1.aaa
Spark is calculated based on the large data parallel computing frame memory. Spark calculated based on the memory, improved real-time data in a large data processing environment, while ensuring a high fault tolerance and scalability, allow a user to Spark disposed over a large number of cheap hardware, form a cluster.
1.1 bbb
For distributed computing systems such as Spark, the task will be distributed to execute on multiple machines, drain the limited resources to achieve rapid cluster parallel computing to achieve fast and efficient, Spark priority to use as a storage memory of each node
2ccc
When Out of Memory will consider using a disk, which greatly reduces disk I / O, provides the efficiency of execution of tasks, making Spark for real-time calculation, iteration, flow calculation scene
3 ddd
Generate some massive data reports / build machine learning related models
3.1eee
Mesos is a resource management framework. User task can run in the plug-in which the frame is calculated. Mesos resources and tasks will be isolated, and to achieve efficient resource scheduling. Can be assigned by the queue, the service management cluster simultaneously run multiple thereof, according to different types of applications where pressure is adjusted corresponding to the amount of resources, resource management elasticity.