There is no specific requirement in Lustre to create multiple MGS; one
MGS will often suffice for many file systems in a subnet.
You should have one MGT, it can be mounted on more than one MGS (but
only one at a time). You need something in place that prevents it being
mounted more than once. ZFS has that ability.
File:Metadata Server HA Cluster Simple lowres v1.png
Brian Andrus
On 11/1/2017 7:08 PM, Parag Khuraswar wrote:
I have two mds nodes. For HA purpose I mentioned –service node options
mkfs.lustre --servicenode=10.2.1.204@o2ib
--servicenode=10.2.1.205@o2ib --mgs /dev/mapper/mpathc
Do I have to mention mgt in command ?
How many mgt’s we can have on one mds or mgs servers ?
Regards,
Parag
*From:*lustre-discuss [mailto:[email protected]]
*On Behalf Of *Brian Andrus
*Sent:* Thursday, November , 2017 7:30 AM
*To:* [email protected]
*Subject:* Re: [lustre-discuss] mdt mounting error
I don't think you use the --servicenode option when formatting an
mgs-only disk, or the --fsname option. Neither of those apply for an
mgs-only with multiple filesystems.
My command for a zfs backed mgs was:
*/mkfs.lustre --mgs --backfstype=zfs MGT/mgt/*
Then I created 2 different sets of OSTs/MDTs with different fsnames,
but the same mgsnode.
Brian Andrus
On 11/1/2017 6:50 PM, Parag Khuraswar wrote:
Hi Raj,
But I have two file system. And I think one mgt can be used for
two filesystems. Correct me if I am wrong.
Regards,
Parag
*From:*Raj [mailto:[email protected]]
*Sent:* Wednesday, November , 2017 4:57 PM
*To:* Parag Khuraswar; Lustre discussion
*Subject:* Re: [lustre-discuss] mdt mounting error
The following can contribute to this issue:
- Missing FS name in mgt creation (it must be <=9 character
long): --fsname=
mkfs.lustre --servicenode=10.2.1.204@o2ib
<mailto:--servicenode=10.2.1.204@o2ib>
--servicenode=10.2.1.205@o2ib
<mailto:--servicenode=10.2.1.205@o2ib> *--fsname=home* --mgs
/dev/mapper/mpathc
- verify if /mdt directory exists
On Wed, Nov 1, 2017 at 6:16 AM Raj <[email protected]
<mailto:[email protected]>> wrote:
What options in mkfs.lustre did you use to format with lustre?
On Wed, Nov 1, 2017 at 6:14 AM Parag Khuraswar
<[email protected] <mailto:[email protected]>> wrote:
Hi Raj,
Yes, /dev/mapper/mpatha available.
I could format and mount using ext4.
Regards,
Parag
*From:*Raj [mailto:[email protected]
<mailto:[email protected]>]
*Sent:* Wednesday, November , 2017 4:39 PM
*To:* Parag Khuraswar; Lustre discussion
*Subject:* Re: [lustre-discuss] mdt mounting error
Parag,
Is the device /dev/mapper/mpatha available?
If not, the multipathd may not have started or the
multipath configuration may not be correct.
On Wed, Nov 1, 2017 at 5:18 AM Parag Khuraswar
<[email protected] <mailto:[email protected]>>
wrote:
Hi,
I am getting below error while mounting mdt. Mgt is
mounted.
Please suggest
[root@mds2 ~]# mount -t lustre /dev/mapper/mpatha /mdt
mount.lustre: mount /dev/mapper/mpatha at /mdt failed:
No such file or directory
Is the MGS specification correct?
Is the filesystem name correct?
If upgrading, is the copied client log valid? (see
upgrade docs)
Regards,
Parag
_______________________________________________
lustre-discuss mailing list
[email protected]
<mailto:[email protected]>
http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
_______________________________________________
lustre-discuss mailing list
[email protected]
<mailto:[email protected]>
http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
_______________________________________________
lustre-discuss mailing list
[email protected]
http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
