Re: [infinispan-dev] Performance improvements, more...
Great ! Which version of JGroups did you use ? 3.0.2 or 3.0.3 ? On 1/19/12 10:25 AM, Sanne Grinovero wrote: Hello, I just got these figures using the Transactional test: Done 2,592,102,434 transactional operations in 62.18 minutes using 5.1.0-SNAPSHOT 2,576,372,975 reads and 15,729,459 writes Reads / second: 690,573 Writes/ second: 4,216 which are much better than what I had 24 hours ago with 23a031e (same test, same parameters) : Done 878,390,104 transactional operations in 23.06 minutes using 5.1.0-SNAPSHOT 873,278,200 reads and 5,111,904 writes Reads / second: 631,100 Writes/ second: 3,694 The main differences are our minor cleanups from yesterday and JBMAR-127 - but this wasn't released yet, I'm depending on a locally built snapshot. Cheers, Sanne ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev -- Bela Ban Lead JGroups (http://www.jgroups.org) JBoss / Red Hat ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev
Re: [infinispan-dev] Performance improvements, more...
On 19 January 2012 09:36, Bela Ban b...@redhat.com wrote: Great ! Which version of JGroups did you use ? 3.0.2 or 3.0.3 ? Right... sorry I forgot to revert experiments on JGroups! So both numbers where running JGroups version 8115f27, which is somewhere between the two: 8115f27 Made MessageDispatcher.members volatile, writes and reads are separated by memo barriers (JGRP-1414) cb6219d Changes to Rsp (https://issues.jboss.org/browse/JGRP-1412) 070b116 updated version to 3.0.3.Final 8f485fa (tag: JGroups_3_0_2_Final) changed version to 3.0.2.Final On 1/19/12 10:25 AM, Sanne Grinovero wrote: Hello, I just got these figures using the Transactional test: Done 2,592,102,434 transactional operations in 62.18 minutes using 5.1.0-SNAPSHOT 2,576,372,975 reads and 15,729,459 writes Reads / second: 690,573 Writes/ second: 4,216 which are much better than what I had 24 hours ago with 23a031e (same test, same parameters) : Done 878,390,104 transactional operations in 23.06 minutes using 5.1.0-SNAPSHOT 873,278,200 reads and 5,111,904 writes Reads / second: 631,100 Writes/ second: 3,694 The main differences are our minor cleanups from yesterday and JBMAR-127 - but this wasn't released yet, I'm depending on a locally built snapshot. Cheers, Sanne ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev -- Bela Ban Lead JGroups (http://www.jgroups.org) JBoss / Red Hat ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev
Re: [infinispan-dev] Performance improvements, more...
On 19 January 2012 09:59, Bela Ban b...@redhat.com wrote: It would be interesting to see the numbers with bbc128, which makes sending a bit faster. I'd expect to see more writes and less reads, compared to their relative numbers. Ok, done. This is the same Infinispan build, but using JGroups bbc128: Done 880,969,860 transactional operations in 24.71 minutes using 5.1.0-SNAPSHOT 875,033,689 reads and 5,936,171 writes Reads / second: 590,216 Writes/ second: 4,003 Looks like a bit slower - confirming the figures I had two days ago. Anyway my purpose with the comparison was just to proof the latest patches in Infinispan where going in the correct direction, so I'm intentionally not changing JGroups versions yet. BTW: I'm done with my implementation of Table, and the numbers look really impressive ! It is about the same as RingBuffer for smaller insertions (5 million), but for 50 million the number stays about the same (insertions and removals per second). For smaller numbers, Table is ca 4 times *faster* than NakReceiverWindow. I still want to add more tests for Table (copy and convert the ones for RingBuffer), and then switch NAKACK2 over from RingBuffer to Table. I'm very curious to see the perf numbers after that change ! Next comes passing up of entire bundles, this should also make a big difference ! Exiting times, cheers ! If you commit it on an experimental branch, I'll give it a preview run .. Cheers, Sanne On 1/19/12 10:50 AM, Sanne Grinovero wrote: On 19 January 2012 09:36, Bela Banb...