[lustre-discuss] OST failure

We had an OST failure. Is there a way to 1. Make the whole Lustre FS read only? 2. Take the failing OST offline to try and recover what's possible? Thanks Michael Michael Hebenstreit Senior Cluster

Re: [lustre-discuss] build help with 5.15 kernel

Thanks for the pointers. -Original Message- From: Degremont, Aurelien Sent: Monday, January 3, 2022 3:35 AM To: Hebenstreit, Michael ; lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] build help with 5.15 kernel Hello Michael Lustre 2.12.8 does not support Linux 5.15

[lustre-discuss] build help with 5.15 kernel

On Behalf Of Hebenstreit, Michael via lustre-discuss Sent: Thursday, December 30, 2021 5:07 PM To: lustre-discuss@lists.lustre.org Subject: [lustre-discuss] build help with 5.15 kernel Hello I'm trying to build the Lustre 2.12.8 client on a 5.15 kernel and already failing in the configure step

[lustre-discuss] build help with 5.15 kernel

Hello I'm trying to build the Lustre 2.12.8 client on a 5.15 kernel and already failing in the configure step. Looks to me like something in the build process has changed. The failure occurs in configure line 14390. From the log: configure:14390: cp conftest.c build && make -d

Re: [lustre-discuss] bios spray passwd change

For Intel server motherboards the tool is called "syscfg". From: lustre-discuss On Behalf Of Einar Næss Jensen Sent: Thursday, June 25, 2020 06:53 To: Hopper, Edward - CTR ; lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] bios spray passwd change Hello. Don't know what

Re: [lustre-discuss] problem after upgrading 2.10.4 to 2.12.4

mas On 24.06.20 20:43, Hebenstreit, Michael wrote: > I would not plan a direct upgrade until Whamcloud fixes the underlying issue. > Currently the only viable way seem to be a step by step upgrade. I imagine > you'd first upgrade to 2.10.8, and then copy all old file to a new place > (someth

Re: [lustre-discuss] problem after upgrading 2.10.4 to 2.12.4

Am Dienstag, den 23.06.2020, 20:03 + schrieb Hebenstreit, Michael: >> Is there any way to stop the scans on the OSTs? > Yes, by re-mounting them with -o noscrub. This doesn't fix the issue > though. > >> Is there any way to force the file system checks? > As shown in y

Re: [lustre-discuss] problem after upgrading 2.10.4 to 2.12.4

previous similar messages Is there any way to stop the scans on the OSTs? From: Hebenstreit, Michael Sent: Tuesday, June 23, 2020 11:19 To: lustre-discuss@lists.lustre.org Subject: problem after upgrading 2.10.4 to 2.12.4 We experienced on our Archive Lustre (ZFS based, 4 OST servers with 6

[lustre-discuss] problem after upgrading 2.10.4 to 2.12.4

We experienced on our Archive Lustre (ZFS based, 4 OST servers with 6 OSTs pools each) the very same issues as described here: https://jira.whamcloud.com/browse/LU-13392 Certain directories cannot be accessed, and the OSTs shows thousands of errors "Can't find FID Sequence". Unfortunately I

[lustre-discuss] Lustre client on RedHat 7.8

Trying to compile for new RH kernel I got some errors, I think because of https://patchwork.kernel.org/patch/11061873/. My solution was this patch $ cat /admin/work/buildenv_rh7/OFED/mlnx-5.0-2.1.8.0-1127.8.2-2.10.8/extra/gss_svc_upcall.patch --- lustre/ptlrpc/gss/gss_svc_upcall.c.orig

Re: [lustre-discuss] changing inode size on MDT

Sent: Monday, November 11, 2019 15:55 To: Hebenstreit, Michael Cc: Mohr Jr, Richard Frank ; lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] changing inode size on MDT You can check the ashift of the zpool via "zpool get all | grep ashift". If this is different, it will m

