spark-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Yann Luppo <YannLu...@LiveNation.com>
Subject Re: performance
Date Thu, 09 Jan 2014 22:11:43 GMT
Thank you guys that was really helpful in identifying the slow step, which in our case is the
leftouterjoin.
I'm checking with our admins to see if we have some sort of distributed system monitoring
in place, which I'm sure we do.

Now just out of curiosity, what would be the rule of thumb or general guideline for the number
of partitions and the number of reducers?
Should it be some kind of factor of the number of cores available? Of nodes available? Should
the number of partitions match the number of reducers or at least be some multiple of it for
better performance?

Thanks,
Yann

From: Evan Sparks <evan.sparks@gmail.com<mailto:evan.sparks@gmail.com>>
Reply-To: "user@spark.incubator.apache.org<mailto:user@spark.incubator.apache.org>"
<user@spark.incubator.apache.org<mailto:user@spark.incubator.apache.org>>
Date: Wednesday, January 8, 2014 5:28 PM
To: "user@spark.incubator.apache.org<mailto:user@spark.incubator.apache.org>" <user@spark.incubator.apache.org<mailto:user@spark.incubator.apache.org>>
Cc: "user@spark.incubator.apache.org<mailto:user@spark.incubator.apache.org>" <user@spark.incubator.apache.org<mailto:user@spark.incubator.apache.org>>
Subject: Re: performance

On this note - the ganglia web front end that runs on the master (assuming you're launching
with the ec2 scripts) is great for this.

Also, a common technique for diagnosing "which step is slow" is to run a '.cache' and a '.count'
on the RDD after each step. This forces the RDD to be materialized, which subverts the lazy
evaluation that causes such diagnosis to be hard sometimes.

- Evan

On Jan 8, 2014, at 2:57 PM, Andrew Ash <andrew@andrewash.com<mailto:andrew@andrewash.com>>
wrote:

My first thought on hearing that you're calling collect is that taking all the data back to
the driver is intensive on the network.  Try checking the basic systems stuff on the machines
to get a sense of what's being heavily used:

disk IO
CPU
network

Any kind of distributed system monitoring framework should be able to handle these sorts of
things.

Cheers!
Andrew


On Wed, Jan 8, 2014 at 1:49 PM, Yann Luppo <YannLuppo@livenation.com<mailto:YannLuppo@livenation.com>>
wrote:
Hi,

I have what I hope is a simple question. What's a typical approach to diagnostic performance
issues on a Spark cluster?
We've followed all the pertinent parts of the following document already: http://spark.incubator.apache.org/docs/latest/tuning.html
But we seem to still have issues. More specifically we have a leftouterjoin followed by a
flatmap and then a collect running a bit long.

How would I go about determining the bottleneck operation(s) ?
Is our leftouterjoin taking a long time?
Is the function we send to the flatmap not optimized?

Thanks,
Yann


Mime
View raw message