IBM Elastic Storage System 3500 Service Manual page 28

Prerequisites
• All new or existing building blocks must be at the ESS 6.1.1.1 or higher. If the setup has any protocol
nodes, these nodes must also be upgraded to ESS 6.1.1.1 levels (underlying code IBM Spectrum Scale
5.1.1.1 must be verified by using the essinstalclcheck command.
• The system must be working correctly before the IBM Elastic Storage System 3500 storage MES
upgrade.
• The existing IBM Elastic Storage System 3500 must be a properly installed 12 NVMe system with 12
NVMe drives correctly located in slots 1 - 6 and 13 - 18.
• If the canister servers are allocated as quorum servers, understand the implications of losing a quorum
server on one canister server at a time during this operation. If you do not want to lose the quorum,
move the quorum to different servers during this procedure.
• It is suggested to wear an ESD wrist band when you work on the hardware, for example, inserting NVMe
drives.
MES upgrade overview
GPFS uses preferentially the new network shared disks (NSDs) to store data of a new file system. GPFS
has four new NSDs that are the same as the four original NSDs and the workload on each server is the
same as it was before. The new file system data goes to the four new NSDs, like before the resizing,
the original file system data goes to the four original NSDs. Consider the necessity of restriping and the
current demands on the system. New data that is added to the file system is correctly striped. Restriping
a large file system requires many insert operations and delete operations, which might affect the system
performance. Restripe a large file system, when the system demand is low.
Concurrent MES upgrade steps
1. Ensure that the technical delivery assessment (TDA) process is complete before you start the MES
upgrade. This step is necessary if you did not purchase MES and attend the TDA with sales.
2. Ensure that the system is at the minimum ESS 6.1.1.1 or higher for the storage MES.
3. If you lose out quorum on each canister server causes an issue with the customer configuration
during MES upgrade, move the quorum to other supported nodes in the system.
4. Ensure that the 12 new NVMe drive FRUs are of the same capacity as the original 12 NVMe drives.
5. Insert the 12 new NVMe drive FRUs into slots 7 - 12 and 19 - 24.
Do not move the original 12 NVMe drives to different slots.
6. Verify the new 24 NVMe disk topology on both canisters by issuing the following command:
# mmvdisk server list --disk-topology --node-class <node class name>
Example
The following example is a case of a missing drive.
# date; mmvdisk server list --disk-topology --node-class ess3200_x86_64_mmvdisk_78E400K
Fri Aug 13 16:37:09 MST 2021
node
number server
------ --------------------------------
6 ess3200rw3a-hs.gpfs.ess
7 ess3200rw3b-hs.gpfs.ess
To identify what needs attention, use the following commands:
mmvdisk server list -N ess3200rw3a-hs.gpfs.ess --disk-topology -L
mmvdisk server list -N ess3200rw3b-hs.gpfs.ess --disk-topology -L
Example
18 IBM Elastic Storage System 3500: Service Guide
needs matching
attention metric disk topology
--------- -------- -------------
yes 95/100 ESS 3200 FN1 24 NVMe
yes 95/100 ESS 3200 FN1 24 NVMe