> BTW also, someone else previously commented on a different thread that maybe > some of my slow-downs were GC related, and at the time I didn't understand > the possible interactions between the GC and multithread timing issues... > which I'm still not sure I completely understand, but all of this has now > been cast in a new light.
Using the -XX:+PrintGC and -XX:+PrintGCDetails JVM options will tell you more about when and whether GC is happening, and what type of GC is happening. Whether or not a GC pause is parallel is relevant to whether or not the JVM will use all (or several depending on settings) available cores during said pause. There is also the concept of "concurrent" GC, which refers to the GC running concurrently (in one or more threads) with your application. Depending on your choice of GC you may have non-parallel/parallel GC during stop-the-world pauses, or parallel/non-parallel GC running concurrently with your application. The '-Xincgc' option will turn on the concurrent mark-sweep GC which makes operation on the old generation concurrent, and I believe the default will also be for parallel GC in the young generation (generations refer to classifications of data as young or new; the distinction exists because GC:s typically perform optimizations based on the fact that most applications generate a lot of short-lived data). If you are interested in how GC:s work I can recommend the following papers: "Uniprocessor garbage collection techniques", which is now fairly old but gives a pretty good (IMO) overview of GC algorithms of different types: ftp://ftp.cs.utexas.edu/pub/garbage/gcsurvey.ps Actually if anyone has good suggestions for similar papers I'm all ears. This was the first paper I ever read about GC and launched my interest in it; I still think it's good, but then I'm biased. "Garbage-First Garbage Collection" describes the upcoming GC which is already available but not yet the default, but intended to be the default replacement for CMS in JDK 1.7: http://research.sun.com/jtech/pubs/04-g1-paper-ismm.pdf That one in particular will cover several aspects that are relevant to concurrency as multi-processor scalability was a design goal. You may also be interested in what I believe to be the original paper about the CMS collector: http://research.sun.com/techrep/2000/smli_tr-2000-88.pdf Of course both CMS and G1 will have changed since the original publications of the papers, but they should offer good insight. -- / Peter Schuller -- You received this message because you are subscribed to the Google Groups "Clojure" group. To post to this group, send email to clojure@googlegroups.com Note that posts from new members are moderated - please be patient with your first post. To unsubscribe from this group, send email to clojure+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/clojure?hl=en To unsubscribe from this group, send email to clojure+unsubscribegooglegroups.com or reply to this email with the words "REMOVE ME" as the subject.
