[Lustre-discuss] [EXTERNAL] Re: Newbie - Unable to mount the OST on the Client
Gupta, Amit
amit.gupta at optum.com
Thu Jan 8 09:06:36 PST 2015
That is starting to make sense.. Let me summarize so I have got it right
Current
mkfs.lustre --fsname=temp --mgs --mdt --index=0 /dev/mapper/mpathcp1 - On MDS/MGS
mkfs.lustre --ost --fsname=client1 --reformat --index=0 --mgsnode=10.177.33.10 at tcp0 /dev/zvol/LSD1Pool/LusterVola0 - ON OST
New
mkfs.lustre --fsname=client1 --mgs --mdt --index=0 /dev/mapper/mpathcp1 - On MDS/MGS
mkfs.lustre --ost --fsname=client1 --reformat --index=0 --mgsnode=10.177.33.10 at tcp0 /dev/zvol/LSD1Pool/LusterVola0 - ON OST
So the only change is the fsname that I had used while creating the MDT should be same as the fsname when creating OST .. In this case it is "client1"
Does that sound correct Rick and Joe ?
-----Original Message-----
From: Mohr Jr, Richard Frank (Rick Mohr) [mailto:rmohr at utk.edu]
Sent: Thursday, January 08, 2015 10:59 AM
To: Gupta, Amit
Cc: Mervini, Joseph A; lustre discuss
Subject: Re: [Lustre-discuss] [EXTERNAL] Re: Newbie - Unable to mount the OST on the Client
Amit,
Are you by any chance specifying a unique value for --fsname for each of the MDT/OSTs? If so, keep in mind that fsname needs to be the same when you format all the MDT/OST devices and that the fsname doesn't have anything to do with the mount point for the MDT/OSTs.
--Rick
On Jan 8, 2015, at 11:52 AM, "Gupta, Amit" <amit.gupta at optum.com<mailto:amit.gupta at optum.com>>
wrote:
> Joe, I agree and I have it configured the same way as you described.. Both the MGS and MDS are on the same node. Adding the output ..
>
> What am I missing here ?. Thanks
>
>
> Here’s what I had used on the MDS/MGS node to configure the lustre fs
>
> mkfs.lustre --fsname=temp --mgs --mdt --index=0 /dev/mapper/mpathcp1
>
> df- k output on MGS/MDS
> /dev/mapper/mpathcp1 201286044 4273344 183232496 3% /mdt
>
>
> [root at mgs/mds ~]# cat /proc/fs/lustre/mgs/MGS/live/*
> fsname: client1
> flags: 0x20 gen: 5
> client1-OST0000
>
> Secure RPC Config Rules:
>
> imperative_recovery_state:
> state: full
> nonir_clients: 0
> nidtbl_version: 4
> notify_duration_total: 0.000000
> notify_duation_max: 0.000000
> notify_count: 2
> fsname: params
> flags: 0x21 gen: 1
>
> Secure RPC Config Rules:
>
> imperative_recovery_state:
> state: full
> nonir_clients: 0
> nidtbl_version: 2
> notify_duration_total: 0.000000
> notify_duation_max: 0.000000
> notify_count: 0
> fsname: temp
> flags: 0x20 gen: 7
> temp-MDT0000
>
> Secure RPC Config Rules:
>
> imperative_recovery_state:
> state: full
> nonir_clients: 0
> nidtbl_version: 4
> notify_duration_total: 0.000000
> notify_duation_max: 0.000000
> notify_count: 1
>
>
> [root at mgs/mds] debugfs -c -R 'ls -l CONFIGS' /dev/mapper/mpathcp1
> debugfs 1.42.12.wc1 (15-Sep-2014)
> /dev/mapper/mpathcp1: catastrophic mode - not reading inode or group bitmaps -
> 32769 40755 (2) 0 0 4096 6-Jan-2015 13:09 .
> 2 40755 (2) 0 0 4096 6-Jan-2015 13:10 ..
