[lustre-discuss] [EXTERNAL] Converting MGS to ZFS - HA Config Question
Mohr, Rick
mohrrf at ornl.gov
Fri May 28 13:46:47 PDT 2021
Sid,
The --failnode option is the sort of the "old way" of configuring failover. It is assumed that the target will always be mounted for the first time on the primary server, and so the --failnode option only needs to list the secondary server NID (because the primary server NID is implied by whatever host mounts the target first).
The --servicenode option is the preferred way of configuring failover now. It does not make any assumptions about primary/secondary nodes, but as a result, you need to specify the NIDs of all nodes that could possibly mount the target. The easiest way to do this is to specify the "--servicenode <nid>" option multiple times (once for each node).
And as you have seen, the two options are not compatible with each other.
-Rick
On 5/27/21, 11:53 PM, "lustre-discuss on behalf of Sid Young via lustre-discuss" <lustre-discuss-bounces at lists.lustre.org on behalf of lustre-discuss at lists.lustre.org> wrote:
Hi,
I am in the process of converting my pre-production cluster to use ZFS, and I have a question regarding HA config parameters. The storage node has 24 disks, I've sliced off two disks in HBA mode to act as a 960G mirror. the command is:
# mkfs.lustre --reformat --mgs --failnode 10.140.93.41 at o2ib --backfstype=zfs mgspool/mgt mirror d3710M0 d3710M1
This runs successfully and I get the output below, however I want to make sure the second MDS node can be failed over too using Pacemaker, so if the server I am on now is 10.140.93.42 and the other MDS is 10.140.93.41, do I need to specify the host its on now (.42) anywhere in the config? I tried the servicenode parameter but it refuses to have servicenode and failnode in the command:
Permanent disk data:
Target: MGS
Index: unassigned
Lustre FS:
Mount type: zfs
Flags: 0x64
(MGS first_time update )
Persistent mount opts:
Parameters: failover.node=10.140.93.41 at o2ib
mkfs_cmd = zpool create -f -O canmount=off mgspool mirror d3710M0 d3710M1
mkfs_cmd = zfs create -o canmount=off mgspool/mgt
xattr=sa
dnodesize=auto
Writing mgspool/mgt properties
lustre:failover.node=10.140.93.41 at o2ib
lustre:version=1
lustre:flags=100
lustre:index=65535
lustre:svname=MGS
[root at hpc-mds-02]#
]# zfs list
NAME USED AVAIL REFER MOUNTPOINT
mgspool 468K 860G 96K /mgspool
mgspool/mgt 96K 860G 96K /mgspool/mgt
[root at hpc-mds-02 by-id]# zpool status
pool: mgspool
state: ONLINE
scan: none requested
config:
NAME STATE READ WRITE CKSUM
mgspool ONLINE 0 0 0
mirror-0 ONLINE 0 0 0
d3710M0 ONLINE 0 0 0
d3710M1 ONLINE 0 0 0
errors: No known data errors
[root at hpc-mds-02#
Sid Young
More information about the lustre-discuss
mailing list