Hi All, I'm experiencing search performance degradation when index size is growing. Eg: For a given query, i'm getting *3500* RPS (Request per second) with *1M* documents on index, whereas with *6M* documents on index is giving me *1200* RPS. Each document size on index is average of 500 bytes. Tried with following different cluster configs, and the behavior is same in both cases.
Elastic Search version:* 1.2.1* *Cluster 1 configuration: 4 node cluster* 2 Routers Nodes: VMs with 4 Core CPU, 4 GB Ram, 20GB disk 2 Data Nodes: Physicals with 32 Core CPU, 198GB Ram (24G allocated to ES process), 250 GB disk *Cluster 2 configuration: 7 node cluster* 2 Routers Nodes: VMs with 4 Core CPU, 4 GB Ram, 20GB disk 2 Data Nodes: VMs with 8 Core CPU, 48GB Ram (24G allocated to ES process), 250 GB local storage In addition to search query performance issue, i observed that the Data nodes CPU is always spiking to 100% on all core. Any inputs would be greatly appreciated. Thanks Gopi -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to elasticsearch+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/elasticsearch/4afce9b6-8076-492a-b79c-97ab793eb2f9%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
