We use Spark with NFS as the data store, mainly using Dr. Jeremy Freeman’s Thunder framework. Works very well (and I see HUGE throughput on the storage system during loads). I haven’t seen (or heard from the devs/users) a need for HDFS or S3.
—Ken
|
- Re: What do I loose if I run spark w... Mich Talebzadeh
- Re: What do I loose if I run spa... Ofir Manor
- Re: What do I loose if I run spa... kant kodali
- Re: What do I loose if I run spa... Michael Gummelt
- Re: What do I loose if I run spa... kant kodali
- Re: What do I loose if I run spa... ayan guha
- Re: What do I loose if I run spa... Michael Gummelt
- Re: What do I loose if I run spa... Mark Hamstra
- Re: What do I loose if I run spa... kant kodali
- Re: What do I loose if I run spa... kant kodali
- Re: What do I loose if I run spa... Carlile, Ken
- Re: What do I loose if I run spa... Steve Loughran
- Re: What do I loose if I run spa... kant kodali
- Re: What do I loose if I run spa... Mich Talebzadeh
- Re: What do I loose if I run spa... kant kodali
- Re: What do I loose if I run spa... Steve Loughran
- Re: What do I loose if I run spa... kant kodali
- Re: What do I loose if I run spark without using HDFS or Z... Peter Figliozzi