Spark executes tasks on an action. An action is broken down to multiple
tasks. Multiple tasks from different actions run either in FIFO or FAIR
mode depending on spark.scheduler.mode.
Of course to get benefit of FAIR scheduling the two actions should be
called by different threads.
On Mon, Oct 26, 2015 at 5:01 PM, Fengdong Yu <fengdo...@everstring.com>
wrote:
> not parallel.
>
> Spark only execute tasks with Action,(‘collect' here)
>
> rdd1.collect and rdd2.collect are executed sequencely, so Spark execute
> two tasks one by one.
>
>
>
>
> On Oct 26, 2015, at 7:26 PM, praveen S <mylogi...@gmail.com> wrote:
>
> Does spark run different actions of an rdd within a driver in parallel
> also?
>
> Let's say
> class Driver{
>
> val rdd1= sc. textFile("... ")
> val rdd2=sc.textFile("....")
> rdd1. collect //Action 1
> rdd2. collect //Action 2
>
> }
>
> Does Spark run Action 1 & 2 run in parallel? ( some kind of a pass through
> the driver code and than start the execution)?
>
> if not than is using threads safe for independent actions/red's?
>
>
>
--
Regards,
Rishitesh Mishra,
SnappyData . (http://www.snappydata.io/)
https://in.linkedin.com/in/rishiteshmishra
