Elasticsearch cluster has 2 nodes. But when I start stress test using esrally, I found that one of them has more rejections than the other
node_name name active queue rejected completed
elasticsearch-logging-0 write 0 0 108266 70186
elasticsearch-logging-1 write 0 0 5662 70109
- Each of them has 2 cores, but their bulk thread pool processor is 2.
- My rally clients number is 200 and the bulk_size is 100.
- Each doc is about 900 bytes.
- The error rate from esrally is 95%!!!!!!!!
PLZ! Can anyone help me!!! ORZ!!!