Off Heap concurrent counter

Concurrent counter are part of almost every system, it is used to collect data, thread synchronization etc. 

Java has good support of heap based counter.

There could be use case when you need counter that can be shared between processor.

How to build inter process counters 

 - Database 

This is first option that comes to mind, database sequence is counter that can be used by multiple process. All concurrency is handled by database. It is good option for starter but we know types of overhead(Network,Locks etc) you get with database. Only Larry Elision will be happy about it, not you!

 - Some Server

You could develop some server/middleware that provides such type of service. This option will still have network latency,marshal/unmarshal overhead.

 - Memory Mapped file

You could use memory mapped file to do this. I got idea from looking at thread-safe-interprocess-shared-memory-in-java presentation from PeterLawrey.

Challenges involved in multi process counter.

- Data visibility 

    Changes done by one process should be visible to all the process. This problem can be solved by using memory mapped file. Operating System gives guarantee about it and java memory model supports it to make is possible. 

- Thread safety 

Counters is all about multiple writers , so thread safety becomes big problem. Compare-and-swap is one option to handles multiple writers.

Is it possible to use CAS for off heap operation ? yes it is possible to do that , welcome to Unsafe.

By using using Memorymapped & Unsafe it is possible to use CAS for Off heap operation.

In this blog i will share my experiment of Memory mapped using CAS.

How ?

- How to get memory address
MappedByteBuffer is using DirectByteBuffer, which is off heap memory. So it is possible to get virtual address of memory and use unsafe to perform CAS operation. Lets look at the code.

Above code create memory mapped file of 8 bytes and get the virtual address. This address can be be used to read/write content of memory mapped file.

- How to Write/read in thread safe manner

Important function to look are readVolatile and increment
readVolatile reads directly from memory and increment is using unsafe to perform CAS on the address obtained from MemoryByteBuffer.

-Performance
Some performance numbers from my system. Each thread increments counter 1 Million times.

Performance of counter is decent , as number of threads are increased CAS failures starts to happen and performance starts to degrade.
Performance of these counter can be improved by having multiple segment to reduce write contention.
I will write about it in next blog.

Conclusion
 - Memory mapped file is very powerful, it can be used to developed lot of things like off heap collections, IPC, Off heap thread coordination etc.
  - Memory mapped file opens gates for GC less programming.

All the code used in this blog is available on github.

ArrayList Using Memory Mapped File

Introduction
In-Memory computing is picking up due to affordable hardware, most of the data is kept in RAM to meet latency and throughput goal, but keeping data in RAM create Garbage Collector overhead especially if you don't pre allocate.
So effectively we need garbage less/free approach to avoid GC hiccups

Garbage free/less data structure
There are couple of option to achieve it
 - Object Pool 
Object pool pattern is very good solution, i wrote about that in Lock Less Object Pool blog

- Off Heap Objects
JVM has very good support for creating off-heap objects. You can get rid of GC pause if you take this highway and highway has its own risk!

-MemoryMapped File
This is mix of Heap & Off Heap, like best of world.

Memory mapped file will allow to map part of the data in memory and that memory will be managed by OS, so it will create very less memory overhead in JVM process that is mapping file.
This can help in managing data in garbage free way and you can have JVM managing large data.
Memory Mapped file can be used to develop IPC, i wrote about that in power-of-java-memorymapped-file blog

In this blog i will create ArrayList that is backed up by MemoryMapped File, this array list can store millions of object and with almost no GC overhead. It sounds crazy but it is possible.

Lets gets in action
In this test i use Instrument object that has below attribute
 - int id
 - double price

So each object is of 12 byte.
This new Array List holds 10 Million Object and i will try to measure writer/read performance

Writer Performance

X Axis - No Of Reading
Y Axis - Time taken to add 10 Million in Ms









Adding 10 Million element is taking around 70 Ms, it is pretty fast.

Writer Throughput

Lets look at another aspect of performance which is throughput

X Axis - No Of Reading
Y Axis - Throughput /Second , in Millions









Writer throughput is very impressive, i ranges between 138 Million to 142 Million

Reader Performance

X Axis - No Of Reading
Y Axis - Time taken to read 10 Million in Ms









It is taking around 44 Ms to read 10 Million entry, very fast. With such type of performance you definitely challenge database.

 Reader Throughput

X Axis - No Of Reading
Y Axis - Throughput /Second , in Millions









Wow Throughput is great it is 220+ million per second

It looks very promising with 138 Million/Sec writer throughput & 220 Million/Sec reader throughput.

Comparison With Array List
Lets compare performance of BigArrayList with ArrayList,

Writer Throughput - BigArrayList Vs ArrayList

 Throughput of BigArrayList is almost constant at around 138 Million/Sec, ArrayList starts with 50 Million and drops under 5 million.

ArrayList has lot of hiccups and it is due to 
 - Array Allocation
 - Array Copy
 - Garbage Collection overhead

BigArrayList is winner in this case, it is 7X times faster than arraylist.

Reader Throughput - BigArrayList Vs ArrayList

ArrayList performs better than BigArrayList, it is around 1X time faster.

BigArrayList is slower in this case because
 - It has to keep mapping file in memory as more data is requested
 - There is cost of un-marshaling

Reader Throughput for BigArrayList is 220+ Million/Sec, it is still very fast and only few application want to process message faster than that.
So for most of the use-case this should work.

Reader performance can be improved by using below techniques 
 - Read message in batch from mapped stream
 - Pre-fetch message by using Index, like what CPU does

By doing above changes we can improve performance by few million, but i think for most of the case current performance is pretty good

Conclusion
Memory mapped file is interesting area to do research, it can solve many performance problem.
Java is now being used for developing trading application and GC is one question that you have to answer from day one, you need to find a way to keep GC happy and MemoryMapped is one thing that GC will love it.

Code used for this blog is available @ GitHub , i ran test with 2gb memory.
Code does't handle some edge case , but good enough to prove the point that that MemoryMapped file can be winner in many case.