Re: Cold boot performance problems

On Fri, Oct 08, 2010 at 05:31:28PM -0700, Dave Viner wrote: > Has anyone found solid step-by-step docs on how to raid0 the ephemeral disks > in ec2 for use by Cassandra? No, but here's a script I used to raid0 3 ephemerals in an xlarge instance. You can edit the top part for different configs for

Re: Cold boot performance problems

Has anyone found solid step-by-step docs on how to raid0 the ephemeral disks in ec2 for use by Cassandra? On Fri, Oct 8, 2010 at 12:11 PM, Jason Horman wrote: > We are currently using EBS with 4 volumes striped with LVM. Wow, we > didn't realize you could raid the ephemeral disks. I thought the

Re: ERROR saved_caches_directory missing

Never mind, I did not pay attention to the new config change. - Original Message - From: "Arya Goudarzi" To: user@cassandra.apache.org Sent: Friday, October 8, 2010 4:22:34 PM Subject: ERROR saved_caches_directory missing Upgraded code from trunk 10/7 to trunk 10/8 and nodes don't start:

Re: ERROR saved_caches_directory missing

create the saved_caches_directory? On Fri, Oct 8, 2010 at 6:22 PM, Arya Goudarzi wrote: > Upgraded code from trunk 10/7 to trunk 10/8 and nodes don't start: > > ERROR 16:19:41,335 Fatal error: saved_caches_directory missing > > Please advice. > > Best Regards, > -Arya > -- Jonathan Ellis Proj

ERROR saved_caches_directory missing

Upgraded code from trunk 10/7 to trunk 10/8 and nodes don't start: ERROR 16:19:41,335 Fatal error: saved_caches_directory missing Please advice. Best Regards, -Arya

Re: Retrieving dead node's token from system keyspace

You only need to removetoken if you want to re-replicate data to other nodes. If each node has a full copy of the data, and the other nodes have forgotten about the dead node anyway, there is no need. (If they have not forgotten about the dead node, then the token will be in the ring information.

Re: Problem Starting Cassandra

On 10/08/2010 03:10 PM, Alberto Velandia wrote: > Hi I'm having a problem starting cassandra after setting up a new server > > INFO 20:08:47,315 JNA not found. Native methods will be disabled. > INFO 20:08:47,688 DiskAccessMode 'auto' determined to be mmap, > indexAccessMode is mmap > ERROR 20:0

Problem Starting Cassandra

Hi I'm having a problem starting cassandra after setting up a new server INFO 20:08:47,315 JNA not found. Native methods will be disabled. INFO 20:08:47,688 DiskAccessMode 'auto' determined to be mmap, indexAccessMode is mmap ERROR 20:08:47,778 Exception encountered during startup. java.lang.NoC

Re: Cold boot performance problems

Creating more ColumnFamilies in more Keyspaces creates more memory overhead. I do not believe sharding your data is the way to go with cassandra. You mentioned that you read 200 to 300 keys per request, and it sounded like all this data was for a single user. If you can group all the user data

Re: Retrieving dead node's token from system keyspace

I had a cluster of three nodes with RF=3 that I was using. Then, my demand dropped off quite a bit and I was trying to bring the cluster down to just one node for some time while working on other things to lower my server costs. Dropping the first node off the cluster worked fine using nodetoo

Re: Retrieving dead node's token from system keyspace

I had a cluster of three nodes with RF=3 that I was using. Then, my demand dropped off quite a bit and I was trying to bring the cluster down to just one node for some time while working on other things to lower my server costs. Dropping the first node off the cluster worked fine using nodetoo

Re: Cold boot performance problems

We are currently using EBS with 4 volumes striped with LVM. Wow, we didn't realize you could raid the ephemeral disks. I thought the opinion for Cassandra though was that the ephemeral disks were dangerous. We have lost of a few machines over the past year, but replicas hopefully prevent real troub

Re: using jna.jar "Unknown mlockall error 0"

On 10/8/10 10:13 AM, Clint Byrum wrote: IIRC, mlockall doesn't work as a non root user on Linux. We had a discussion a while back about using the jvm's support for Huge Pages to get around that limitation a while back, but I don't recall where that went. Do you mean.. https://issues.apache.

Re: Cold boot performance problems

Two things that can help: In 0.6.5, enable the dynamic snitch with -Dcassandra.dynamic_snitch_enabled=true -Dcassandra.dynamic_snitch=cassandra.dynamic_snitch_enabled which if you are doing a rolling restart will let other nodes route around the slow node (at CL.ONE) until it's warmed up (by the

Cold boot performance problems

We are experiencing very slow performance on Amazon EC2 after a cold boot. 10-20 tps. After the cache is primed things are much better, but it would be nice if users who aren't in cache didn't experience such slow performance. Before dumping a bunch of config I just had some general questions.

