HPE Community read-only access December 15, 2018
This is a maintenance upgrade. You will be able to read articles and posts, but not post or reply.
Hours:
Dec 15, 4:00 am to 10:00 am UTC
Dec 14, 10:00 pm CST to Dec 15, 4:00 am CST
Dec 14, 8:00 pm PST to Dec 15, 2:00 am PST
Array Performance and Data Protection
cancel
Showing results for 
Search instead for 
Did you mean: 

Cache Churn - infosight charts

 
SOLVED
Go to solution
jayst136
Occasional Advisor

Cache Churn - infosight charts

I'm really trying to understand the Cache Churn charts.

i'm looking at a chart which has been split by volume. The volume with the highest cache churn has 50% cache churn for small IO during business hours. The same volume has 71% cache churn for large IO during business hours. How should i interpret those charts?

The resource utilization chart confuses me a little as well, it shows 5% cache usage, but 5% of what actually? 

4 REPLIES
chris24
Respected Contributor
Solution

Re: Cache Churn - infosight charts

Firstly the volume with high large and small IO means that it is your busiest volume and responsible for most of the blocks in cache - it's probably a catch all data-store used by a host of machines, consider splitting up up the machines into separate volumes to give you a clearer idea of which volumes (VM's) are hitting your cache the hardest.

Cache utilization basically refers to "The amount of cache required/The amount of cache installed" - if you are at 5% it means you are using 5% of the total cache - i.e. you have a long way to go to utilizing your full 100% cache and have to consider buying more.

jayst136
Occasional Advisor

Re: Cache Churn - infosight charts

thanks for the answer, makes it clear enough for me now!

jayst136
Occasional Advisor

Re: Cache Churn - infosight charts

Looking again at the resource utilization chart, it has updated itself with new data and now shows 105% cache usage.
How should i interpret >100% cache usage ?

jayst136
Occasional Advisor

Re: Cache Churn - infosight charts

ok the resources utilization chart now displays 72% for the cache, not at a new data point but at the same datapoint where 105% was displayed previously.

We'll see how it goes from here.