> 12 100644 (1) 0 0 12288 6-Jan-2015 13:10 mountdata
> 81 100644 (1) 0 0 0 6-Jan-2015 13:10 params-client
> 82 100644 (1) 0 0 0 6-Jan-2015 13:10 params
> 83 100644 (1) 0 0 11200 6-Jan-2015 13:10 temp-client
> 84 100644 (1) 0 0 9792 6-Jan-2015 13:10 temp-MDT0000
> 104 100644 (1) 0 0 10600 6-Jan-2015 13:12 client2-client
> 105 100644 (1) 0 0 8880 6-Jan-2015 13:12 client2-OST0000
> 107 100644 (1) 0 0 10600 6-Jan-2015 23:38 client1-client
> 108 100644 (1) 0 0 8880 6-Jan-2015 23:38 client1-OST0000
>
>
> From: Mervini, Joseph A [mailto:jamervi at sandia.gov]
> Sent: Thursday, January 08, 2015 10:43 AM
> To: Gupta, Amit
> Cc: 한종우; lustre discuss
> Subject: Re: [EXTERNAL] Re: [Lustre-discuss] Newbie - Unable to mount
> the OST on the Client
>
> In lustre you MUST have a MGS _AND_ MDS node and an associated MDT (file system) running on the MDS. Typically the MDS and MGS are configured on the same node.
>
> If you don't have this, lustre won't work.
> ====
>
> Joe Mervini
> Sandia National Laboratories
> High Performance Computing
> 505.844.6770
> jamervi at sandia.gov<mailto:jamervi at sandia.gov>
>
>
>
> On Jan 8, 2015, at 7:23 AM, Gupta, Amit <amit.gupta at optum.com<mailto:amit.gupta at optum.com>> wrote:
>
>
> Jongwoo,
>
> This is the mount command that is being used on the client machine
> [root at Client ~]# mount -t lustre 10.177.33.10 at tcp:/client1<mailto:10.177.33.10 at tcp:/client1> /mnt/lustre
>
> Here 10.177.33.10 is the MGS Server and “client1” is the filesystem
> name for the OST
>
> On the OSS, here is this filesystem mounted as
>
> /dev/zd912 1069706420 483556 1013552180 1% /client1
> The commands used on OST to mount and format “client1” were
>
> mkfs.lustre --ost --fsname=client1 --reformat --index=0
> --mgsnode=10.177.33.10 at tcp0<mailto:--mgsnode=10.177.33.10 at tcp0> /dev/zvol/LSD1Pool/LusterVola0 mount -t
> lustre /dev/zvol/LSD1Pool/LusterVola0 /client1
>
>
>
> From: 한종우 [mailto:jw.han at apexcns.com]
> Sent: Wednesday, January 07, 2015 9:20 PM
> To: Gupta, Amit
> Cc: lustre-discuss at lists.lustre.org<mailto:lustre-discuss at lists.lustre.org>
> Subject: Re: [Lustre-discuss] Newbie - Unable to mount the OST on the
> Client
>
> Hi Gupta,
>
> What I see is
>
> • there is no MDS and/or filesystem name
> • mount command did not specify filesystem name, otherwise the filesystem name is "client1"
> try preparing MDT volume and format it with a filesystem name( on the
> MGS is okay) and mount the MDT, and retry lustre mount with following
> command
>
> [root at Client ~]# mount -t lustre 10.177.33.10 at tcp:/<FILESYSTEMNAME<mailto:10.177.33.10 at tcp:/<FILESYSTEMNAME>>
> /mnt/lustre
>
> Regards,
>
> Jongwoo Han
>
>
> 2015-01-07 22:25 GMT+09:00 Gupta, Amit <amit.gupta at optum.com<mailto:amit.gupta at optum.com>>:
> Hi All ,
>
> Need some guidance on getting past this error that I get mounting the OST on the Client. This is the first time I am trying to mount it so not sure what I could be missing.. I will be glad to provide any other logs that would be helpful to determine the root cause of this issue..
>
> Thanks
>
> There are 3 servers in the configuration running Lustre
> kernel-2.6.32-431.20.3.el6_lustre.x86_64
>
> 10.177.33.10 is MGS/MGT Server
> 10.177.33.9 is the Lustre Client
> 10.177.33.22 is OSS
>
>
> [root at Client ~]# mount -t lustre 10.177.33.10 at tcp:/client1<mailto:10.177.33.10 at tcp:/client1> /mnt/lustre
> mount.lustre: mount 10.177.33.10 at tcp:/client1<mailto:10.177.33.10 at tcp:/client1> at /mnt/lustre failed:
> Invalid argument This may have multiple causes.
> Is 'client1' the correct filesystem name?
> Are the mount options correct?
