Re: Recommended OS

2014-02-12 Thread Jeffrey Kesselman
I haven't run Cassandra in production myself, but for other high load Java based servers I've had really good scaling success with OpenSolaris. In particular I've used Joyent's SmartOS which has the additional advantage of bursting to cover brief periods of exceptional load. On Tue, Feb 11,

Re: Possibly losing data with corrupted SSTables

2014-02-12 Thread Francisco Nogueira Calmon Sobral
Hi, Rahul. I've removed the corrupted sstables and 'nodetool repair' ran successfully for the column family. I'm not sure whether or not we've lost data. Best regards, Francisco Sobral On Jan 30, 2014, at 3:58 PM, Rahul Menon ra...@apigee.com wrote: Yes should delete all files related to

in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Brian Tarbox
We're running a C* cluster with 6 servers spread across the four us-east1 zones. We also spread our clients (hundreds of them) across the four zones. Currently we give our clients a connection string listing all six servers and let C* do its thing. This is all working just fine...and we're

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Andrey Ilinykh
yes, sure. Taking data from the same zone will reduce latency and save you some money. On Wed, Feb 12, 2014 at 10:13 AM, Brian Tarbox tar...@cabotresearch.comwrote: We're running a C* cluster with 6 servers spread across the four us-east1 zones. We also spread our clients (hundreds of them)

Re: Recommended OS

2014-02-12 Thread Robert Coli
On Wed, Feb 12, 2014 at 8:55 AM, Jeffrey Kesselman jef...@gmail.com wrote: I haven't run Cassandra in production myself, but for other high load Java based servers I've had really good scaling success with OpenSolaris. In particular I've used Joyent's SmartOS which has the additional

Re: Recommended OS

2014-02-12 Thread Jeffrey Kesselman
Its quite possible its well tricked out for Linux. My major issue with Linux has been that its TCP/IP stack is nowhere near as scalable as Solaris' for massive numbers of simultaneous connections. But thats probably less of an issue with a Cassandra node then it has been with the game servers

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Yogi Nerella
Also, may be you need to check the read consistency to local_quorum, otherwise the servers still try to read the data from all other data centers. I can understand the latency, but I cant understand how it would save money? The amount of data transferred from the AWS server to the client should

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Russell Bradberry
Cross zone data transfer does not cost any extra money.  LOCAL_QUORUM = QUORUM if all 6 servers are located in the same logical datacenter.   Ensure your clients are connecting to either the local IP or the AWS hostname that is a CNAME to the local ip from within AWS.  If you connect to the

RE: Worse perf after Row Caching version 1.2.5:

2014-02-12 Thread PARASHAR, BHASKARJYA JAY
Thanks Jonathan, I have the cfstats but our prod team has changed some configs after my post and I do not have the cfhistograms information now. No Of nodes: 3 Ram: 472GB Cassandra version: 1.2.5 I am pasting the cfstats below. Regards Jay CREATE TABLE EnablerCreditReasonInfo ( key text

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread William Oberman
Same region, cross zone transfer is $0.01 / GB (see http://aws.amazon.com/ec2/pricing/, Data Transfer section). On Wed, Feb 12, 2014 at 3:04 PM, Russell Bradberry rbradbe...@gmail.comwrote: Cross zone data transfer does not cost any extra money. LOCAL_QUORUM = QUORUM if all 6 servers are

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Russell Bradberry
Not when using private IP addresses.  That pricing ONLY applies if you are using the public interface or EIP/ENI.  If you use the private IP addresses there is no cost associated. On February 12, 2014 at 3:13:58 PM, William Oberman (ober...@civicscience.com) wrote: Same region, cross zone

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Andrey Ilinykh
I think you are mistaken. It is true for the same zone. between zones 0.01/G On Wed, Feb 12, 2014 at 12:17 PM, Russell Bradberry rbradbe...@gmail.comwrote: Not when using private IP addresses. That pricing *ONLY *applies if you are using the public interface or EIP/ENI. If you use the

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Ben Bromhead
0.01/G between zones irrespective of IP is correct. As for your original question, depending on the driver you are using you could write a custom co-ordinator node selection policy. For example if you are using the Datastax driver you would extend

Re: Recommended OS

2014-02-12 Thread Ben Bromhead
We are currently trialling SmartOS with Cassandra and have seen some pretty good results (and the mmap stuff appears to work). As Rob said, if this is production cluster, run with linux… there will be far less pain. If you are super keen on running on something different from linux in

