Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Java’s new garbage collector promises low pause times on multi-terabyte heaps

opsian.com

Post reply on HN
Print view View original

191–200 of 245 posts

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#191

Post by chrisseaton »

negativegate wrote: post #189
chrisseaton wrote: post #181

Earlier quoted context omitted.

> 4TB uses 42 bits of address space. Can't you compress that into less than 42 bits?

No, compression only works when you don't need to represent every possibility, or can use less bytes for some inputs and more bytes for others. https://en.wikipedia.org/wiki/Pigeonhole_principle#Uses_and_...

Why do you need to represent every possibility? You obviously aren't going to squeeze 2^42 objects into 2^42 bytes are you? They each take more than a byte. You don't need to address bytes individually.

There's more holes than pigeons here.

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#192

Post by lemming »

humbleMouse wrote: post #176
pgwhalen wrote: post #173

Earlier quoted context omitted.

That’s not much of an answer. If anything, it seems to me like Oracle is seeding more control to the community. I could be wrong though, I don’t follow this stuff as close as some.

Coming sometime this winter they will require a license to use java 9 and up. Below is a link for the downvoters and skeptics: https://www.aspera.com/en/blog/oracle-will-charge-for-java-s...

Here is the rebuttal which shows that this is patently false for all actual use cases: http://blog.joda.org/2018/08/java-is-still-available-at-zero...

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#193

Post by geodel »

pjmlp wrote: post #169
humbleMouse wrote: post #164

Earlier quoted context omitted.

Basically oracle is attempting a hostile takeover of java. I'm keeping everything I do openjdk8 to avoid potential legal action.

You know that the majority of OpenJDK developers are Oracle employees, right?

Exactly. Some people think large software as programing language, compilers, GC etc can write itself. Or a few thousand dollar donation will be enough to pay to top engineers to keep working on it.

Oracle/Google/MS or Apple will continue to exert control on direction of languages they developed and open sourced because they continue to pay for majority of development expense.

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#195

Post by didibus »

humbleMouse wrote: post #175
pjmlp wrote: post #169

Earlier quoted context omitted.

You know that the majority of OpenJDK developers are Oracle employees, right?

I didn't know that. However, doesn't change my stance. Why would I upgrade to java 9 or 10 when I am at the mercy of oracle's lawyers?

Why aren't you at the same mercy with Java 8?

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#196

Post by jblow »

earenndil wrote: post #39
nicktelford wrote: post #4

> GC’s SPECjbb 2015 throughput numbers are roughly comparable with the Parallel GC (which optimises for throughput) but with an average pause time of 1ms and a max of 4ms. This is in contrast to G1 and Parallel who had average pause times in excess of 200ms. Not bad! Looking forward to seeing how this performs with a diverse range of workloads as it matures.

I wonder if that would make java more suitable to game development since pauses need to be <8ms, ideally.

8ms? Where do you get that number from?

If your player has a 144Hz monitor then your pause time, rounded to the nearest millisecond, has to be 0ms.

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#197

Post by AboutTheWhisles »

Who are these people that are designing systems that have terabytes of heap under a single GC, but still want/expect/need low pause times.

I would think if there were processes that needed consistent latency you would isolate them.

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#198

Post by vilhelm_s »

jblow wrote: post #196
earenndil wrote: post #39

Earlier quoted context omitted.

I wonder if that would make java more suitable to game development since pauses need to be <8ms, ideally.

8ms? Where do you get that number from? If your player has a 144Hz monitor then your pause time, rounded to the nearest millisecond, has to be 0ms.

Where do you get your number from? 1/(144 Hz) is 7ms. 1/(60 Hz) is 17ms.

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#199

Post by phakding »

eikenberry wrote: post #83
phakding wrote: post #58

Earlier quoted context omitted.

I worked for a company where we had a 100-150 microseconds order latency. We had to tune jvm to extremes. But it is very doable to optimize Java gc for low gc pause times.

With those latency requirements why did you use Java?

You would be surprised to know majority of trading companies/exchanges use Java for trading platform. So does majority of companies in finance sector. I have been working in this secor for over 10 years and have interviewed for many of them.

Re: Java’s new garbage collector promises low pause times on multi-terabyte heaps

#200

Post by Inityx »

AboutTheWhisles wrote: post #197

Who are these people that are designing systems that have terabytes of heap under a single GC, but still want/expect/need low pause times. I would think if there were processes that needed consistent latency you would isolate them.

Probably really old teams that had their scope change over time, with decades of technical debt, whose large controlling entities are too slow-moving to afford any kind of large refactor or rewrite in a more suitable language.
Post reply on HN