Hi, Am Montag, 17. März 2014 14:42:39 UTC+1 schrieb Patrik Nordwall: > > > > > On Mon, Mar 17, 2014 at 1:45 PM, Carsten Saathoff > <[email protected]<javascript:> > > wrote: > >> Hi, >> >> Am Montag, 17. März 2014 09:06:28 UTC+1 schrieb Patrik Nordwall: >> >> On my MacBook Pro: 2,3 GHz Intel Core i7, SSD >>>>> 110201.58 persistent commands per second >>>>> 10204.87 persistent events per second >>>>> >>>> >>>> How have these numbers be obtained? If I can achieve those numbers with >>>> a lot of Porcessors in the system, I am more than happy ;) >>>> >>> >>> with the PerformanceSpec >>> Run with: >>> sbt -Dakka.persistence.performance.cycles.load=200000 >>> -Dakka.persistence.performance.cycles.warmup=10000 "project >>> akka-persistence-experimental" "test-only akka.persistence. >>> PerformanceSpec" >>> >> >> I ran those tests as well. >> Output is in the following gist: >> >> https://gist.github.com/kodemaniak/9598402 >> >> The eventsourcing and persistent channel test don't even terminate >> successfully. Only the command sourcing works partially, but the numbers >> are way worse than your numbers. I ran those tests on a desktop PC, 16 GB >> RAM (sbt gets 4GB), SATA Harddisks (RAID 1) and a Core i5 processor. >> >> I am doing a lot of data importing on this machine with HBase, and my >> feeling is that given the hardware a higher throughput should be possible. >> So I really start to wonder whether anything else is wrong on my machine. >> >> Do you have any comparative numbers fpr systems without a SSD? >> > > The only thing I have is from our build servers. > 48 core AMD Opteron 6172 2.1 GHz, spinning disk > -Dakka.persistence.performance.cycles.load=200000 -Dakka.persistence. > performance.cycles.warmup=10000 > 37709.13 persistent commands per second > 2209.10 persistent events per second > > Note that sbt forks the test and the heap is therefore default size (256MB > in your case). Not sure if that matters. >
OK, so that's also slower than your benchmarks from before. I don't think the heap is an issue here. But all tests I performed locally on my machine provide consistent results in the respect, that LevelDB on my machine stays around 3k commands/second. I am a bit surprised, but maybe that's the way it is. At least currently I don't have an idea what could be wrong. Thanks so far Carsten -- >>>>>>>>>> Read the docs: http://akka.io/docs/ >>>>>>>>>> Check the FAQ: >>>>>>>>>> http://doc.akka.io/docs/akka/current/additional/faq.html >>>>>>>>>> Search the archives: https://groups.google.com/group/akka-user --- You received this message because you are subscribed to the Google Groups "Akka User List" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at http://groups.google.com/group/akka-user. For more options, visit https://groups.google.com/d/optout.
