similar to: Remove filesystem directories from MDT

Hello, lfs prints different obd(idx) compared to lctl dl. We use single striping. cluster1 tmp # lfs find --obd scia-OST0017_UUID /data/scia/L0/V0.00/20100327/SCI_NL__0PNPDE20100327_193441_000040582088_00071_42209_1158.N1 /data/scia/L0/V0.00/20100327/SCI_NL__0PNPDE20100327_193441_000040582088_00071_42209_1158.N1 cluster1 tmp # lfs getstripe

Hi, I''m seeing what can only be described as dismal striped write performance from lustre 1.6.3 clients :-/ 1.6.2 and 1.6.1 clients are fine. 1.6.4rc3 clients (from cvs a couple of days ago) are also terrible. the below shows that the OS (centos4.5/5) or fabric (gigE/IB) or lustre version on the servers doesn''t matter - the problem is with the 1.6.3 and 1.6.4rc3 client kernels

I''m a Lustre newbie who just joined this list. I''d appreciate any help on the following Lustre 2.4 issue I''m running into: Every time I mount the MDT, the mount appears to succeed but /var/log/messages contains the message: "LustreError: 11-0: lustre-MDT0000-lwp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11". The MDT uses 4 local

Hi, The documentation warns about using smaller inodes than 512 bytes on the MDT. If I plan to use a stripecount of one (I have many small files), is it possible to use an inode size of 256 bytes and still use in-inode EAs for metadata ? Thanks /Jakob

Greetings Group! I hope this will be an easy one. To conserve steps in backing up the metadata extended attributes of a Lustre mdt, I am looking at using a newer version of tar combined with its --xattrs option. (Note: Previously I have used the mdt two-step back-up from the Lustre Manual and it has been successful.) If I can backup the extended attributes via tar so that I don''t

Just checking to be sure this isn''t a known bug or problem. I couldn''t find a bz for this, but it would appear that tunefs.lustre --print fails on a lustre mdt or ost device if mounted with mmp. Is this expected behavior? TIA mds1-gps:~ # tunefs.lustre --print /dev/mapper/mdt1 checking for existing Lustre data: not found tunefs.lustre FATAL: Device /dev/mapper/mdt1 has not

Article by Jeff Layton: http://www.linux-mag.com/id/7839 anyone have views on whether this sort of caching would be useful for the MDT? My feeling is that MDT reads are probably pretty random but writes might benefit...? GREG -- Greg Matthews 01235 778658 Senior Computer Systems Administrator Diamond Light Source, Oxfordshire, UK

For future filesystem compatibility, we are wondering if there are any Lustre MDT filesystems in existence that have 2B or more total inodes? This is fairly unlikely, because it would require an MDT filesystem that is > 8TB in size (which isn''t even supported yet) and/or has been formatted with specific options to increase the total number of inodes. This can be checked with

For future filesystem compatibility, we are wondering if there are any Lustre MDT filesystems in existence that have 2B or more total inodes? This is fairly unlikely, because it would require an MDT filesystem that is > 8TB in size (which isn''t even supported yet) and/or has been formatted with specific options to increase the total number of inodes. This can be checked with

I am trying to build lustre-1.6.6 against the pre-patched kernel downloaded from SUN. But as written in Operations manual, it creates rpms for 2.6.18-92.1.10.el5_lustrecustom. Is there a way to ask it not to append custom as extraversion. Running kernel is 2.6.18-92.1.10.el5_lustre.1.6.6smp. -- Regards-- Rishi Pathak National PARAM Supercomputing Facility Center for Development of Advanced

From: Scott Seago <sseago at redhat.com> This adds some of the network API stuff to ovirt-agent. It's still not complete but what is there is functional. Signed-off-by: Ian Main <imain at redhat.com> --- src/ovirt-agent/lib/ovirt.rb | 3 + .../ovirt/controllers/hardwarepool_controller.rb | 2 +- .../lib/ovirt/controllers/network_controller.rb |

This isn't yet functional, but I'm submitting the patch so Ian can continue work on it. Signed-off-by: Scott Seago <sseago at redhat.com> --- .../lib/ovirt/controllers/network_controller.rb | 26 ++++++++++++++++++++ .../physical_network_impl_controller.rb | 10 +++++++ .../lib/ovirt/controllers/vlan_impl_controller.rb | 9 +++++++

Hello, I would like to" btrfs restore" a broken btrfs filesystem before I attempt to recover it. However, I only need to recover a subvolume inside of it. It seems the -r option should do the job, but I do not know the objid number of the subvolume I want, only the path. Is there a way to know the objid of a subvolume given its path, without mounting the filesystem? Thanks, Cesar

Hi all, Here is the situation: I have 2 nodes MDS1 , MDS2 (10.0.0.22 , 10.0.0.23) I wish to use as failover MGS, active/active MDT with zfs. I have a jbod shelf with 12 disks, seen by both nodes as das (the shelf has 2 sas ports, connected to a sas hba on each node), and I am using lustre 2.4 on centos 6.4 x64 I have created 3 zfs pools: 1. mgs: # zpool

Hi Guys, I''m trying to figure out a way to get a list of files with objects present on an OST that is down. Normally one could do: lfs find -O <OST> dir but that is giving us Input/output errors (I assume because the OST is down). Is there a good way to get a list of objects (Maybe from the MDS?), what OSTs they are on, and correlate them with files? Thanks, Mark -- Mark

The Processors agent reports details regarding the processing power for the managed node. Defined the agent within schema.xml. Wrote the wrapper code to create and populate an instance of the agent. The properties for the Processors agent have also been trimmed back to what is readily available via HAL. Signed-off-by: Darryl L. Pierce <dpierce at redhat.com> --- src/Makefile.am | 26

Hello, I am building an Rails applications that has to integrate an legacy system (lxoffice) (schema at: http://www.lx-office.org/uploads/media/DB_Schema_2.1.1_R_393_17_03_2005_.pdf). They somehow use global ids (global for some tables). I can not change the schema and still I want to use Rails to access it and not pure SQL. When I try to insert a record I get the following message:

Hi, Doing connection.pk_and_sequence_for doesn''t return anything when I''m positive I''ve got a PK and sequence on my table on column "id", see DDL below. Is this a bug? ?> Player.primary_key => "id" >> Player.connection.default_sequence_name "players" => "players_id_seq" >>

Le 06/03/2011 00:14, "Hung-Sheng Tsao (Lao Tsao ??) Ph. D." a ?crit : > question to solaris forum > http://forums.oracle.com/forums/search.jspa?objID=c300&q=Solaris Since you have been (and you alone) kind enough to try and help me, I will give you in writing a detailed explanation on how this mess came to be : however, as I explained, I have only known the Solaris OS, or

There was no valid reason to keep this set of APIs in their own agent and class, so those have been eliminated. A new HostListener method, HostListener::updated(), was added. It is via this method that the Host will notify all transports that the load average statistic is updated on the host. Signed-off-by: Darryl L. Pierce <dpierce at redhat.com> --- src/Makefile.am | 11