Re: Creating and using indices

On Fri, Oct 8, 2010 at 9:27 AM, Christian Decker wrote: > On Thu, Oct 7, 2010 at 6:25 PM, Jonathan Ellis wrote: >> No, LT[E] is not on the roadmap for primary index clauses (GT[E] is, >> for 0.7.1).  So you would want to create an index with an inverted >> comparator, to turn LTE into GTE. > > Hm

Re: using jna.jar "Unknown mlockall error 0"

IIRC, mlockall doesn't work as a non root user on Linux. We had a discussion a while back about using the jvm's support for Huge Pages to get around that limitation a while back, but I don't recall where that went. On Oct 8, 2010, at 2:53 AM, Utku Can Topçu wrote: > Thanks Nicolas, > > I've ju

Logging to Cassandra wiki page

For those interested I've added a wiki page to provide information on logging directly to Cassandra. It has a few links right now but if anyone would like to help out in fleshing it out, it would be much appreciated :). Wiki page: http://wiki.apache.org/cassandra/LoggingToCassandra FAQ entry ab

Re: Creating and using indices

On Thu, Oct 7, 2010 at 6:25 PM, Jonathan Ellis wrote: > On Thu, Oct 7, 2010 at 10:13 AM, Christian Decker > wrote: > > So basically my indices should work? Is there a simple way to check that, > so > > that we can exclude that? > > > > Are LTE working (or on the roadmap for the 0.7.0 release)? >

Re: Dazed and confused with Cassandra on EC2 ...

On Fri, Oct 8, 2010 at 4:54 AM, Jedd Rashbrooke wrote: > On 8 October 2010 02:05, Matthew Dennis wrote: >> Also, in general, you probably want to set Xms = Xmx (regardless of the >> value you eventually decide on for that). > >  Matthew - we'd just about reached that conclusion!  Is it as big an

Re: Newbie Question about restarting Cassandra

On Fri, Oct 8, 2010 at 2:12 AM, Peter Schuller wrote: >> If your C* process dies and/or is killed you should not lose data.  It's >> written to the commit log before the client is acked, however that entry may >> not have made it to disk yet in the case of commitlogsync=periodic.  So, if >> you ki

Re: Creating and using indices

That's exactly what I missed, thanks Tyler, I'll try and create the ColumnDefinition from scratch and see if I can get this to work :-) On Thu, Oct 7, 2010 at 5:49 PM, Tyler Hobbs wrote: > Actually, you're trying to add an index to an already existing column > family here, right? > > That's not

Re: Dazed and confused with Cassandra on EC2 ...

On 7 October 2010 20:49, Peter Schuller wrote: > ... if you "waste" 10-15 gigs of RAM on the JVM heap for a > Cassandra instances which could live with e.g. 1 GB, you're actively > taking away those 10-15 gigs of RAM from the operating system to use > for the buffer cache. Particularly if you're I

Re: using jna.jar "Unknown mlockall error 0"

Thanks Nicolas, I've just tried it as running root and the warning did not show up. Do we need to run cassandra as root in order to use JNA? Regards, Utku On Fri, Oct 8, 2010 at 11:45 AM, Nicolas Mathieu wrote: > If I'm not wrong, when I run cassandra as root I don't get that mlockall > erro

Re: using jna.jar "Unknown mlockall error 0"

If I'm not wrong, when I run cassandra as root I don't get that mlockall error 0. Maybe there is another solution anyway. nico008 On 08/10/2010 11:33, Roger Schildmeijer wrote: On Fri, Oct 8, 2010 at 11:27 AM, Utku Can Topçu > wrote: Hi, In order to cont

Re: using jna.jar "Unknown mlockall error 0"

I'm running an Ubuntu 9.10 linux box. On Fri, Oct 8, 2010 at 11:33 AM, Roger Schildmeijer wrote: > > > On Fri, Oct 8, 2010 at 11:27 AM, Utku Can Topçu wrote: > >> Hi, >> >> In order to continue on memory optimizations, I've been trying to use the >> JNA. However, when I copy the jna.jar to the l

Re: using jna.jar "Unknown mlockall error 0"

On Fri, Oct 8, 2010 at 11:27 AM, Utku Can Topçu wrote: > Hi, > > In order to continue on memory optimizations, I've been trying to use the > JNA. However, when I copy the jna.jar to the lib directory? I get the > warning. I'm currently running the 0.6.5 version of cassandra. > > WARN [main] 2010-

using jna.jar "Unknown mlockall error 0"

Hi, In order to continue on memory optimizations, I've been trying to use the JNA. However, when I copy the jna.jar to the lib directory? I get the warning. I'm currently running the 0.6.5 version of cassandra. WARN [main] 2010-10-08 09:16:18,924 FBUtilities.java (line 595) Unknown mlockall error

Re: Newbie Question about restarting Cassandra

> If your C* process dies and/or is killed you should not lose data.  It's > written to the commit log before the client is acked, however that entry may > not have made it to disk yet in the case of commitlogsync=periodic.  So, if > you kill the C* process you're fine.  If you nicely restart the O