News for hackers. Stuff that matters.
Re:JEP 295: Ahead-of-Time Compilation by brianwawok on Thursday October 27, 2016 @03:28PM (#12808854)
This is clearly still great for a few places. For example in the trading industry, you would have a few seconds of being very slow when starting up for the week - or anytime you crashed and needed to reboot midweek.

Also risk of "hot pathing" the wrong paths if the server comes up during say a market closed time...

Re:JEP 295: Ahead-of-Time Compilation by OldSchoolJohnny on Thursday October 27, 2016 @04:51PM (#12809961)
I'm surprised to hear anyone running Java in the trading industry. Isn't speed a huge factor in that industry?
Re:JEP 295: Ahead-of-Time Compilation by eternalban on Thursday October 27, 2016 @05:15PM (#12810245)
> Isn't speed a huge factor in that industry?

Exactly. There are a lot of high performance system written in Java. For long running systems, the startup cost is irrelevant. And for networked systems (such as fintech) you are going to be IO bound. The main issue as far as Java and high performance is the GC related pauses and that is a concern shared with any GC'd runtime.

Re:JEP 295: Ahead-of-Time Compilation by PeCaN on Thursday October 27, 2016 @10:11PM (#12812460)
And for Java it's actually much less of an issue thanks to the crazy manhours put into developing fast GC for Java. I suspect Azul Systems's pauseless GC is probably quite popular in HFT.
Re:JEP 295: Ahead-of-Time Compilation by brianwawok on Friday October 28, 2016 @12:20PM (#12817642)
They are trying to sell it for sure. They attend a lot of events.

I am not aware of any trading company using it. May be some.. but the high perf people I know go other ways.

Re:JEP 295: Ahead-of-Time Compilation by lygaret on Thursday October 27, 2016 @05:12PM (#12810206)
The JVM is super speedy, if you can mitigate startup time and the time required to warm up the JIT.
Re:JEP 295: Ahead-of-Time Compilation by lomnakkus on Thursday October 27, 2016 @05:16PM (#12810256)
... and Distruptor/Aeron. (etc.)
Re:JEP 295: Ahead-of-Time Compilation by kitd on Friday October 28, 2016 @04:05AM (#12813912)
You're assuming Java is slow. Evidence suggests otherwise. Eg. LMAX Exchange uses a lock-free ringbuffer they call Disruptor [1] which enables 6M tps on a single thread [2]

[1] https://lmax-exchange.github.io/disruptor/ [2] http://martinfowler.com/articles/lmax.html

Re:JEP 295: Ahead-of-Time Compilation by brianwawok on Friday October 28, 2016 @12:23PM (#12817678)
And disruptor is a few years old now, there is a whole new wave of queues with even better performance.
Re:JEP 295: Ahead-of-Time Compilation by taneq on Thursday October 27, 2016 @08:10PM (#12811670)
I seem to recall a prior discussion where a dev working on HFT stuff said that speed is a huge factor, but so is the ability to rapidly change functionality. They settled on Java because it was fast enough (HFT would have to be IO bound, right?) while still being flexible enough to allow them to adapt to daily changes in requirements.
Re:JEP 295: Ahead-of-Time Compilation by pjmlp on Friday October 28, 2016 @01:51AM (#12813431)
Besides what the others already replied, the use in the trade industry is one of the reasons of Java having to adopt AOT, value types, JNI replacement and better integration with GPGPUs.
Re:JEP 295: Ahead-of-Time Compilation by chrisseaton on Thursday October 27, 2016 @07:14PM (#12811303)
Re:JEP 295: Ahead-of-Time Compilation by maaaats on Thursday October 27, 2016 @05:12PM (#12810212)
Thus the Java.
Re:JEP 295: Ahead-of-Time Compilation by nurettin on Friday October 28, 2016 @06:14AM (#12814505)
Java shot itself in the foot with the whole GC thing. Then it built a gigantic robot exoskeleton called Hotspot to help itself walk fast again.
Re:JEP 295: Ahead-of-Time Compilation by lucian1900 on Friday October 28, 2016 @06:58AM (#12814682)
Java's GC isn't why it can be slower than C/C++ and the JIT (HotSpot) has nothing to do with the GC.
Re:JEP 295: Ahead-of-Time Compilation by nurettin on Saturday October 29, 2016 @02:04AM (#12822822)
Well you just told that to someone who lived with GC pauses and profilers for years. And I did not say hotspot is about GC.
Re:JEP 295: Ahead-of-Time Compilation by WatchDog on Thursday October 27, 2016 @05:23PM (#12810334)
A lot of firms will run some training data through their application after startup, so that the hot paths get optimised.
Re:JEP 295: Ahead-of-Time Compilation by kasey_junk on Thursday October 27, 2016 @06:30PM (#12810914)
I have done this so can confirm, but every time I did I wished I didn't need to. I had a running nightmare where yesterday's trading data made us trade today.
Re:JEP 295: Ahead-of-Time Compilation by greglindahl on Thursday October 27, 2016 @10:17PM (#12812492)
Or today's trading is different enough from yesterday's that your app hits perf issues. Black swan, anyone?
Re:JEP 295: Ahead-of-Time Compilation by brianwawok on Friday October 28, 2016 @02:22PM (#12819142)
Might not even be that. At some point you need to cut out the output from going to the real exchange.

If you had an IF somewhere random in your code.. you will then JIT code that is wrongly optimized.

If you try to put some kind of network device to capture the traffic and respond with fake responses to make the code happy.. you are one bitflip away from sending bad stuff to prod.

Re:JEP 295: Ahead-of-Time Compilation by kasey_junk on Friday October 28, 2016 @02:27PM (#12819201)
> you are one bitflip away from sending bad stuff to prod.

Including some ascii art of Trogdor the Burnanator!

Re:JEP 295: Ahead-of-Time Compilation by brianwawok on Friday October 28, 2016 @03:41PM (#12819911)
Ya that is tricky with binary formats. What exchanges still support ASCII? I want to send messages that are both ASCII art and a valid trade...
Re:JEP 295: Ahead-of-Time Compilation by brianwawok on Friday October 28, 2016 @12:21PM (#12817656)
Except at the exchange, where you can't do this. Or you accidentally bitflip something and take yesterdays data, inject into todays books, and cause millions of dollars in mistakes.