Is OST OI still in use with FID on OST?
by Peng Tao
Hi,
I noticed that FID on OST is enabled since 2.4. With it, it seems the
OI files on OST are not used, unless old client connect w/o
OBD_CONNECT_FID flag, is it correct?
Just want to confirm my understanding of the code.
BTW, is there any documentation of FID on OST? I see that LUDOC-81 is
open but no patch submitted.
Thanks,
Tao
7 years, 11 months
LAD '13 - Call for Papers: 1 Day Remaining
by OpenSFS Administration
Hello All,
There is 1 day remaining to submit your proposal for speakership
opportunities at Lustre Administrators and Developers Workshop (LAD) 2013.
Topic areas of interest include: tools, administration experiences,
configuration setup, development, etc. If your topic does not fit within
these categories, please do not hesitate to submit a proposal, all
submissions are welcome!
How to Submit a Proposal
. Develop an abstract for a 30 minute presentation
. Send abstract to: lad13(a)eofs.org
. Deadline: July 31, 2013
LAD 2013 Event Details
. When: September 16-17, 2013
. Where: Paris, France
. Venue: Hotel Lutetia
. Website: http://www.eofs.eu/?id=lad13
Registration Information
LAD 2013 registration is now open! Click here
<http://lad.eofs.org/register.php> to take advantage of the Early Bird
discount. Please note Early Bird pricing will expire on August 10, 2013.
If you have any questions please contact lad13(a)eofs.org.
We are looking forward to seeing you at LAD 2013!
***A special thank you to the following LAD 2013 sponsors: Bull, CEA,
DataDirect Networks, Intel, NetApp, and Xyratex.***
Kind Regards,
__________________________
OpenSFS Administration
3855 SW 153rd Drive Beaverton, OR 97006 USA
Phone: +1 503-619-0561 | Fax: +1 503-644-6708
Twitter: <https://twitter.com/opensfs> @OpenSFS
Email: <mailto:admin@opensfs.org> admin(a)opensfs.org | Website:
<http://www.opensfs.org/> www.opensfs.org
7 years, 12 months
contemplating move off of QFS
by Adam Edgar
We are currently using Oracle's QFS for a system we inherited from a different group within my company. We've had nothing but headaches from QFS and Solars so we are considering a move to Lustre and Linux. Has anyone here gone through that process? Did they by chance document the migration? Are there any pros or cons I need to be aware of?
Any help here will be much appreciated.
ASE
7 years, 12 months
Error Mounting OST device on OSS Server
by Singhal, Upanshu
Hello,
I am getting an error while mount the OST device on OSS Server. I have built the lustre 2.3 source code and kernel and installed all packages. MGS server installation and configuration is fine, OSS server installation is also fine, mkfs.lustre command works fine, it fails during mount. Any clue or suggestion?
Errors from console are:
[root@lustre-5 /]# mount -t lustre /dev/sdb /mnt
mount.lustre: mount /dev/sdb at /mnt failed: No such device
Are the lustre modules loaded?
Check /etc/modprobe.conf and /proc/filesystems
Error in /var/log/message:
Jul 24 23:05:04 lustre-5 kernel: obdfilter: Unknown symbol security_inode_unlink
Jul 24 23:05:04 lustre-5 modprobe: FATAL: Error inserting obdfilter (/lib/modules/2.6.32.lustremaster/updates/kernel/fs/lustre/obdfilter.ko): Unknown symbol in module, or unknown parameter (see dmesg)
Jul 24 23:05:04 lustre-5 kernel: LustreError: 158-c: Can't load module 'obdfilter'
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21565:0:(genops.c:291:class_newdev()) OBD: unknown type: obdfilter
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21565:0:(obd_config.c:365:class_attach()) Cannot create device lustre-OST0002 of type obdfilter : -19
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21565:0:(obd_config.c:1499:class_config_llog_handler()) Err -19 on cfg command:
Jul 24 23:05:04 lustre-5 kernel: Lustre: cmd=cf001 0:lustre-OST0002 1:obdfilter 2:lustre-OST0002_UUID
Jul 24 23:05:04 lustre-5 kernel: LustreError: 15c-8: MGC10.243.107.53@tcp: The configuration from log 'lustre-OST0002' failed (-19). This may be the result of communication errors between this node and the MGS, a bad configuration, or other errors. See the syslog for more information.
