Re: Testing row cache feature in trunk: write should put record in cache

2010-02-19 Thread Jonathan Ellis
The whole point of rowcache is to avoid the serialization overhead, though. If we just wanted the serialized form cached, we would let the os block cache handle that without adding an extra layer. (0.6 uses mmap'd i/o by default on 64bit JVMs so this is very efficient.) On Fri, Feb 19, 2010 at

Re: Cassandra News Page

2010-02-19 Thread Ian Holsman
Hi Sal. we'll be moving off the incubator site shortly. we'll address that when we go to cassandra.apache.org regards Ian On Feb 18, 2010, at 4:06 PM, Sal Fuentes wrote: This is just a thought, but I think some type of *latest news* page would be nice to have on the main site

Re: Testing row cache feature in trunk: write should put record in cache

2010-02-19 Thread Weijun Li
I see. How much is the overhead of java serialization? Does it slow down the system a lot? It seems to be a tradeoff between CPU usage and memory. As for mmap of 0.6, do you mmap the sstable data file even it is a lot larger than the available memory (e.g., the data file is over 100GB while you

Unbalanced read latency among nodes in a cluster

2010-02-19 Thread Weijun Li
I setup a two cassandra clusters with 2 nodes each. Both use random partitioner. It's strange that for each cluster, one node has much shortter read latency than the other one This is the info of one of the cluster: Node A: read count 77302, data file 41GB, read latency 58180, io saturation 100%

Re: Testing row cache feature in trunk: write should put record in cache

2010-02-19 Thread Jonathan Ellis
mmap is designed to handle that case, yes. it is already in 0.6 branch. On Fri, Feb 19, 2010 at 2:44 PM, Weijun Li weiju...@gmail.com wrote: I see. How much is the overhead of java serialization? Does it slow down the system a lot? It seems to be a tradeoff between CPU usage and memory. As

Re: Unbalanced read latency among nodes in a cluster

2010-02-19 Thread Jonathan Ellis
http://wiki.apache.org/cassandra/Operations On Fri, Feb 19, 2010 at 3:03 PM, Weijun Li weiju...@gmail.com wrote: I setup a two cassandra clusters with 2 nodes each. Both use random partitioner. It's strange that for each cluster, one node has much shortter read latency than the other one

Re: cassandra freezes

2010-02-19 Thread Jonathan Ellis
are you using the old deb package? because that had broken gc settings. On Fri, Feb 19, 2010 at 10:40 PM, Santal Li santal...@gmail.com wrote: I meet almost same thing as you. When I do some benchmarks write test, some times one Cassandra will freeze and other node will consider it was

PHP/TBinaryProtocolAccelerated I64 timestamp (microtime) issue

2010-02-19 Thread Michael Pearson
Hi, is anyone else using thrift/php TBinaryProtocolAccelerated (thrift_protocol.so) call? It doesn't look to be sending timestamps correctly (casting as signed int 32) no such issue with TBinaryProtocol. eg: generating 13 digit cassandra_Column-timestamp via microtime() insert() via

Re: cassandra freezes

2010-02-19 Thread Santal Li
the GC options as bellow: JVM_OPTS= \ -ea \ -Xms2G \ -Xmx8G \ -XX:SurvivorRatio=8 \ -XX:TargetSurvivorRatio=90 \ -XX:+AggressiveOpts \ -XX:+UseParNewGC \ -XX:+UseConcMarkSweepGC \ -XX:+CMSParallelRemarkEnabled \

Re: StackOverflowError on high load

2010-02-19 Thread Jonathan Ellis
https://issues.apache.org/jira/browse/CASSANDRA-804 should have fixed this in trunk / 0.6. or at least log more about what is going on so we can fix it better. :) On Thu, Feb 18, 2010 at 12:44 AM, Ran Tavory ran...@gmail.com wrote: I ran the process again and after a few hours the same node