Re: Is StarCluster still under active development?

From: Rajat Banerjee <no email>
Date: Sun, 3 Apr 2016 23:37:18 -0400

Hi Tony,
Interesting findings. Yes that does seem like a bug with polling_interval.
All of the logic to make a load balancing decision is done
in _eval_add_node and doesn't consider average job duration. It was a
design decision at the time: look at the queue and current slot count to
see if throughput meets the parameter longest_allowed_queue_time, or
whether we should try to predict job durations. We surveyed some of the
most active users at that time and most said their job sizes were varying
and unpredictable and not amenable to 'prediction'. So we went with the
former.

Thanks for sharing your findings, but I'm not sure why you seem cranky that
the ELB isn't meeting your predictive load balancing needs and has some
bugs in unused code? It's open source for a reason, so people can adapt and
improve it.
best,
Raj

On Sun, Apr 3, 2016 at 8:41 AM, Tony Robinson <tonyr_at_speechmatics.com>
wrote:

> Okay, I've found another bug with the load balancer which explains why
> avg_job_duration() was getting shorter and shorter.
>
> get_qatime() initially loads the whole (3 hours) history, but after that
> sets temp_lookback_window = self.polling_interval
>
> The problem with this is self.polling_interval has to be much shorter than
> a job duration (it's got to be able to keep up) and the -b option to qacct
> sets "The earliest start time for jobs to be summarized,", so it only
> selects jobs that have been started recently and finished (so that they get
> into qacct) - hence they must be the very short jobs. Hence the cache is
> originally populated quite reasonably but then only gets updated with very
> short jobs, all the long ones never get into the cache.
>
> As I say below, I don't think any of this code is used anyway so it
> doesn't matter too much that it's all broken.
>
> I'll progress with my (weekend and part time) clean up and implementation
> of a true predictive load balancer. I have both (a) mean and variance for
> all job types and (b) working code assuming that avg_job_duration() is
> correct, so it's probably only another days work to get solid (or a month
> or two of elapsed time, I'm done for this weekend).
>
>
> Tony
>
>
> On 01/04/16 17:01, Tony Robinson wrote:
>
> On 01/04/16 16:22, Rajat Banerjee wrote:
>
> Regarding:
> How about we just call qacct every 5 mins, or if the qacct buffer is
> empty.
> calling qacct and getting the job stats is the first part of the load
> balancers loop to see what the cluster is up to. I prioritized knowing the
> current state, and keeping the LB running it's loop as fast as possible
> (2-10 seconds), so it could run in a 1-minute loop and stay roughly
> on-schedule. It's easy to run the whole LB loop with 5 minutes between
> loops with the command line arg polling_interval, if that suits your
> workload better. I do not mean to sound dismissive, but the command line
> options (with reasonable defaults)are there so you can test and tweak to
> your work load.
>
>
> Ah, I wasn't very clear. What I mean is that we only update the qacct
> stats every 5 minutes. I run the main loop every 30s.
>
> But calling qacct doesn't' take any time - we could do it every polling
> interval:
>
> root_at_master:~# date
> Fri Apr 1 16:54:31 BST 2016
> root_at_master:~# echo qacct -j -b `date +%y%m%d`$((`date +%H` - 3))`date
> +%m`
> qacct -j -b 1604011304
> root_at_master:~# time qacct -j -b `date +%y%m%d`$((`date +%H` - 3))`date
> +%m` | wc
> 99506 224476 3307423
>
> real 0m0.588s
> user 0m0.560s
> sys 0m0.076s
> root_at_master:~#
>
>
> If calling qacct is slow then the update could be run at the end of the
> loop so it would have all of the loop wait time to complete in.
>
> Regarding:
> Three sorts of jobs, all of which should occur in the same numbers,
> Have you tried testing your call to qacct to see if it's returning what
> you want? You could modify it in your source if it's not representative of
> your jobs:
>
> https://github.com/jtriley/StarCluster/blob/develop/starcluster/balancers/sge/__init__.py#L528
> qacct_cmd = 'qacct -j -b ' + qatime
>
>
> Yes, thanks, I'm comparing to running qacct outside of the load balancer.
>
> Obviously one size doesn't fit all here, but if you find a set of args for
> qacct that work better for you, let me know.
>
>
> At the moment I don't think that the output of qacct is used at all is
> it? I thought it was only used to give job stats, I don't think it's
> really used to bring nodes up/down.
>
>
> Tony
>
> --
> Speechmatics is a trading name of Cantab Research Limited
> We are hiring: www.speechmatics.com/careers
> <http:www.speechmatics.com/careers>
> Dr A J Robinson, Founder, Cantab Research Ltd
> Phone direct: 01223 794096, office: 01223 794497
> Company reg no GB 05697423, VAT reg no 925606030
> 51 Canterbury Street, Cambridge, CB4 3QG, UK
>
>
>
> --
> Speechmatics is a trading name of Cantab Research Limited
> We are hiring: www.speechmatics.com/careers
> Dr A J Robinson, Founder, Cantab Research Ltd
> Phone direct: 01223 794096, office: 01223 794497
> Company reg no GB 05697423, VAT reg no 925606030
> 51 Canterbury Street, Cambridge, CB4 3QG, UK
>
> _______________________________________________
> StarCluster mailing list
> StarCluster_at_mit.edu
> http://mailman.mit.edu/mailman/listinfo/starcluster
>
>
Received on Sun Apr 03 2016 - 23:37:40 EDT