tag:blogger.com,1999:blog-11683713.post540813462044138543..comments2024-01-12T21:16:50.520-08:00Comments on Spyced: Cassandra 0.5.0 releasedJonathan Ellishttp://www.blogger.com/profile/11003648392946638242noreply@blogger.comBlogger13125tag:blogger.com,1999:blog-11683713.post-6819271787328125522010-03-21T16:18:44.407-07:002010-03-21T16:18:44.407-07:00Yousef: thanks for the heads up, I've updated ...Yousef: thanks for the heads up, I've updated the post to the correct ones. (they changed when we graduated from the incubator.)Jonathan Ellishttps://www.blogger.com/profile/11003648392946638242noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-70239286969429855292010-03-21T16:08:05.971-07:002010-03-21T16:08:05.971-07:00The links to changelog / notes are 404sThe links to changelog / notes are 404sYousef Ourabihttp://yousefourabi.comnoreply@blogger.comtag:blogger.com,1999:blog-11683713.post-76769729993693242732010-03-16T11:49:57.176-07:002010-03-16T11:49:57.176-07:00Right. I should be using "time python stress...Right. I should be using "time python stress.py". Duh, of course. Sorry for being so dense.Michael Spiegelhttps://www.blogger.com/profile/02070462251438659587noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-5881117744810924782010-03-16T08:49:07.590-07:002010-03-16T08:49:07.590-07:00Yes, although the time in the lower right is not a...Yes, although the time in the lower right is not a high-resolution clock :)Jonathan Ellishttps://www.blogger.com/profile/11003648392946638242noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-38353632391017260312010-03-16T06:59:11.110-07:002010-03-16T06:59:11.110-07:00I apologize if this is trivial, I want to be sure ...I apologize if this is trivial, I want to be sure I'm interpreting the output from stress.py correctly. Default arguments to the script are OK (as long as I'm running python 2.6 to get multiprocessing). Run the script first with "-o insert" and then "-o read". The total throughput is the bottom entry in the leftmost column divided by the bottom entry in the bottom entry in the rightmost column. Is that correct? I happen to be using the 0.6.0-beta2 release.Michael Spiegelhttps://www.blogger.com/profile/02070462251438659587noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-47420458046680922782010-02-01T08:19:28.831-08:002010-02-01T08:19:28.831-08:00One commitlog disk, one data disk, both xfs.One commitlog disk, one data disk, both xfs.Jonathan Ellishttps://www.blogger.com/profile/11003648392946638242noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-35562214177889106882010-02-01T08:10:06.499-08:002010-02-01T08:10:06.499-08:00Hey Jonathan, what was your physical disk setup (m...Hey Jonathan, what was your physical disk setup (mounts, drives) for this bench?Unknownhttps://www.blogger.com/profile/02996372167263331045noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-79673051336064565442010-01-29T14:54:56.714-08:002010-01-29T14:54:56.714-08:00it's in contrib/py_stress (it actually uses mu...it's in contrib/py_stress (it actually uses multiple processes if multiprocessing is available, since the GIL sucks, but it will fall back to threads if it has to).Jonathan Ellishttps://www.blogger.com/profile/11003648392946638242noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-59793720605336748642010-01-29T14:52:10.679-08:002010-01-29T14:52:10.679-08:00I would be interested to see your thread writing c...I would be interested to see your thread writing code. I'd like to emulate multiple threads writing to cassandra.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-11683713.post-29853365872097204362010-01-26T05:27:22.694-08:002010-01-26T05:27:22.694-08:00Both graphs are with ConsistencyLevel.ONE but that...Both graphs are with ConsistencyLevel.ONE but that's not going to affect throughput much (just latency) since ConsistencyLevel doesn't reduce the number of writes you do (in a non-failure scenario), just how many you wait for before returning success to the client.Jonathan Ellishttps://www.blogger.com/profile/11003648392946638242noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-13834070850718355822010-01-26T05:23:43.821-08:002010-01-26T05:23:43.821-08:00Okay great! Thanks. So you are using replication f...Okay great! Thanks. So you are using replication factor of 3 and read/write quorum of 2?Flaviohttps://www.blogger.com/profile/18367419649122204899noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-81703983305493304872010-01-26T05:20:18.060-08:002010-01-26T05:20:18.060-08:00The first graph is a single node, benchmarked with...The first graph is a single node, benchmarked with 50 threads.<br /><br />The second graph is a 4 node cluster running with a replication factor of 3 (that is, each write is replicated to 3 nodes), so you'd expect throughput to be about 30% more than the single node case, minus some overhead for dealing with the network, and that's what happens.Jonathan Ellishttps://www.blogger.com/profile/11003648392946638242noreply@blogger.comtag:blogger.com,1999:blog-11683713.post-50960157505191506442010-01-26T00:27:37.928-08:002010-01-26T00:27:37.928-08:00Hey Jonathan.
I would be really interested to kno...Hey Jonathan. <br />I would be really interested to know what is the cluster size of the cluster you have been using for the benchmarks. It would give a better understanding of the throughput/sec. <br /><br />And how many threads have been used in the first graph and was the experiment really only executed on one single node?Flaviohttps://www.blogger.com/profile/18367419649122204899noreply@blogger.com