HPE Storage Users Group

While doing health checks I have noticed that the disks are experiencing high iops:-
PLease suggest how to resolve this issues?
PD disk:0 Disk is experiencing a high level of I/O per second: 230.2
PD disk:2 Disk is experiencing a high level of I/O per second: 214.6
PD disk:6 Disk is experiencing a high level of I/O per second: 184.0
PD disk:8 Disk is experiencing a high level of I/O per second: 247.2
PD disk:9 Disk is experiencing a high level of I/O per second: 166.2
PD disk:10 Disk is experiencing a high level of I/O per second: 227.8
PD disk:11 Disk is experiencing a high level of I/O per second: 220.6
PD disk:12 Disk is experiencing a high level of I/O per second: 228.8
PD disk:13 Disk is experiencing a high level of I/O per second: 161.2
PD disk:14 Disk is experiencing a high level of I/O per second: 200.2
PD disk:15 Disk is experiencing a high level of I/O per second: 176.0
PD disk:16 Disk is experiencing a high level of I/O per second: 206.8
PD disk:17 Disk is experiencing a high level of I/O per second: 182.6
PD disk:18 Disk is experiencing a high level of I/O per second: 183.6
PD disk:20 Disk is experiencing a high level of I/O per second: 198.8
PD disk:21 Disk is experiencing a high level of I/O per second: 169.0
PD disk:22 Disk is experiencing a high level of I/O per second: 221.4
PD disk:23 Disk is experiencing a high level of I/O per second: 166.4
PD disk:24 Disk is experiencing a high level of I/O per second: 196.4
PD disk:25 Disk is experiencing a high level of I/O per second: 190.4
PD disk:26 Disk is experiencing a high level of I/O per second: 209.8
PD disk:27 Disk is experiencing a high level of I/O per second: 176.6
PD disk:28 Disk is experiencing a high level of I/O per second: 211.4
PD disk:29 Disk is experiencing a high level of I/O per second: 176.8
PD disk:30 Disk is experiencing a high level of I/O per second: 252.4
PD disk:31 Disk is experiencing a high level of I/O per second: 179.6
PD disk:32 Disk is experiencing a high level of I/O per second: 193.4
PD disk:33 Disk is experiencing a high level of I/O per second: 173.8
PD disk:34 Disk is experiencing a high level of I/O per second: 209.8
PD disk:35 Disk is experiencing a high level of I/O per second: 156.6
PD disk:36 Disk is experiencing a high level of I/O per second: 243.2
PD disk:37 Disk is experiencing a high level of I/O per second: 158.2
PD disk:38 Disk is experiencing a high level of I/O per second: 229.6
PD disk:39 Disk is experiencing a high level of I/O per second: 189.4
PD disk:40 Disk is experiencing a high level of I/O per second: 248.8
PD disk:41 Disk is experiencing a high level of I/O per second: 207.4
PD disk:42 Disk is experiencing a high level of I/O per second: 177.4
PD disk:43 Disk is experiencing a high level of I/O per second: 185.0
PD disk:44 Disk is experiencing a high level of I/O per second: 190.2

Hi,

what Type of disk are you using?
It seems that these are 10k FC or 7k NL Drives and for both of them more than 150 IOPs are a lot.
I´d suggest adding more disks or SSDs for AO.

Regards

_________________
6x 7440
2x 20450
1x 8200

The error is self explanatory as far as the problem, but whether it's a genuine alert is down to whether you are happy with your performance.

I get this error every time I reindex a large database. But we do this after hours and there is no feeling that performance is unacceptable during the day. Ergo, our solution is to ignore the alert.

You may find your services can be tuned on a server, something can be disabled or similar. Otherwise, adding disks is your solution.

As Josh26 said, you need to see if this is acceptable. Out of interest is it happening all the time, or is it only select times? If it select times you can try and figure out which VV is hammering the 3par and see if it can be stopped? We had this before where a customer a disk benchmark program running continually once we figured out which VV were then able to identify the VM and stop the running benchmark program.

Try running your health checks at a time when the system is less busy, if you have one. It depends on why you are running the health checks.

I think is support was preparing to do a non-disruptive upgrade to your 3PAR and encountered that result, they was postpone the upgrade for a less utilized time.

All the above recommendations are good.

First - Identify where the workload is coming from. Identify which host/vv is generating all the traffic.

Check if your system has multiple tiers of CPGs, is Adaptive Optimization licensed and in use, is dynamic optimization licensed?

_________________
Richard Siemers
The views and opinions expressed are my own and do not necessarily reflect those of my employer.