MineCraft and off heap memory

Overview

MineCraft is a really good example of when off heap memory can really help.

The key requirement are
  • The bulk of the retained data is a simple data structure (in minecraft's case its lots of byte[])
  • The usage of off heap memory can be hidden in abstraction.

The test

I used the following test for starting minecraft server from a seed from scratch which is a particularly expensive operation for the server.
  • Preset the level-seed=114 in server.properties
  • Delete the world* directories
  • Start the server with these options to see what the GC is doing -Xloggc:gc.log
    -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps
    -XX:+PrintGCTimeStamps -XX:+PrintTenuringDistribution -Xmx6g
  • Connect with one client
  • Perform /worldgen village
  • Perform /save-all
  • Exit.

To analyse the logs I am using jClarity's Censum.

Standard MineCraft

There is two particularly expensive things it does
  • It caches block stage in many byte[]s
  • It attempts to cache int[] used for processing without limit.
A Censum report for the above test looks like this


The high pause times are partly due to having to manage the large objects.

Off heap MineCraft

Two changes were made to address this
  • Use off heap ByteBuffer for long term caching.  Unsafe would be more efficient but not as portable.
  • Put a cap on the number of int[] cached.
Note: the problem with the temporary int[] only became visible to me after moving the bulk of the data off heap. Addressing the biggest problem over reveals more quick fix problems.

A Censum report for the same test looks like this


There is still some premature promotion i.e. further improvements can be made but you can see that the application is spending.

Conclusion

Using off heap memory can help you tame you GC pause times, especially if the bulk of your data is in simple data structures which can be easily abstracted.  Doing so can also help reveal other simple optimisations you can do to improve the consistency of your performance.

Footnote

Many organisation treat performance as an enhancement and optional, however if you instil a culture where reasonable performance is a requirement, and failing to meet this requirement is a bug, performance issue are more likely to be fix. c.f. https://bugs.mojang.com/browse/MC-56447

The Source Used

The source used for the test is available here. https://github.com/peter-lawrey/MineOffHeap

The logs produced are available here. https://github.com/peter-lawrey/MineOffHeap/tree/master/logs

Comments

Post a Comment

Popular posts from this blog

Java is Very Fast, If You Don’t Create Many Objects

Image
  You still have to watch how many objects you create. This article looks at a benchmark passing events over TCP/IP at 4 billion events per minute using the net.openhft.chronicle.wire.channel package in Chronicle Wire and why we still avoid object allocations..  One of the key optimisations is creating almost no garbage. Allocation is a very cheap operation and collection of very short-lived objects is also very cheap. Does this really make a difference? What difference does one small object per event (44 bytes) make to the performance in a throughput test where GC pauses are amortised? While allocation is as efficient as possible, it doesn’t avoid the memory pressure on the L1/L2 caches of your CPUs and when many cores are busy, they are contending for memory in the shared L3 cache.  Results Benchmark on a Ryzen 5950X with Ubuntu 22.10. JVM Vendor, Version No objects Throughput, Average Latency* One object per event Throughput, Average Latency* Azul Zulu 1.8.0_322 60.6 ...
Read more

System wide unique nanosecond timestamps

A Unique Identifier can be very useful for tracing. Those ids are even more useful when they contain a high-resolution timestamp.  Not only do they record the time of an event, but if unique can help trace events as they pass through the system. Such unique timestamps however can be expensive depending on how they are implemented.   This post explores a lightweight means of producing a unique, monotonically increasing system-wide nano-second resolution timestamp available in our open-source library. Uses for Unique Identifiers Unique identifiers can be useful to associate with a piece of information so that information can be referred to later unambiguously. This could be an event, a request, an order id, or a customer id. They can naturally be used as a primary key in a database or key/value store to retrieve that information later. One of the challenges of generating these identifiers is avoiding creating duplicates while not having an increasing cost.  You could ...
Read more

What does Chronicle Software do?

Image
Overview Chronicle Software is about simplifying fast data.  It is a suite of libraries to make it easier to write, monitor and tune data processing systems where performance and scalability are concerned. But its free, how do you make money, through support? We offer premium support . However, we often hear from users for the first time about a year after they have it in production.  Most users find they can support the software themselves.  It is only after a year or so, they have questions or concerns about where to take the product next.  In many cases, it is to a problem we have already solved and they just need to upgrade their software or use a new module we have added. As we don't know who is using most of our software, we can't advise them on how best to use our software and what updates or enhancements they would benefit from. We need users to contact us and ask questions.  We have a free forum , and we respond to 50% of questions in 2 hours...
Read more