NUMA architecture and Java

Time to deploy your application, looking forward to procure hardware that suits best to the load requirements. Boxes with 40 cores or 80 cores are pretty common these days. General conception is more cores, more processing power, more throughput. But I have seen a little contrary results, showing a small cpu-intensive test run performs slower on 80 core box than smaller 40 core box.

These boxes with huge cores comes with Non-Uniform Memory Access (NUMA) Architecture. NUMA is an architecture which boosts the performance of memory access for local nodes. These new hardware boxes are divided into different zones called Nodes. These nodes have a certain number of cores alloted with a portion of memory alloted to them. So for the box with 1 TB RAM and 80 Cores, we have 4 nodes each having 20 cores and 256 GB of memory alloted.

You can check that using command, numactl --hardware

>numactl --hardware
available: 4 nodes (0-3)
node 0 size: 258508 MB
node 0 free: 186566 MB
node 1 size: 258560 MB
node 1 free: 237408 MB
node 2 size: 258560 MB
node 2 free: 234198 MB
node 3 size: 256540 MB
node 3 free: 237182 MB
node distances:
node   0   1   2   3 
  0:  10  20  20  20 
  1:  20  10  20  20 
  2:  20  20  10  20 
  3:  20  20  20  10

When JVM starts it starts thread which are scheduled on the cores in some random nodes. Each thread uses its local memory to be fastest as possible. Thread might be in WAITING state at some point and gets rescheduled on CPU. This time its not guaranteed that it will be on same node. Now this time, it has to access a remote memory location which adds latency. Remote memory access is slower, because the instructions has to traverse a interconnect link which introduces additional hops.

Linux command numactl provides a way to bind the process to certain nodes only. It locks a process to a specific node both for execution and memory allocation. If a JVM instance is locked to a single node then the inter node traffic is removed and all memory access will happen on the fast local memory.

numactl --cpunodebind=nodes, -c nodes 
Only execute process on the CPUs of nodes. 

Created a small test which tries to serialize a big object and calculates the transactions per sec and latency.

To execute a java process bound to one node execute

 
numactl --cpunodebind=0 java -Dthreads=10 -jar serializationTest.jar 

Ran this test on two different boxes.

Box A
4 CPU x 10 cores x 2 (hyperthreading) = Total of 80 cores
Nodes: 0,1,2,3

Box B
2 CPU x 10 cores x 2 (hyperthreading) = Total of 40 cores
Nodes: 0,1

CPU Speed : 2.4 Ghz for both.
Default settings are too use all nodes available on boxes.

BoxNUMA policyTPSLatency (Avg)Latency (Min)
ADefault2613718
BDefault387255
A–cpunodebind=0,1405233
B–cpunodebind=01,61353
A–cpunodebind=01,61953

So we can infer that the default settings on Box A with more Nodes is performing low on a ‘CPU-intesive’ test compared to default setting on 2-node Box B. But as we bind the process to only 2 nodes, it performs equally better. Probably, because it has lesser nodes to hop and probability of threads getting rescheduled on same is increased to 50%.

With --cpunodebind=0, it just outperforms all the cases.

NOTE: Above test was run with 10 threads on 10 core.

Test Jar: download
Test Sources: download

Reference: NUMA & Java from our JCG partner Himadri Singh at the Billions & Terabytes blog.

Related Whitepaper:

Functional Programming in Java: Harnessing the Power of Java 8 Lambda Expressions

Get ready to program in a whole new way!

Functional Programming in Java will help you quickly get on top of the new, essential Java 8 language features and the functional style that will change and improve your code. This short, targeted book will help you make the paradigm shift from the old imperative way to a less error-prone, more elegant, and concise coding style that’s also a breeze to parallelize. You’ll explore the syntax and semantics of lambda expressions, method and constructor references, and functional interfaces. You’ll design and write applications better using the new standards in Java 8 and the JDK.

Get it Now!  

Leave a Reply


six × = 24



Java Code Geeks and all content copyright © 2010-2014, Exelixis Media Ltd | Terms of Use
All trademarks and registered trademarks appearing on Java Code Geeks are the property of their respective owners.
Java is a trademark or registered trademark of Oracle Corporation in the United States and other countries.
Java Code Geeks is not connected to Oracle Corporation and is not sponsored by Oracle Corporation.

Sign up for our Newsletter

15,153 insiders are already enjoying weekly updates and complimentary whitepapers! Join them now to gain exclusive access to the latest news in the Java world, as well as insights about Android, Scala, Groovy and other related technologies.

As an extra bonus, by joining you will get our brand new e-books, published by Java Code Geeks and their JCG partners for your reading pleasure! Enter your info and stay on top of things,

  • Fresh trends
  • Cases and examples
  • Research and insights
  • Two complimentary e-books