Re: [lustre-discuss] changing inode size on MDT

libzfs2-0.7.9-1.el7.x86_64 lustre-osd-zfs-mount-2.10.8-1.el7.x86_64 lustre-zfs-dkms-2.10.8-1.el7.noarch zfs-0.7.9-1.el7.x86_64 zfs-dkms-0.7.9-1.el7.noarch From: Andreas Dilger Sent: Thursday, October 03, 2019 20:38 To: Hebenstreit, Michael Cc: Mohr Jr, Richard Frank ; lustre-discuss

Re: [lustre-discuss] changing inode size on MDT

So bottom line - don't change the default values, it won't get better? From: Andreas Dilger Sent: Thursday, October 03, 2019 19:38 To: Hebenstreit, Michael Cc: Mohr Jr, Richard Frank ; lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] changing inode size on MDT On Oct 3, 2019

Re: [lustre-discuss] changing inode size on MDT

: Thursday, October 03, 2019 05:41 To: Degremont, Aurelien ; Hebenstreit, Michael ; Andreas Dilger Cc: lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] changing inode size on MDT Hi, A little pedantic but for ‘inodes’ don’t exist in a zfs pool per-se. So the code which attempts to report

Re: [lustre-discuss] changing inode size on MDT

2, 2019 18:49 To: Hebenstreit, Michael Cc: Mohr Jr, Richard Frank ; lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] changing inode size on MDT There are several confusing/misleading comments on this thread that need to be clarified... On Oct 2, 2019, at 13:45, Hebenstrei

Re: [lustre-discuss] changing inode size on MDT

Message- From: Mohr Jr, Richard Frank Sent: Wednesday, October 02, 2019 13:39 To: Hebenstreit, Michael Cc: lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] changing inode size on MDT > On Oct 2, 2019, at 1:08 PM, Hebenstreit, Michael > wrote: > > Could anyone poi

Re: [lustre-discuss] changing inode size on MDT

This is for an archiving system (1PB) with no performance or other special requirements but a lot of small files (I know, not a Lustre speciality) Thanks Michael From: Colin Faber Sent: Wednesday, October 02, 2019 11:19 To: Hebenstreit, Michael Cc: lustre-discuss@lists.lustre.org Subject: Re

[lustre-discuss] changing inode size on MDT

Could anyone point out to me what the downside of having an inode size of 1k on the MDT would be (compared to the 4k default)? Thanks Michael Michael Hebenstreit Senior Cluster Architect Intel Corporation,

Re: [lustre-discuss] lustre client on centos 7.7

In the new kernel include/linux/pci-dma.h is missing – I copied it from an older version From: lustre-discuss On Behalf Of w...@umich.edu Sent: Wednesday, September 25, 2019 15:13 To: discussion Subject: Re: [lustre-discuss] lustre client on centos 7.7 Hi All We are also encounting problems

Re: [lustre-discuss] request for help - ZFS based Lustre, MDT disk not mounting

PM To: Hebenstreit, Michael Cc: lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] request for help - ZFS based Lustre, MDT disk not mounting On Wed, Jun 20, 2018 at 12:13 AM Hebenstreit, Michael wrote: > Mount succeeded finally after 30+min I've had similar situations after unclean shu

Re: [lustre-discuss] request for help - ZFS based Lustre, MDT disk not mounting

Mount succeeded finally after 30+min Mount as zfs worked -Original Message- From: Peter Bortas [mailto:bor...@gmail.com] Sent: Tuesday, June 19, 2018 4:08 PM To: Hebenstreit, Michael Cc: lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] request for help - ZFS based Lustre

Re: [lustre-discuss] request for help - ZFS based Lustre, MDT disk not mounting

94061 2 mgs osd_zfs 363587 31 lquota363475 77 mdt,osd_zfs From: Feng Zhang [mailto:prod.f...@gmail.com] Sent: Tuesday, June 19, 2018 8:13 AM To: Hebenstreit, Michael Cc: lustre-discuss Subject: Re: [lustre-discuss] request for help - ZFS based

