osdir.com


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Cluster scaling


Hi Branislav,

what is it you would expect?

Some thoughts:

Batches are often misunderstood, they work well only if they contain only one partition key - think of a batch of different sensor data to one key. If you group batches with many partition keys and/or do large batches this puts high load on the coordinator node with then itself needs to talk to the nodes holding the partitions. This could explain the scaling you see in your second try without batches. Keep in mind that the driver supports executeAsync and ResultSetFutures.

Second, put commitlog and data directories on seperate disks when using spindles.

Third, have you monitored iostats and cpustats while running your tests?

Cheers,

Jan

Am 08.02.2017 um 16:39 schrieb Branislav Janosik -T (bjanosik - AAP3 INC at Cisco):

Hi all,

 

I have a cluster of three nodes and would like to ask some questions about the performance.

I wrote a small benchmarking tool in java that mirrors (read, write) operations that we do in the real project.

Problem is that it is not scaling like it should. The program runs two tests: one using batch statement and one without using the batch.

The operation sequence is: optional select, insert, update, insert. I run the tool on my server with 128 threads (# of threads has no influence on the performance),

creating usually 100K resources for testing purposes.

 

The average results (operations per second) with the use of batch statement are:

 

Replication Factor = 1       with reading        without reading

                1-node cluster     37K                         46K

                2-node cluster     37K                         47K

                3-node cluster     39K                         70K

 

Replication Factor = 2       with reading        without reading

                2-node cluster     21K                         40K

                3-node cluster     30K                         48K

 

The average results (operations per second) without the use of batch statement are:

 

Replication Factor = 1       with reading        without reading

                1-node cluster     31K                         20K

                2-node cluster     38K                         39K

                3-node cluster     45K                         87K

 

Replication Factor = 2       with reading        without reading

                2-node cluster     19K                         22K

                3-node cluster     26K                         36K

 

The Cassandra VMs specs are: 16 CPUs,  16GB and two 32GB of RAM, at least 30GB of disk space for each node. Non SSD, each VM is on separate physical server.

 

The code is available here https://github.com/bjanosik/CassandraBenchTool.git . It can be built with Maven and then you can use jar in target directory with java -jar target/cassandra-test-1.0-SNAPSHOT-jar-with-dependencies.jar .

Thank you for any help.

 


-- 
Jan Kesten, mailto:j.kesten@xxxxxxxxxxx
Tel.: +49 561/4739664-0 FAX: -9 Mobil: +49 160 / 90 98 41 68
enercast GmbH Universitätsplatz 12 D-34127 Kassel HRB15471
http://www.enercast.de Online-Prognosen für erneuerbare Energien
Geschäftsführung: Thomas Landgraf (CEO), Bernd Kratz (CTO), Philipp Rinder (CSO)

Diese E-Mail und etwaige Anhänge können vertrauliche und/oder rechtlich geschützte Informationen enthalten. Falls Sie nicht der angegebene Empfänger sind oder falls diese E-Mail irrtümlich an Sie adressiert wurde, benachrichtigen Sie uns bitte sofort durch Antwort-E-Mail und löschen Sie diese E-Mail nebst etwaigen Anlagen von Ihrem System. Ebenso dürfen Sie diese E-Mail oder ihre Anlagen nicht kopieren oder an Dritte weitergeben. Vielen Dank.

This e-mail and any attachment may contain confidential and/or privileged information. If you are not the named addressee or if this transmission has been addressed to you in error, please notify us immediately by reply e-mail and then delete this e-mail and any attachment from your system. Please understand that you must not copy this e-mail or any attachment or disclose the contents to any other person. Thank you for your cooperation.