@redhat.com wrote: Great ! Which version of JGroups did you use ? 3.0.2 or 3.0.3 ? Right... sorry I forgot to revert experiments on JGroups! So both numbers where running JGroups version 8115f27, which is somewhere between the two: 8115f27 Made MessageDispatcher.members volatile, writes and reads are separated by memo barriers (JGRP-1414) cb6219d Changes to Rsp (https://issues.jboss.org/browse/JGRP-1412) 070b116 updated version to 3.0.3.Final 8f485fa (tag: JGroups_3_0_2_Final) changed version to 3.0.2.Final On 1/19/12 10:25 AM, Sanne Grinovero wrote: Hello, I just got these figures using the Transactional test: Done 2,592,102,434 transactional operations in 62.18 minutes using 5.1.0-SNAPSHOT   2,576,372,975 reads and 15,729,459 writes   Reads / second: 690,573   Writes/ second: 4,216 which are much better than what I had 24 hours ago with 23a031e (same test, same parameters) : Done 878,390,104 transactional operations in 23.06 minutes using 5.1.0-SNAPSHOT   873,278,200 reads and 5,111,904 writes   Reads / second: 631,100   Writes/ second: 3,694 The main differences are our minor cleanups from yesterday and JBMAR-127 - but this wasn't released yet, I'm depending on a locally built snapshot. -- Bela Ban Lead JGroups (http://www.jgroups.org) JBoss / Red Hat ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev
Re: [infinispan-dev] Performance improvements, more...
On 1/19/12 11:45 AM, Sanne Grinovero wrote: On 19 January 2012 09:59, Bela Banb...@redhat.com wrote: It would be interesting to see the numbers with bbc128, which makes sending a bit faster. I'd expect to see more writes and less reads, compared to their relative numbers. Ok, done. This is the same Infinispan build, but using JGroups bbc128: Done 880,969,860 transactional operations in 24.71 minutes using 5.1.0-SNAPSHOT 875,033,689 reads and 5,936,171 writes Reads / second: 590,216 Writes/ second: 4,003 OK, thanks. Not as dramatic though as the change in 23a031e... Looks like a bit slower - confirming the figures I had two days ago. Anyway my purpose with the comparison was just to proof the latest patches in Infinispan where going in the correct direction, so I'm intentionally not changing JGroups versions yet. BTW: I'm done with my implementation of Table, and the numbers look really impressive ! It is about the same as RingBuffer for smaller insertions (5 million), but for 50 million the number stays about the same (insertions and removals per second). For smaller numbers, Table is ca 4 times *faster* than NakReceiverWindow. I still want to add more tests for Table (copy and convert the ones for RingBuffer), and then switch NAKACK2 over from RingBuffer to Table. I'm very curious to see the perf numbers after that change ! Next comes passing up of entire bundles, this should also make a big difference ! Exiting times, cheers ! If you commit it on an experimental branch, I'll give it a preview run .. The branch is JGRP-1396-2, the class is Table. There is a stress test called TableStressTest (you can compare it to NakReceiverWindowStressTest and RingBufferStressTest). -- Bela Ban Lead JGroups (http://www.jgroups.org) JBoss / Red Hat ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev
Re: [infinispan-dev] Performance improvements, more...