[lustre-discuss] request for help - ZFS based Lustre, MDT disk not mounting

Mount commands hangs, no error messages in kernel log, tried already rebooting (twice) - any ideas? Thanks Michael root 4137 0.0 0.0 123520 1048 pts/0S+ 07:56 0:00 mount -t lustre mgsmdt/mdt /lfs/lfs11/mdt root 4138 0.0 0.0 81728 3272 pts/0S+ 07:56 0:00

Re: [lustre-discuss] server_bulk_callback errors until server reboots

] Sent: Thursday, June 07, 2018 10:36 AM To: Hebenstreit, Michael Cc: White, Cliff ; lustre-discuss Subject: Re: [lustre-discuss] server_bulk_callback errors until server reboots I seen the error when we had mix of FDR (using mlx4) and EDR(using mlx5) devices in lustre network

Re: [lustre-discuss] server_bulk_callback errors until server reboots

No, clients do not show any issues. -Original Message- From: White, Cliff Sent: Thursday, June 07, 2018 9:26 AM To: Hebenstreit, Michael ; lustre-discuss Subject: Re: [lustre-discuss] server_bulk_callback errors until server reboots On 6/7/18, 7:00 AM, "lustre-discuss on b

[lustre-discuss] problem with one orphan

I've got an orphan problem - this process on the combined mds/mgs is running at 100%    PID USER  PR  NI    VIRT    RES    SHR S  %CPU %MEM TIME+ COMMAND   5902 root  20   0   0  0  0 R 100.0  0.0 974:22.49 orph_lfs11-MDD0 And I literally got millions of dmesg entries

Re: [lustre-discuss] rhel 7.5

I have 2.11 already running on a 7.5 clone (client only) -Original Message- From: lustre-discuss [mailto:lustre-discuss-boun...@lists.lustre.org] On Behalf Of Michael Di Domenico Sent: Monday, April 30, 2018 11:49 AM Cc: lustre-discuss Subject: Re:

Re: [lustre-discuss] Do I need Lustre?

You can do a simple test. Run a small sample of you application directly out of /dev/shm (the ram-disk). Then run it from the NFS file server. If you measure significant speedups your application is I/O sensitive and a Lustre configured with OPA or other InfiniBand solution will help. From:

Re: [lustre-discuss] file distribution over OSTs

Thanks – and sorry – my comment on “verbose” was for the command, not about your info ☺ Case closed, thanks all for answers That was quick ☺ From: Colin Faber [mailto:cfa...@gmail.com] Sent: Tuesday, April 07, 2015 3:54 PM To: Hebenstreit, Michael Subject: Re: [lustre-discuss] file

[lustre-discuss] file distribution over OSTs

Can I find out how a file (size 130GB, stripesize 1MB) is distributed over OSTs? thanks Michael Michael Hebenstreit Senior Cluster Architect Intel Corporation, MS: RR1-105/H14  Software and Services

Re: [lustre-discuss] file distribution over OSTs

: Colin Faber [mailto:cfa...@gmail.com] Sent: Tuesday, April 07, 2015 3:45 PM To: Hebenstreit, Michael Cc: lustre-discuss@lists.lustre.org Subject: Re: [lustre-discuss] file distribution over OSTs lfs getstripe is the command you're looking for. On Tue, Apr 7, 2015 at 3:43 PM, Hebenstreit, Michael

[Lustre-discuss] module dependecies

Please do not ask why, but I need to be able to replace the IB stack (as in - all InfiniBand modules) at runtime with a Lustre FS mounted. Is there a possibility to tell lnet to completely switch to tcp, unload ko2iblnd.ko and next unload the IB stack, load the new IB stack, load a matching

