundgren, Andrew
To: '[EMAIL PROTECTED]'
Sent: Monday, March 17, 2008 7:29 PM
Subject: [Lustre-discuss] how to replace a bad OST.
I am trying to learn how to replace
Is there any restriction that lustre nodes on TCP must be on the same IP
subnets?
Is there anything special that needs to be done to make a client on one network
see an MGS/OSSes on another network?
Thanks!
--
Andrew
___
Lustre-discuss mailing list
Thanks!
I believe it is a router ACL issue. But I wanted to make sure this wasn't an
issue.
From: Klaus Steden [mailto:[EMAIL PROTECTED]
Sent: Friday, March 07, 2008 3:51 PM
To: Lundgren, Andrew; '[EMAIL PROTECTED]'
Subject: Re: [Lustre-discuss] lustre cross IP
I got them yesterday. Thank you.
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
Sent: Friday, January 25, 2008 12:57 AM
To: Lundgren, Andrew
Cc: Sébastien Buisson; [EMAIL PROTECTED]
Subject: RE: [Lustre-discuss] e2fsprogs version recommended
for Lustre
41 matches
Mail list logo