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21531:0:(obd_mount.c:1321:server_start_targets()) failed to start server lustre-OST0002: -19
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21531:0:(obd_mount.c:1963:server_fill_super()) Unable to start targets: -19
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21531:0:(obd_mount.c:1760:server_put_super()) no obd lustre-OST0002
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21531:0:(ldlm_request.c:1166:ldlm_cli_cancel_req()) Got rc -108 from cancel RPC: canceling anyway
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21531:0:(ldlm_request.c:1792:ldlm_cli_cancel_list()) ldlm_cli_cancel_list: -108
Jul 24 23:05:04 lustre-5 kernel: Lustre: server umount lustre-OST0002 complete
Jul 24 23:05:04 lustre-5 kernel: LustreError: 21531:0:(obd_mount.c:2569:lustre_fill_super()) Unable to mount (-19)
Thanks,
-Upanshu
Upanshu Singhal
EMC Data Storage Systems, Bangalore, India.
Phone: 91-80-67375604
7 years, 12 months
Error on executing llmount.sh
by Singhal, Upanshu
Hello,
I am able to install luster 2.3 now, but I am getting following error:
FATAL: Error inserting obdfilter (/lib/modules/2.6.32.lustremaster/updates/kernel/fs/lustre/obdfilter.ko): Unknown symbol in module, or unknown parameter (see dmesg)
obdfilter: Unknown symbol security_inode_unlink
This could be due to the following warning while installing luster-modules:
[root@lustre-5 lustre]# rpm -ivh lustre-modules-2.3.0-2.6.32.lustremaster.x86_64.rpm
Preparing... ########################################### [100%]
1:lustre-modules ########################################### [100%]
WARNING: /lib/modules/2.6.32.lustremaster/updates/kernel/fs/lustre/obdfilter.ko needs unknown symbol security_inode_unlink
Any insight?
Upanshu Singhal
EMC Data Storage Systems, Bangalore, India.
Phone: 91-80-67375604
8 years
Issue installing e2fsprogs on RHEL 6.3 for Lustre 2.3
by Singhal, Upanshu
Hello,
In order to install and configure Lustre 2.3 on RHEL 6.3, I am installing e2fsprogs packages. But I get following error, does anyone have faced the similar issue, if so, then what is the resolution?
[root@lustre-5 lustre]# rpm -Uvh ./e2fsprogs-1.42.7.wc1-7.el6.x86_64.rpm ./e2fsprogs-libs-1.42.7.wc1-7.el6.x86_64.rpm
error: Failed dependencies:
libcom_err >= 1.42.2 is needed by e2fsprogs-1.42.7.wc1-7.el6.x86_64
Thanks,
-Upanshu
Upanshu Singhal
EMC Data Storage Systems, Bangalore, India.
Phone: 91-80-67375604
8 years
Re: [HPDD-discuss] HPDD-discuss Digest, Vol 8, Issue 14
by Singhal, Upanshu
Hello Malcolm,
Thanks for your email, I have selinux=disabled, but still having the same issue.
Thanks,
-Upanshu
-----Original Message-----
From: hpdd-discuss-bounces(a)ml01.01.org [mailto:hpdd-discuss-bounces@ml01.01.org] On Behalf Of hpdd-discuss-request(a)ml01.01.org
Sent: Monday, July 22, 2013 2:31 PM
To: hpdd-discuss(a)ml01.01.org
Subject: HPDD-discuss Digest, Vol 8, Issue 14
Send HPDD-discuss mailing list submissions to
hpdd-discuss(a)lists.01.org
To subscribe or unsubscribe via the World Wide Web, visit
https://lists.01.org/mailman/listinfo/hpdd-discuss
or, via email, send a message with subject or body 'help' to
hpdd-discuss-request(a)lists.01.org
You can reach the person managing the list at
hpdd-discuss-owner(a)lists.01.org
When replying, please edit your Subject line so it is more specific than "Re: Contents of HPDD-discuss digest..."
Today's Topics:
1. Re: Issue installing Lustre 1.87 (Cowe, Malcolm J)
2. Re: Issue installing Lustre 1.87 (Singhal, Upanshu)
----------------------------------------------------------------------
Message: 1
Date: Mon, 22 Jul 2013 07:42:39 +0000
From: "Cowe, Malcolm J" <malcolm.j.cowe(a)intel.com>
To: "hpdd-discuss(a)lists.01.org" <hpdd-discuss(a)lists.01.org>
Subject: Re: [HPDD-discuss] Issue installing Lustre 1.87
Message-ID:
<5B2521AFFB62E743BE362149134E9A890D88B436(a)PGSMSX102.gar.corp.intel.com>
Content-Type: text/plain; charset="us-ascii"
+1: you almost certainly have SELinux enabled. The formatting of the file system will fail with this error when SELinux is configured. For example, on a test system I have set up a quick experiment to replicate your problem by setting SELinux to "enforcing":