Re: [Lustre-discuss] unmounting with open requests

, January 16, 2014 7:22 AM To: Hebenstreit, Michael Cc: lustre-discuss@lists.lustre.org Subject: Re: [Lustre-discuss] unmounting with open requests On Jan 15, 2014, at 3:08 PM, Hebenstreit, Michael michael.hebenstr...@intel.com wrote: umount -f will not work if you have open kernel calls

[Lustre-discuss] unmounting with open requests

Is there a way to force the Lustre kernel modules to cancel/terminate all outstanding requests and allow the file system to be unmounted and the kernel modules to be removed from the running kernel? Thanks Michael Michael

Re: [Lustre-discuss] unmounting with open requests

unmounting/lustre_rmmod will work Michael From: Lee, Brett Sent: Wednesday, January 15, 2014 12:56 PM To: Hebenstreit, Michael; lustre-discuss@lists.lustre.org Subject: RE: unmounting with open requests Michael, Not that I know of. But you might try a different order, unmounting any Lustre mounts

Re: [Lustre-discuss] configure error using Lustre 2.3 and OFED 3.5

I had to do quite a few patches to OFE 3.5 to get it compiled. Essentially nothing but taking care of functions backported by RH to the kernel Michael -Original Message- From: Shuichi Ihara [mailto:sih...@ddn.com] Sent: Saturday, April 20, 2013 3:23 AM To: Hebenstreit, Michael Cc

[Lustre-discuss] configure error using Lustre 2.3 and OFED 3.5

Configure fails at testing for openib - anyone an idea? Thanks Michaell configure:10034: checking whether to enable OpenIB gen2 support configure:10138: cp conftest.c build make -d modules CC=gcc -f /home/mhebenst/lustre-2.3.0/build/Makefile LUSTRE_LINUX_CONFIG=/adm

Re: [Lustre-discuss] configure error using Lustre 2.3 and OFED 3.5

That's not my problem - OFED is working, Lustre is not willing to compile :P Michael -Original Message- From: Diep, Minh Sent: Friday, April 19, 2013 5:33 PM To: Hebenstreit, Michael; Lustre-discuss@lists.lustre.org Subject: Re: [Lustre-discuss] configure error using Lustre 2.3 and OFED

Re: [Lustre-discuss] configure error using Lustre 2.3 and OFED 3.5

script is .. not advisable Michael -Original Message- From: lustre-discuss-boun...@lists.lustre.org [mailto:lustre-discuss-boun...@lists.lustre.org] On Behalf Of Hebenstreit, Michael Sent: Friday, April 19, 2013 5:39 PM To: Diep, Minh; Lustre-discuss@lists.lustre.org Subject: Re

[Lustre-discuss] is there a way to run Lustre over UDP instead TCP?

See title... Thanks Michael Michael Hebenstreit Senior Cluster Architect Intel Corporation Software and Services Group/HTE 2800 N Center Dr, DP3-307 Tel.: +1 253 371 3144 WA

Re: [Lustre-discuss] rhel6.1?

I have 1.8.5.56 working for almost a 9 months now patchless with RH61 and OFED 1.5.3 - so I guess you are safe using 1.8.6 or later Michael -Original Message- From: lustre-discuss-boun...@lists.lustre.org [mailto:lustre-discuss-boun...@lists.lustre.org] On Behalf Of Michael Di

Re: [Lustre-discuss] Help! Newbie trying to set up Lustre network

you should do a lsmod and check what modules are loaded :) -Original Message- From: lustre-discuss-boun...@lists.lustre.org [mailto:lustre-discuss-boun...@lists.lustre.org] On Behalf Of Brian J. Murrell Sent: Tuesday, February 22, 2011 11:17 AM To: lustre-discuss@lists.lustre.org

[Lustre-discuss] trying to port 1.8.5 to RH6 I'm facing Kernel panics due to an error in the handling of page-private

If I understand everything correctly page-private should contain either 0 or a pointer to kernel space. For reasons I can not currently comprehend sometimes the value is set to 2. llap_cast_private() then tries to access page-private-llap_magic, and naturally this leads to NULL pointer