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Brian Tarbox
We're definitely using all private IPs. I guess my question really is: with repl=3 and quorum operations I know we're going to push/pull bits across the various AZs within us-east-1. So, does having the client start the conversation with a server in the same AZ save us anything? On Wed, Feb

non-vnodes own 0.0% of the ring on nodetool status

2014-02-12 Thread Paulo Ricardo Motta Gomes
Hello, After adding a new datacenter with virtual nodes enabled, the output of nodetool status shows that nodes from the non-vnodes datacenter owns 0.0% of the data, as shown below: Datacenter: NonVnodesDC = Status=Up/Down |/ State=Normal/Leaving/Joining/Moving --

Re: non-vnodes own 0.0% of the ring on nodetool status

2014-02-12 Thread Russell Bradberry
This is normal as nodetool without specifying a keyspace outputs information for the ring as if it is SimpleStrategy with RF=1.  Try specifying a keyspace. On February 12, 2014 at 4:35:31 PM, Paulo Ricardo Motta Gomes (paulo.mo...@chaordicsystems.com) wrote: Hello, After adding a new

Re: in AWS is it worth trying to talk to a server in the same zone as your client?

2014-02-12 Thread Robert Coli
On Wed, Feb 12, 2014 at 1:14 PM, Ben Bromhead b...@instaclustr.com wrote: An alternate method would be to define the zones as data centres and then you could leverage existing DC aware policies (We've never tried this though). https://issues.apache.org/jira/browse/CASSANDRA-3810 =Rob

Re: Recommended OS

2014-02-12 Thread Robert Coli
On Wed, Feb 12, 2014 at 1:25 PM, Ben Bromhead b...@instaclustr.com wrote: If you are super keen on running on something different from linux in production (after all the warnings), run most of your cluster on linux, then run a single node or a separate DC with SmartOS, Solaris, BeOS, OS/2,

Thrift CAS usage

2014-02-12 Thread mahesh rajamani
Hi, I am using CAS feature through thrift cas api. I am able to set the expected column with some value and use cas through thrift api. But I am sure what I should set for expected column list to achieve IF NOT EXIST condition for a column. Can someone help me on this? -- Regards, Mahesh

Re: Recommended OS

2014-02-12 Thread Jonathan Haddad
I just would advise against it because it's going to be difficult to narrow down what's causing problems. For instance, if you have Node A which is performing GC, it will affect query times on Node B which is trying to satisfy a quorum read. Node B might actually have very low load, and it will

Re: Possibly losing data with corrupted SSTables

2014-02-12 Thread sankalp kohli
You might want to look at this JIRA i filed today CASSANDRA-6696 https://issues.apache.org/jira/browse/CASSANDRA-6696 You are good if you are fine with data reappearing. On Wed, Feb 12, 2014 at 9:20 AM, Francisco Nogueira Calmon Sobral fsob...@igcorp.com.br wrote: Hi, Rahul. I've removed

Is it possible to set a counter to zero using CQL?

2014-02-12 Thread Jacob Rhoden
Hi Guys, My question is probably best described by example. Is it possible to indicate that on a particular day, the total number of “events” were zero. // Three events today update mytable count=count+1 where day=“20140101” update mytable count=count+1 where day=“20140101” update mytable

Re: Is it possible to set a counter to zero using CQL?

2014-02-12 Thread Steven A Robenalt
Hi Jacob, I get the same effect using: update mytable set count = count + 0 where day = 20140103 The count field is changed from null to zero as a result. Steve On Wed, Feb 12, 2014 at 6:31 PM, Jacob Rhoden jacob.rho...@me.com wrote: Hi Guys, My question is probably best described by

Re: Intermittent long application pauses on nodes

2014-02-12 Thread Keith Wright
Frank did you ever file a ticket for this issue or find the root cause? I believe we are seeing the same issues when attempting to bootstrap. Thanks From: Robert Coli rc...@eventbrite.commailto:rc...@eventbrite.com Reply-To: user@cassandra.apache.orgmailto:user@cassandra.apache.org

How to transfer data from Oracle into Cassandra

2014-02-12 Thread Susheel Kumar
Hi, Can you please tell me how to transfer data from Oracle database into Cassandra. We have like 50*10=500 tables (normalized) and would like to transfer data from them to Cassandra to perform READ operations. Basically intent is that if we can reduce load from Oracle database and keep only

Re: Worse perf after Row Caching version 1.2.5:

2014-02-12 Thread Marcus Eriksson
select * from table will not populate row cache, but if the row is cached, it will be used. You need to use select * from table where X=Y to populate row cache. when setting caching = rows_only you disable key cache which might hurt your performance. On Wed, Feb 12, 2014 at 9:05 PM, PARASHAR,

Re: CQL3 Custom Functions

2014-02-12 Thread Drew Kutcharian
In that case are there any plans of supporting microsecond version of dateOf() and now() functions. It's pretty common to use microsecond precision timeuuids. I created this JIRA: https://issues.apache.org/jira/browse/CASSANDRA-6672 cheers, Drew On Feb 11, 2014, at 1:11 AM, Sylvain Lebresne