> Check the syslog for more info
>
>
> The OST is mounted on OSS as Client1
>
>
>
>
> Error from Logs
>
> Jan 7 13:10:46 client kernel: LustreError: 156-2: The client profile
> 'client1-client' could not be read from the MGS. Does that filesystem exist?
> Jan 7 13:10:46 client kernel: LustreError:
> 11278:0:(lov_obd.c:951:lov_cleanup()) client1-clilov-ffff8820337cec00:
> lov tgt 0 not cleaned! deathrow=0, lovrc=1 Jan 7 13:10:46 client
> kernel: Lustre: Unmounted client1-client Jan 7 13:10:46 client
> kernel: LustreError: 13167:0:(obd_mount.c:1342:lustre_fill_super())
> Unable to mount (-22)
>
> ================================================
>
> Pinging MGS and Client from OSS
> =================================================
>
> [root at OSS ]# lctl ping 10.177.33.10
> 12345-0 at lo
> 12345-10.177.33.10 at tcp<mailto:12345-10.177.33.10 at tcp>
> [root at OSS]# lctl ping 10.177.33.9
> 12345-0 at lo
> 12345-10.177.33.9 at tcp<mailto:12345-10.177.33.9 at tcp>
>
> =====================
> OST mounted as Client1 on OSS
> =============================
>
> /dev/zd912 1069706420 483556 1013552180 1% /client1
>
>
> [root at OSS]# tunefs.lustre /dev/zd912
> checking for existing Lustre data: found Reading CONFIGS/mountdata
>
> Read previous values:
> Target: client1-OST0000
> Index: 0
> Lustre FS: client1
> Mount type: ldiskfs
> Flags: 0x2
> (OST )
> Persistent mount opts: errors=remount-ro
> Parameters: mgsnode=10.177.33.10 at tcp<mailto:mgsnode=10.177.33.10 at tcp>
>
>
> Permanent disk data:
> Target: client1-OST0000
> Index: 0
> Lustre FS: client1
> Mount type: ldiskfs
> Flags: 0x2
> (OST )
> Persistent mount opts: errors=remount-ro
> Parameters: mgsnode=10.177.33.10 at tcp<mailto:mgsnode=10.177.33.10 at tcp>
>
>
> lctl > modules
> add-symbol-file lustre/osp/osp.o 0xffffffffa10f5000 add-symbol-file
> lustre/mdd/mdd.o 0xffffffffa0b12000 add-symbol-file lustre/lod/lod.o
> 0xffffffffa109f000 add-symbol-file lustre/mdt/mdt.o 0xffffffffa0fe7000
> add-symbol-file lustre/mgs/mgs.o 0xffffffffa08c9000 add-symbol-file
> lustre/lfsck/lfsck.o 0xffffffffa0f17000 add-symbol-file
> lustre/ost/ost.o 0xffffffffa018c000 add-symbol-file lustre/mgc/mgc.o
> 0xffffffffa0ef9000 add-symbol-file lustre/quota/lquota.o
> 0xffffffffa0dfc000 add-symbol-file lustre/llite/lustre.o
> 0xffffffffa0ce2000 add-symbol-file lustre/lov/lov.o 0xffffffffa0c66000
> add-symbol-file lustre/mdc/mdc.o 0xffffffffa0c25000 add-symbol-file
> lustre/fid/fid.o 0xffffffffa0c07000 add-symbol-file lustre/lmv/lmv.o
> 0xffffffffa0bbc000 add-symbol-file lustre/fld/fld.o 0xffffffffa0b9d000
> add-symbol-file lnet/klnds/socklnd/ksocklnd.o 0xffffffffa0b64000
> add-symbol-file lustre/ptlrpc/ptlrpc.o 0xffffffffa0923000
> add-symbol-file lustre/obdclass/obdclass.o 0xffffffffa06e4000
> add-symbol-file lnet/lnet/lnet.o 0xffffffffa067b000 add-symbol-file
> libcfs/libcfs/libcfs.o 0xffffffffa05e1000 add-symbol-file
> ldiskfs/ldiskfs.o 0xffffffffa055d000 lctl > lustre_build_version
> Lustre version: 2.6.0-RC2--PRISTINE-2.6.32-431.20.3.el6_lustre.x86_64
> lctl version: 2.6.0-RC2--PRISTINE-2.6.32-431.20.3.el6_lustre.x86_64
>
>
>
>
> ]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]
