When using direct memory can be faster

Overview

Using direct memory is no guarantee of improving performance.  Given it adds complexity, it should be avoided unless you have a compelling reason to use it.

This excellent article by Sergio Oliveira Jr shows its not simply a matter of using direct memory to improve performance Which one is faster: Java heap or native memory?

Where direct memory and memory mapped files can help is when you have a large amounts of data and/or you have to perform some IO with that data.

Time series data.

Time series data tends to have both a large number of entries and involve IO to load and store the data.  This makes it a good candidate for memory mapped files and direct memory.

I have provided an example here;  main and tests where the same operations are performed on regular objects and on memory mapped files.  Note: I am not suggesting that the access to the Objects is slow but the overhead of using objects which is the issue. e.g. loading, creating, the size of the object headers, garbage collection and saving the objects.

The test loads time series data with the time and two columns, bid and ask prices (normalised as int values) This is used to calculate and save a simple mid price basis point movement.  The test performs one GC to include the overhead of managing the objects involved.

Storage   1 million10 million30 million100 million250 million
Objects  0.55s  4.4s  16.7s  86.7s  225s
MMap  0.056s  0.46s    1.3s    4.5s     11s

The full results

Not only is memory mapped data 10x faster for smaller data sets, it scales better for large data sizes because
  • Memory mapped data is available as soon as it is mapped into memory
  • It creates only a small number of objects, which has almost no heap foot print reducing GC times. 
  • It can be arranged in memory as you desire reducing the over head per row as it doesn't have an object per row.
  • It doesn't have to do anything extra to save the data.
 Using direct memory and memory mapped files is not as simple as using Java objects, but if you have big data requirements it can make a big difference.

Using direct memory and memory mapped files can also make a big difference for low latency requirements, something I have discussed in previous articles.

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