[root@m64-1 ~]# cat /etc/selinux/config
# This file controls the state of SELinux on the system.
# SELINUX= can take one of these three values:
# enforcing - SELinux security policy is enforced.
# permissive - SELinux prints warnings instead of enforcing.
# disabled - No SELinux policy is loaded.
SELINUX=enforcing
# SELINUXTYPE= can take one of these two values:
# targeted - Targeted processes are protected,
# mls - Multi Level Security protection.
SELINUXTYPE=targeted
[root@m64-1 ~]# mkfs.lustre --reformat --mgs /dev/sdb
Permanent disk data:
Target: MGS
Index: unassigned
Lustre FS:
Mount type: ldiskfs
Flags: 0x64
(MGS first_time update )
Persistent mount opts: user_xattr,errors=remount-ro
Parameters:
device size = 1024MB
formatting backing filesystem ldiskfs on /dev/sdb
target name MGS
4k blocks 262144
options -q -O uninit_bg,dir_nlink,quota,huge_file,flex_bg -E lazy_journal_init -F
mkfs_cmd = mke2fs -j -b 4096 -L MGS -q -O uninit_bg,dir_nlink,quota,huge_file,flex_bg -E lazy_journal_init -F /dev/sdb 262144
mkfs.lustre: Can't make configs dir /tmp/mntRmd6cD/CONFIGS (Permission denied)
mkfs.lustre FATAL: failed to write local files
mkfs.lustre: exiting with -1 (Unknown error 18446744073709551615)
When SELinux is disabled, the file system will format without issue. You will have to edit the appropriate configuration (on RHEL/CentOS: /etc/selinux/config) and reboot the system in order for the change to take effect.
Regards,
Malcolm.
From: hpdd-discuss-bounces(a)lists.01.org [mailto:hpdd-discuss-bounces@lists.01.org] On Behalf Of Patrick Farrell
Sent: Friday, July 19, 2013 11:56 PM
To: hpdd-discuss(a)lists.01.org
Subject: Re: [HPDD-discuss] Issue installing Lustre 1.87
Upanshu,
The error message you're getting is what's expected if you still have SELinux enabled on that system. I don't think you need to worry about lctl or the LNET settings right now - The mkfs.lustre is failing because it can't make the temporary directory.
I'd make sure selinux is set to disabled in /etc/selinux/config.
The line which starts 'selinux=' should read 'disabled'.
You can check whether or not that setting has taken effect with:
getenforce
I'd suggest making sure of that config file change and restarting the system, then try your format command again.
- Patrick Farrell
8 years
LUG 2013 Survey Results
by OpenSFS Administration
Hello All,
Thank you for participating in the LUG 2013 survey, the results are in and
we have a winner! Congratulations to Richard H., Intel, who won his choice
of complementary LUG 2014 registration or a $200 Visa gift card.
We had 44 attendees participate in the survey and received valuable feedback
that will aid in 2014 planning. Some areas of interest were:
. Structure of agenda to be examined (length of sessions/days)
. Wealth of future topic ideas
. Split tracks are of interest to the audience
. Networking activity would be of value to attendees
Attached is the summary data for your review.
Please let us know if you have any questions.
Thank you,
OpenSFS Administration
__________________________
OpenSFS Administration
3855 SW 153rd Drive Beaverton, OR 97006 USA
Phone: +1 503-619-0561 | Fax: +1 503-644-6708
Twitter: <https://twitter.com/opensfs> @OpenSFS
Email: <mailto:admin@opensfs.org> admin(a)opensfs.org | Website:
<http://www.opensfs.org> www.opensfs.org
8 years
IB connectivity issues with Lustre 2.1.6
by Adesanya, Adeyemi
Hi.
I upgraded our OSS servers from 2.1.4 to 2.1.6 (RHEL6). Things looked OK until I discovered the IB clients are no longer able to communicate with the upgraded servers.
Seeing messages like this in the OSS logs:
Jul 19 19:28:55 ki-oss01 kernel: LustreError: 2248:0:(o2iblnd_cb.c:2903:kiblnd_cm_callback()) 192.168.115.100@o2ib: REJECTED 28
Jul 19 19:28:55 ki-oss01 kernel: LustreError: 2248:0:(o2iblnd_cb.c:2903:kiblnd_cm_callback()) Skipped 64 previous similar messages
Jul 19 19:30:01 ki-oss01 kernel: LustreError: 2248:0:(o2iblnd_cb.c:2903:kiblnd_cm_callback()) 192.168.115.120@o2ib: REJECTED 28
The IB clients will mount but df -h or any file dereferencing will hang. "lfs df" on the IB clients also shows the OSTs as inactive. tcp communications are just fine. I've also tried upgraded the client version from 2.1.4 to 2.1.6 - no difference. The message almost looks like it is related to some security policy.
Any suggestions before I roll back to version 2.1.4?
-------
Yemi
8 years
