[GitHub] [zookeeper] maoling commented on issue #1129: ZOOKEEPER-3593: fix the default value of jute.maxbuffer in client side and an optimization for the documentation

[GitBox <gi...@apache.org>]

maoling commented on issue #1129: ZOOKEEPER-3593: fix the default value of jute.maxbuffer in client side and an optimization for the documentation
URL: https://github.com/apache/zookeeper/pull/1129#issuecomment-580994614
 
 
   @i3wangyi
   > I was recently trying to experiment with the performance downgrade when znode is larger than 1MB and happened to find this PR
   
   - For example, you are testing `znode` which is 4 MB.
       - For server side, set `-Djute.maxbuffer=4194304` in the `zkServer.sh`
       - For client side, set `System.setProperty("jute.maxbuffer", "4194304")` in your own java test code.
   - Actually, we have a comprehensive benchmark tool, but not merged yet. You can try [it](https://github.com/brianfrankcooper/YCSB/pull/1327). which has a detailed docs.
   
   ```
   # test for big znode. Notice:jute.maxbuffer should also be set the same value in the server side.
   ./bin/ycsb run zookeeper -jvm-args="-Djute.maxbuffer=4194304" -s -P workloads/workloadc -p zookeeper.connectString=127.0.0.1:2181/benchmark
   ```
   - If you have more questions, plz ask here.
   

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services