> ]] ==================================================
>
> On MGS Server
> ====================================================
>
> [root at MGS ~]# lctl ping 10.177.33.9 at tcp<mailto:10.177.33.9 at tcp> 12345-0 at lo
> 12345-10.177.33.9 at tcp<mailto:12345-10.177.33.9 at tcp> [root at MGS ~]# lctl ping 10.177.33.22 at tcp<mailto:10.177.33.22 at tcp>
> 12345-0 at lo 12345-10.177.33.22 at tcp<mailto:12345-10.177.33.22 at tcp> [root at MGS ~]# cat
> /proc/fs/lustre/mgs/MGS/live/*
> fsname: client1
> flags: 0x20 gen: 5
> client1-OST0000
>
> Secure RPC Config Rules:
>
> imperative_recovery_state:
> state: full
> nonir_clients: 0
> nidtbl_version: 3
> notify_duration_total: 0.000000
> notify_duation_max: 0.000000
> notify_count: 1
> fsname: params
> flags: 0x21 gen: 1
>
> Secure RPC Config Rules:
>
> imperative_recovery_state:
> state: full
> nonir_clients: 0
> nidtbl_version: 2
> notify_duration_total: 0.000000
> notify_duation_max: 0.000000
> notify_count: 0
> fsname: temp
> flags: 0x20 gen: 7
> temp-MDT0000
>
> Secure RPC Config Rules:
>
> imperative_recovery_state:
> state: full
> nonir_clients: 0
> nidtbl_version: 4
> notify_duration_total: 0.000000
> notify_duation_max: 0.000000
> notify_count: 1
>
>
> lctl > lustre_build_version
> Lustre version: 2.6.0-RC2--PRISTINE-2.6.32-431.20.3.el6_lustre.x86_64
> lctl version: 2.6.0-RC2--PRISTINE-2.6.32-431.20.3.el6_lustre.x86_64
> lctl > modules
> add-symbol-file lustre/osp/osp.o 0xffffffffa10bc000 add-symbol-file
> lustre/mdd/mdd.o 0xffffffffa1057000 add-symbol-file lustre/lod/lod.o
> 0xffffffffa0fed000 add-symbol-file lustre/mdt/mdt.o 0xffffffffa0f0d000
> add-symbol-file lustre/lfsck/lfsck.o 0xffffffffa0e97000
> add-symbol-file lustre/mgs/mgs.o 0xffffffffa0e3c000 add-symbol-file
> lustre/mgc/mgc.o 0xffffffffa0e10000 add-symbol-file
> lustre/quota/lquota.o 0xffffffffa0d13000 add-symbol-file
> ldiskfs/ldiskfs.o 0xffffffffa0c8f000 add-symbol-file
> lustre/llite/lustre.o 0xffffffffa0b75000 add-symbol-file
> lustre/lov/lov.o 0xffffffffa0af9000 add-symbol-file lustre/mdc/mdc.o
> 0xffffffffa0ab8000 add-symbol-file lustre/fid/fid.o 0xffffffffa0a9a000
> add-symbol-file lustre/lmv/lmv.o 0xffffffffa0a4f000 add-symbol-file
> lustre/fld/fld.o 0xffffffffa0a38000 add-symbol-file
> lnet/klnds/socklnd/ksocklnd.o 0xffffffffa09ff000 add-symbol-file
> lustre/ptlrpc/ptlrpc.o 0xffffffffa07be000 add-symbol-file
> lustre/obdclass/obdclass.o 0xffffffffa057f000 add-symbol-file
> lnet/lnet/lnet.o 0xffffffffa0516000 add-symbol-file
> libcfs/libcfs/libcfs.o 0xffffffffa047c000
>
>
>
> ]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]
> ]]]]]]]]]]
>
> ====================================================
> Trying to Mount OST on the Client
> =====================================================
>
> [root at Client ~]# mount -t lustre 10.177.33.10 at tcp:/client1<mailto:10.177.33.10 at tcp:/client1> /mnt/lustre
> mount.lustre: mount 10.177.33.10 at tcp:/client1<mailto:10.177.33.10 at tcp:/client1> at /mnt/lustre failed:
> Invalid argument This may have multiple causes.
> Is 'client1' the correct filesystem name?
> Are the mount options correct?
> Check the syslog for more info.
