S3 Versus HDFS For Spark Data Storage

Reynold Xin, Josh Rosen, and Kyle Pistor argue that you should use blob storage (S3, Azure Blob, etc.) instead of disk when building a cloud-based Spark cluster:

Based on our experience, S3’s availability has been fantastic. Only twice in the last six years have we experienced S3 downtime and we have never experienced data loss from S3.

Amazon claims 99.999999999% durability and 99.99% availability. Note that this is higher than the vast majority of organizations’ in-house services. The official SLA from Amazon can be found here: Service Level Agreement – Amazon Simple Storage Service (S3).

For HDFS, in contrast, it is difficult to estimate availability and durability. One could theoretically compute the two SLA attributes based on EC2’s mean time between failures (MTTF), plus upgrade and maintenance downtimes. In reality, those are difficult to quantify. Our understanding working with customers is that the majority of Hadoop clusters have availability lower than 99.9%, i.e. at least 9 hours of downtime per year.

It’s interesting how opinion has shifted; even a year ago, the recommendation would be different.

Related Posts

Mounting HDFS As A Local Filesystem

Guy Shilo looks at two techniques for mounting HDFS as a local filesystem: NFS Gateway is a HDFS component that enables the use to expose HDFS through NFS3 interface so that Linux machines can mount it and access it just as a local filesystem. The manual installation is quite cumbersome and is covered here. Cloudera manager […]

Read More

How Humio Uses Kafka

Kresten Krab describes ways that Humio uses Apache Kafka for their product: Humio is a log analytics system built to run both on-prem and as a hosted offering. It is designed for “on-prem first” because, in many logging use cases, you need the privacy and security of managing your own logging solution. And because volume […]

Read More

Categories

June 2017
MTWTFSS
« May Jul »
 1234
567891011
12131415161718
19202122232425
2627282930