Hello
We are team of freelancers working extensively on Big Data technologies and Hadoop Ecosystem.
We have developers with 7 years of experience.
For this project we need to understand couple of things:
First thing is I need to know is your cluster configurations, then what level and how you are running jobs on spark and what all configuration you are using.
Also we need to know if you are getting any error then what it is?
We can surely resolve this issue and give you best possible solution.
Looking forward to get in touch and have a brief technical call.
Once we understand these details we can come up with time and cost required to complete this task.
Thank you.
I have 9 years of corporate experience as an senior developer watch all IT setup like systems,routers,server racks, software's and all maintenance,development ERP , website etc.
This is my first bid but having tremendous amount of experience in implementation and support of Database and big data related technology .I worked from some biggest name like HP and Indian railways which qualifying for this project.
My Skill Are:
3+ Year Experience Hadoop Eco system implementation and support .
2+ Year of Experience of Vertica Database.
6 + Year of experience on various database Administration like oralce,sql server,Postgresql
I am Sumangala and have over 11 years of software development experience.
I assume you are using Yarn. I suggest you look at the below parameter and increase the vcores to 4 times the number of actual cores you have.
yarn.nodemanager.resource.cpu-vcores
Then you can use the --executor-cores property to specify the number of virtual cores to be used by each process when submitting the jobs. Till all the virtual cores fill up the jobs will run in parallel.
If the solution works for you please ping and thank me and you can give me a good review.