Terracotta Discussion Forums

Hi,

We would like to distribute a huge cache over several nodes (1 to 10)... But the first tests are not convincing (with a very limited cache & only 2 nodes):

it seems we can't execute more than 2000 gets/second (small test with 2 nodes, and a small cache)

==============

This cache is accessed every seconds by any nodes...

The cache will contain about 100M of entries.

Key: String (size avg 30 chars = 100 bytes)
Value: 24 bytes

Total key = 100*100M= 10 GB
Total Value = 24*100M = 2.4 GB

Expected Gets/Sec = 100000
Expected Puts/Sec = 1000

==============

Could you confirm it is not possible to reach these expectations... and therefore I will have to redesign our solution to reduce the transactions?

TIA.

Hi,
The expected throughput from the distributed cache is definitely possible. Can you please share your tc-config.xml, ehcache.xml , client/server JVM arguments and some hardware details of the test you are currently running.

Cheers
Ridhav

Hey we have similar problem and we need the similar throughput.

attachment has the configuration . Let us know if you have nay suggestion

Thanks in Advanced

@sahsha29
Changing the consistency to eventual in your ehcache.xml would help as a first step, In the latest builds, the updates are readily available across the nodes quickly even while using eventual consistency.

If you can share some more details about your use case, We can suggest few more things. You should try using Big Memory on your L2's (Use trial licence) with persistence in 'temp-swap' mode and you should see considerable increase in your throughput.

-Ridhav