On Thu, May 20, 2010 at 02:11:23PM -0700, Jonathan Ellis wrote:
> No, CM is not exposed to nodetool yet. (You should really be putting
> metrics into a real monitoring system rather than relying on nodetool.
> Some example munin plugins are at
> http://github.com/jbellis/cassandra-munin-plugins,
Can you monitor cassandra-level metrics like the ones in
http://github.com/jbellis/cassandra-munin-plugins ?
the usual culprit is usually compaction but your compacted row size is
small. nothing else really comes to mind.
(you should check system keyspace too tho, HH rows can get large)
On Fri,
Thanks!
You should probably add it to http://wiki.apache.org/cassandra/ClientOptions.
On Fri, May 21, 2010 at 12:22 PM, Pedro Gomes
wrote:
> Hi all
> In the following weeks I have developed a plugin to the java persistence
> platform Datanucleus, similar to the one presented by Google for App En
On Fri, May 21, 2010 at 9:09 AM, Ian Soboroff wrote:
> HINTED-HANDOFF-POOL 1 158 23
this is your smoking gun. HH tasks suck a ton of CPU and you have 158
backed up.
i would just blow the HH files away from your data/system directory,
restart the node, and run rep
Because when we tested it, it was slower.
2010/5/21 Даниел Симеонов :
> Hi,
> I have a question about the thrift protocol used to connect to Cassandra,
> I saw in class CassandraDaemon that TServerSocket is being used,
> why TNonblockingServerSocket is not being used? Thank you very much!
> Bes
We can get Cassandra to run great for a few hours now. Writing to and
reading from cassandra work well and the read/write times are good etc. We
also changed our config to enable row caching (we're hoping to ditch our
memcache server layer entirely).
Unfortunately, running on an EC2 High Memory
curious how did things turn out?
On Tue, May 18, 2010 at 1:38 PM, Curt Bererton wrote:
> We only have a few CFs (6 or 7). I've increased the MemtableThroughputInMB
> and MemtableOperationsInMillions as per your suggestions. Do we really
> need a swap file though? I suppose it can't hurt, but wi
Hi all
In the following weeks I have developed a plugin to the java persistence
platform Datanucleus, similar to the one presented by Google for App Engine and
a Hbase already present in the platform . Datanucleus:
http://www.datanucleus.org/project/download.html
For now it allows the persist
Ok, spending some time slogging through the cassandra-user archives. Seems
lots of folks have this problem. Starting with a JVM upgrade, then skimming
through JIRA looking for patches.
Ian
On Fri, May 21, 2010 at 12:09 PM, Ian Soboroff wrote:
> So at the moment, I'm not running my loader, and
Hello all,
We're running cassandra on EC2 (via Rightscale), and I'm working on
connecting up the cassandra JMX monitoring to try to debug why our 0.6.1
Cassandra machine spike to 100% CPU and then choke after about 6 hours worth
of production data running through them.
We're running on 64 bit EC2
On Mon, May 17, 2010 at 10:39 PM, Ma Xiao wrote:
Hi all,
Recently we have a 5 nodes running cassandra, 4 X 1.5TB drives for each,
...then I put 4 paths with DataFileDirectory,
my question is what's going to happen when one of the disk fail, especialy
the one has os installed which also hold
Hi,
I have a question about the thrift protocol used to connect to Cassandra,
I saw in class CassandraDaemon that TServerSocket is being used,
why TNonblockingServerSocket is not being used? Thank you very much!
Best regards, Daniel.
So at the moment, I'm not running my loader, and I'm looking at one node
which is slow to respond to nodetool requests. At this point, it has a pile
of hinted-handoffs pending which don't seem to be draining out. The
system.log shows that it's GCing pretty much constantly.
Ian
$ /usr/local/src/
Thanks.
You resolved my Problem.
My error :
I didn't see transport.open, open a new socket for each call.
I did think it's reuse the same one.
2010/5/20 Jonathan Ellis
> "disseminating load info" is not related to your problem.
>
> certainly you should be using connection pooling rather th
Oh ok thanks guys. That all makes perfect sense. I mistakenly thought the
timestamp was needed as a discriminator for the delete.
On Fri, May 21, 2010 at 10:24 AM, Jonathan Ellis wrote:
> ts is when the delete is performed, not the ts of the column you're
> deleting.
>
> you need to provide a
Thanks, I'll try that next time.
On May 21, 2010 5:23 PM, "Jonathan Ellis" wrote:
There is no other way to make the cluster "forget" a node w/o
decommission / removetoken.
You could do everything up to "stop the entire cluster" and do a
rolling restart instead, kill the 2 nodes you want to rem
On the to-do list for today. Is there a tool to aggregate all the JMX
stats from all nodes? I mean, something a little more complete than nagios.
Ian
On Fri, May 21, 2010 at 10:23 AM, Jonathan Ellis wrote:
> you should check the jmx stages I posted about
>
> On Fri, May 21, 2010 at 7:05 AM, I
ts is when the delete is performed, not the ts of the column you're deleting.
you need to provide a ts for every operation so that if there are
multiple clients updating the same column at the same time, cassandra
can decide who "wins."
On Fri, May 21, 2010 at 6:55 AM, Mark Greene wrote:
> Is th
you should check the jmx stages I posted about
On Fri, May 21, 2010 at 7:05 AM, Ian Soboroff wrote:
> Just an update. I rolled the memtable size back to 128MB. I am still
> seeing that the daemon runs for a while with reasonable heap usage, but then
> the heap climbs up to the max (6GB in this
There is no other way to make the cluster "forget" a node w/o
decommission / removetoken.
You could do everything up to "stop the entire cluster" and do a
rolling restart instead, kill the 2 nodes you want to remove, and then
do removetoken, which would still do extra i/o but at least the slow
nod
http://wiki.apache.org/cassandra/ArchitectureInternals
2010/5/20 史英杰 :
> What inner mechanism does Cassandra adopt to get this kind of fault
> tolerance?
>
> 2010/5/20 Simon Smith
>>
>> On Thu, May 20, 2010 at 8:08 AM, 史英杰 wrote:
>> > Hi, All,
>> > I am now learning the mechanism Cassandra a
On Fri, May 21, 2010 at 8:55 AM, Mark Greene wrote:
> Is there a particular reason why timestamp is required to do a deletion?
Because a delete is just a write with a tombstone flag, and the write with
the highest timestamp wins.
> If i'm reading the api docs correctly, this would require a r
Just an update. I rolled the memtable size back to 128MB. I am still
seeing that the daemon runs for a while with reasonable heap usage, but then
the heap climbs up to the max (6GB in this case, should be plenty) and it
starts GCing, without much getting cleared. The client catches lots of
excep
Is there a particular reason why timestamp is required to do a deletion? If
i'm reading the api docs correctly, this would require a read of the column
first correct?
I know there is an issue filed to have a better way to delete via range
slices but I wanted to make sure this was the only way to
On Thu, May 20, 2010 at 22:16, Arya Goudarzi wrote:
>
> P.S. By the way, if someone grants me access, I'd like to contribute to the
> documentaions on Apache Cassandra.
>
I believe anybody can create a wiki account and make changes. Have at it!
Gary.
25 matches
Mail list logo
