Hi,
Lukas is correct, due to the fact that all workers must be available to
send and receive messages during each superstep, Giraph needs all mappers
up and running at once to begin a computation.
On Jan 27, 2015 11:01 AM, Walaa Eldin Moustafa wa.moust...@gmail.com
wrote:
Thanks! Are not there
Thanks! Are not there any options to relax this restriction? My end goal is
to have small input splits for each worker so that workers can finish
processing input splits without throwing out of memory exceptions.
On Tue, Jan 27, 2015 at 1:14 AM, Lukas Nalezenec
lukas.naleze...@firma.seznam.cz
On 23.1.2015 00:40, Walaa Eldin Moustafa wrote:
Hi,
I am experimenting with a memory-intensive Giraph application on top
of a large graph (50 million nodes), on a 14 node cluster.
When setting the number of workers to a large number (500 in this
example), I get errors for not being able to
Just bumping up this thread. Thanks in advance for the help.
Thanks,
Walaa.
On Thu, Jan 22, 2015 at 3:40 PM, Walaa Eldin Moustafa wa.moust...@gmail.com
wrote:
Hi,
I am experimenting with a memory-intensive Giraph application on top of a
large graph (50 million nodes), on a 14 node