All looking very good, people. Bela, feel like putting Table into NAKACK and 3.0.3? ;) On 19 Jan 2012, at 16:29, Bela Ban wrote: On 1/19/12 11:45 AM, Sanne Grinovero wrote: On 19 January 2012 09:59, Bela Banb...@redhat.com wrote: It would be interesting to see the numbers with bbc128, which makes sending a bit faster. I'd expect to see more writes and less reads, compared to their relative numbers. Ok, done. This is the same Infinispan build, but using JGroups bbc128: Done 880,969,860 transactional operations in 24.71 minutes using 5.1.0-SNAPSHOT 875,033,689 reads and 5,936,171 writes Reads / second: 590,216 Writes/ second: 4,003 OK, thanks. Not as dramatic though as the change in 23a031e... Looks like a bit slower - confirming the figures I had two days ago. Anyway my purpose with the comparison was just to proof the latest patches in Infinispan where going in the correct direction, so I'm intentionally not changing JGroups versions yet. BTW: I'm done with my implementation of Table, and the numbers look really impressive ! It is about the same as RingBuffer for smaller insertions (5 million), but for 50 million the number stays about the same (insertions and removals per second). For smaller numbers, Table is ca 4 times *faster* than NakReceiverWindow. I still want to add more tests for Table (copy and convert the ones for RingBuffer), and then switch NAKACK2 over from RingBuffer to Table. I'm very curious to see the perf numbers after that change ! Next comes passing up of entire bundles, this should also make a big difference ! Exiting times, cheers ! If you commit it on an experimental branch, I'll give it a preview run .. The branch is JGRP-1396-2, the class is Table. There is a stress test called TableStressTest (you can compare it to NakReceiverWindowStressTest and RingBufferStressTest). -- Bela Ban Lead JGroups (http://www.jgroups.org) JBoss / Red Hat ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev -- Manik Surtani ma...@jboss.org twitter.com/maniksurtani Lead, Infinispan http://www.infinispan.org ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev
Re: [infinispan-dev] Performance improvements, more...
On 1/19/12 12:03 PM, Manik Surtani wrote: All looking very good, people. Bela, feel like putting Table into NAKACK and 3.0.3? ;) Definitely not in NAKACK, it will be in NAKACK2 in 3.1. Once this has been running in production for a year or so, we can rename it to NAKACK. Remember, NakReceiverWindow might not be the fastest class around, but it's very stable and *correct*, and has been around for 12+ years... :-) If my experiments with NAKACK2 in 3.1 prove successful and I'm done sooner than expected, then, yes, I can backport it to 3.0.3 (or 3.0.4). I'd prefer to have Sanne run a test with the experimental 3.1 first though, so we can see if this makes a difference at all... On 19 Jan 2012, at 16:29, Bela Ban wrote: On 1/19/12 11:45 AM, Sanne Grinovero wrote: On 19 January 2012 09:59, Bela Banb...@redhat.com wrote: It would be interesting to see the numbers with bbc128, which makes sending a bit faster. I'd expect to see more writes and less reads, compared to their relative numbers. Ok, done. This is the same Infinispan build, but using JGroups bbc128: Done 880,969,860 transactional operations in 24.71 minutes using 5.1.0-SNAPSHOT 875,033,689 reads and 5,936,171 writes Reads / second: 590,216 Writes/ second: 4,003 OK, thanks. Not as dramatic though as the change in 23a031e... Looks like a bit slower - confirming the figures I had two days ago. Anyway my purpose with the comparison was just to proof the latest patches in Infinispan where going in the correct direction, so I'm intentionally not changing JGroups versions yet. BTW: I'm done with my implementation of Table, and the numbers look really impressive ! It is about the same as RingBuffer for smaller insertions (5 million), but for 50 million the number stays about the same (insertions and removals per second). For smaller numbers, Table is ca 4 times *faster* than NakReceiverWindow. I still want to add more tests for Table (copy and convert the ones for RingBuffer), and then switch NAKACK2 over from RingBuffer to Table. I'm very curious to see the perf numbers after that change ! Next comes passing up of entire bundles, this should also make a big difference ! Exiting times, cheers ! If you commit it on an experimental branch, I'll give it a preview run .. The branch is JGRP-1396-2, the class is Table. There is a stress test called TableStressTest (you can compare it to NakReceiverWindowStressTest and RingBufferStressTest). -- Bela Ban Lead JGroups (http://www.jgroups.org) JBoss / Red Hat ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev -- Manik Surtani ma...@jboss.org twitter.com/maniksurtani Lead, Infinispan http://www.infinispan.org ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev -- Bela Ban Lead JGroups (http://www.jgroups.org) JBoss / Red Hat ___ infinispan-dev mailing list infinispan-dev@lists.jboss.org https://lists.jboss.org/mailman/listinfo/infinispan-dev
