Re: Unbalanced cluster

You wouldnt have a build file laying around for that, would you? On Tue, Jul 11, 2017 at 3:23 PM, Nate McCall wrote: > On Tue, Jul 11, 2017 at 3:20 AM, Avi Kivity wrote: > >> >> >> >> [1] https://github.com/avikivity/shardsim >> > > Avi, that's super

Re: index_interval

On 2017-07-10 15:09 (-0700), Fay Hou [Storage Service] ­ wrote: > BY defaults: > > AND max_index_interval = 2048 > AND memtable_flush_period_in_ms = 0 > AND min_index_interval = 128 > > "Cassandra maintains index offsets per partition to speed up the lookup >

Re: Unbalanced cluster

On Tue, Jul 11, 2017 at 3:20 AM, Avi Kivity wrote: > > > > [1] https://github.com/avikivity/shardsim > Avi, that's super handy - thanks for posting.

Re: Unbalanced cluster

the reason for the default of 256 vnodes is because at that many tokens the random distribution of tokens is enough to balance out each nodes token allocation almost evenly. any less and some nodes will get far more unbalanced, as Avi has shown. In 3.0 there is a new token allocating algorithm

index_interval

BY defaults: AND max_index_interval = 2048 AND memtable_flush_period_in_ms = 0 AND min_index_interval = 128 "Cassandra maintains index offsets per partition to speed up the lookup process in the case of key cache misses (see cassandra read path overview

Re: private interface for interdc messaging

Hi,  I am not sure why you would want to connect clients on public interface. Are you making db calls from clients outside the DC?  Also, not sure why you expect two DCs to communicate on private networks unless they are two logical DCs within same physical DC.  Generally,  you configure multi

Re: Data Model Suggestion Required

On 2017-07-10 07:13 (-0700), Siddharth Prakash Singh wrote: > I am planning to build a user activity timeline. Users on our system > generates different kind of activity. For example - Search some product, > Calling our sales team, Marking favourite etc. > Now I would like to

Re: Cassandra crashed with OOM, and the system.log and debug.log doesn't match.

On 2017-07-10 02:07 (-0700), 张强 wrote: > Hi experts, I've a single cassandra 3.11.0 node working with kairosdb (a > time series database), after running 4 days with stable workload, the > database client start to get "request errors", but there are not a lot of > error or

Re: Unbalanced cluster

32 tokens is too few for 33 nodes. I have a sharding simulator [1] and it shows $ ./shardsim --vnodes 32 --nodes 33 --shards 1 33 nodes, 32 vnodes, 1 shards maximum node overcommit: 1.42642 maximum shard overcommit: 1.426417 So 40% overcommit over the average. Since some nodes can be

Re: Cassandra crashed with OOM, and the system.log and debug.log doesn't match.

Thanks for your reply! There are 3 column families, they are created by kairosdb, one column family takes almost all the workload. I didn't tune the heap size, so by default it'll be 3GB. I have monitored the cpu and memory usage, the cpu usage is about 30% in average, and the available memory is

Data Model Suggestion Required

I am planning to build a user activity timeline. Users on our system generates different kind of activity. For example - Search some product, Calling our sales team, Marking favourite etc. Now I would like to generate timeline based on these activities. Timeline could be for all events, filtered

Re: private interface for interdc messaging

Did your network team setup route? Can you run traceroute and see? Sent from my iPhone > On Jul 10, 2017, at 2:12 AM, CPC wrote: > > Hi, > > setting broadcast adress does not resolve problem. We still saw interdc > traffic like below: > dc1 public => dc2 private > >

Unbalanced cluster

Hi, One of our clusters is becoming somehow unbalanced, at least some of the nodes: (output edited to remove unnecessary information) -- Address Load Tokens Owns (effective) Rack UN 192.168.1.22 2.99 TB32 10.6% RACK1 UN 192.168.1.23 3.35 TB32

Re: error 1300 from csv export

Sorry for the noise, somehow overread the copy option BEGINTOKEN and ENDTOKEN.. Michael On 10.07.2017 13:11, Micha wrote: > Hi, > > I got some errors from a csv export of a table. > They are of the form: > "Error for (number-1, number-2): ReadFailure Error from server: > code=1300 ... " >

error 1300 from csv export

Hi, I got some errors from a csv export of a table. They are of the form: "Error for (number-1, number-2): ReadFailure Error from server: code=1300 ... " At the end "Exported 650 ranges out of 658 total, some records might be missing" Is there a way to start the export only for the failed

Re: Cassandra crashed with OOM, and the system.log and debug.log doesn't match.

Hi, *How many column families are there? What is the heap size?* You can turn off logs for statusLogger.java and gc to optimize heap usage. Can you also monitor cpu usage and memory usage? IMO, in your case memory is the bottle-neck. Thanks!! On Mon, Jul 10, 2017 at 5:07 PM, 张强

Re: private interface for interdc messaging

Hi, setting broadcast adress does not resolve problem. We still saw interdc traffic like below: dc1 public => dc2 private traffic. We we want is: dc1 private => dc2 private Any idea? Also could it be related to https://issues.apache.org/jira/browse/CASSANDRA-12673. Any idea? On 7 July 2017 at

Re: Understanding of cassandra metrics

So, Range latency(or Scan in case of coordinator) appears only when we are reading multiple partition key in the same query? пт, 7 июл. 2017 г. в 20:29, Chris Lohfink : > The coordinator read/scan (Scan is just different naming for the Range, so > coordinator view of

Re: UDF for sorting

I have read HowToContribute and created the ticket CASSANDRA-13682 with PR and path available flag. Eduardo Alonso Vía de las dos Castillas, 33, Ática 4, 3ª Planta 28224 Pozuelo de