First bit of feedback. The `M.forEachPair` loop is about 1600-1800 millis
per user (recall the size is ~2.6M users x ~2.8M items). There doesn't
appear to be any out of the ordinary GC going on (yet). Going to look at
optimising this loop a bit and see where I can get. Definitely time-boxing
this though ;)


On 6 March 2013 12:16, Sebastian Schelter <[email protected]> wrote:

> Btw, all important jobs in ALS are map-only, so its the number of map
> slotes that counts.
>
> On 06.03.2013 12:11, Sean Owen wrote:
> > OK, that's reasonable on 35 machines. (You can turn up to 70 reducers,
> > probably, as most machines can handle 2 reducers at once).
> > I think the recommendation step loads one whole matrix into memory.
> You're
> > not running out of memory but if you're turning up the heap size to
> > accommodate, you might be hitting swapping, yes. I think (?) the
> > conventional wisdom is to turn off swap for Hadoop.
> >
> > Sebastian yes that is probably a good optimization; I've had good results
> > reusing a mutable object in this context.
> >
> >
> > On Wed, Mar 6, 2013 at 10:54 AM, Josh Devins <[email protected]> wrote:
> >
> >> The factorization at 2-hours is kind of a non-issue (certainly fast
> >> enough). It was run with (if I recall correctly) 30 reducers across a 35
> >> node cluster, with 10 iterations.
> >>
> >> I was a bit shocked at how long the recommendation step took and will
> throw
> >> some timing debug in to see where the problem lies exactly. There were
> no
> >> other jobs running on the cluster during these attempts, but it's
> certainly
> >> possible that something is swapping or the like. I'll be looking more
> >> closely today before I start to consider other options for calculating
> the
> >> recommendations.
> >>
> >>
> >
>
>

Reply via email to