>
> [root at client ~]# lctl ping 10.177.33.10 at tcp<mailto:10.177.33.10 at tcp> 12345-0 at lo
> 12345-10.177.33.10 at tcp<mailto:12345-10.177.33.10 at tcp> [root at client ~]# lctl ping 10.177.33.22 at tcp<mailto:10.177.33.22 at tcp>
> 12345-0 at lo 12345-10.177.33.22 at tcp<mailto:12345-10.177.33.22 at tcp>
>
>
> [root at client ~]# lctl
> lctl > lustre_build_version
> Lustre version: 2.6.0-RC2--PRISTINE-2.6.32-431.20.3.el6.x86_64
> lctl version: 2.6.0-RC2--PRISTINE-2.6.32-431.20.3.el6.x86_64
> lctl > modules
> add-symbol-file lustre/osc/osc.o 0xffffffffa1212000
> add-symbol-file lustre/mgc/mgc.o 0xffffffffa11f4000
> add-symbol-file lustre/llite/lustre.o 0xffffffffa10da000
> add-symbol-file lustre/lov/lov.o 0xffffffffa105e000
> add-symbol-file lustre/mdc/mdc.o 0xffffffffa101d000
> add-symbol-file lustre/fid/fid.o 0xffffffffa100f000
> add-symbol-file lustre/lmv/lmv.o 0xffffffffa0fc4000
> add-symbol-file lustre/fld/fld.o 0xffffffffa0fb3000
> add-symbol-file lustre/ptlrpc/ptlrpc.o 0xffffffffa0e0b000
> add-symbol-file lustre/obdclass/obdclass.o 0xffffffffa0bff000
> add-symbol-file lnet/klnds/socklnd/ksocklnd.o 0xffffffffa08f8000
> add-symbol-file lnet/lnet/lnet.o 0xffffffffa04db000
> add-symbol-file libcfs/libcfs/libcfs.o 0xffffffffa0441000
>
> This e-mail, including attachments, may include confidential and/or
> proprietary information, and may be used only by the person or entity
> to which it is addressed. If the reader of this e-mail is not the intended
> recipient or his or her authorized agent, the reader is hereby notified
> that any dissemination, distribution or copying of this e-mail is
> prohibited. If you have received this e-mail in error, please notify the
> sender by replying to this message and delete this e-mail immediately.
>
>
> _______________________________________________
> Lustre-discuss mailing list
> Lustre-discuss at lists.lustre.org<mailto:Lustre-discuss at lists.lustre.org>
> http://lists.lustre.org/mailman/listinfo/lustre-discuss
>
>
>
>
> --
> Jongwoo Han
> Principal consultant
> jw.han at apexcns.com<mailto:jw.han at apexcns.com>
> Tel: +82- 2-3413-1704
> Mobile:+82-505-227-6108
> Fax: : +82- 2-544-7962
>
> This e-mail, including attachments, may include confidential and/or
> proprietary information, and may be used only by the person or entity
> to which it is addressed. If the reader of this e-mail is not the intended
> recipient or his or her authorized agent, the reader is hereby notified
> that any dissemination, distribution or copying of this e-mail is
> prohibited. If you have received this e-mail in error, please notify the
> sender by replying to this message and delete this e-mail immediately.
>
> _______________________________________________
> Lustre-discuss mailing list
> Lustre-discuss at lists.lustre.org<mailto:Lustre-discuss at lists.lustre.org>
> http://lists.lustre.org/mailman/listinfo/lustre-discuss
>
>
> This e-mail, including attachments, may include confidential and/or
> proprietary information, and may be used only by the person or entity
> to which it is addressed. If the reader of this e-mail is not the intended
> recipient or his or her authorized agent, the reader is hereby notified
> that any dissemination, distribution or copying of this e-mail is
> prohibited. If you have received this e-mail in error, please notify the
> sender by replying to this message and delete this e-mail immediately.
>
> _______________________________________________
> Lustre-discuss mailing list
> Lustre-discuss at lists.lustre.org<mailto:Lustre-discuss at lists.lustre.org>
> http://lists.lustre.org/mailman/listinfo/lustre-discuss
This e-mail, including attachments, may include confidential and/or
proprietary information, and may be used only by the person or entity
to which it is addressed. If the reader of this e-mail is not the intended
recipient or his or her authorized agent, the reader is hereby notified
that any dissemination, distribution or copying of this e-mail is
prohibited. If you have received this e-mail in error, please notify the
sender by replying to this message and delete this e-mail immediately.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20150108/54f4c48f/attachment.htm>
More information about the lustre-discuss
mailing list