giraph-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Eli Reisman <initialcont...@gmail.com>
Subject Re: Review Request: Adding calls to progress during ZooKeeper barrier waits allows heathly jobs to progress to completion without timing out on some Hadoop clusters.
Date Thu, 19 Jul 2012 19:20:10 GMT
sorry, first time using review board. I have had a lot of trouble uploading
diffs without a 500 error msg, so I just attached files (which seems to
work) also have had trouble choosing a root directory where diff was
generated, even when "giraph/" is in the autofill drop down list!

Anyone know what to do about this? I can just wait on JIRA comments if this
is too much trouble. Just trying out RB. Do you guys prefer patches to go
through it?

Thanks,

Eli


On Wed, Jul 18, 2012 at 3:08 AM, Alessandro Presta <alessandro@fb.com>wrote:

> Eli, you must have added the patch as a generic attachment, whereas you're
> supposed to choose "upload diff". That way we can review it.
> Same with https://reviews.apache.org/r/6020/
>
> On 7/18/12 1:58 AM, "Eugene Koontz" <ekoontz@hiro-tan.org> wrote:
>
> >Hi Eli,
> >       I got a 404 on :
> >https://reviews.apache.org/r/6026/diff/
> >
> >
> >I can see the review itself: https://reviews.apache.org/r/6026/
> >
> >but no way to review the diff inline.
> >
> >-Eugene
> >
> >On 7/17/12 5:37 PM, Eli Reisman wrote:
> >>
> >> -----------------------------------------------------------
> >> This is an automatically generated e-mail. To reply, visit:
> >> https://reviews.apache.org/r/6026/
> >> -----------------------------------------------------------
> >>
> >> Review request for giraph.
> >>
> >>
> >> Description
> >> -------
> >>
> >> Simply repeats a pattern of simple changes to places where an idle
> >>worker might wait uninterrupted in a PredicateLock (awaiting BspEvent in
> >>BspServiceWorker in most cases) for a Znode to be published that allows
> >>it to progress onward. Without occasional calls to context.progress() in
> >>these waits, otherwise healthy jobs can time out due to idle workers not
> >>heartbeating to the underlying Hadoop system. This patch still allows
> >>timeouts, but other when the workers have actually failed.
> >>
> >>
> >> Diffs
> >> -----
> >>
> >>
> >> Diff: https://reviews.apache.org/r/6026/diff/
> >>
> >>
> >> Testing
> >> -------
> >>
> >> July 14, 15, 16th on cluster with variety of data loads and
> >>memory/worker constraints. Passes 'mvn verify' etc.
> >>
> >>
> >> Thanks,
> >>
> >> Eli Reisman
> >>
> >>
> >
> >
>
>

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message