#x27;queue 1' and 'queue 2' with the config that
> you provided? That is, based on your configs what is the queue name that
> was using 100% and which was being starved for resources?
>
> Thanks,
> -Eric
>
>
>
> On Friday, October 11, 2019, 6:41:08 AM CDT,
oo.state
RUNNING
yarn.scheduler.capacity.root.foo.user-limit-factor
1
On Wed, Oct 9, 2019 at 10:56 PM Lars Francke wrote:
> Sunil,
>
> thank you for the answer.
>
> This is HDP 3.1 based on Hadoop 3.1.1.
> No preemption defaults were changed I belie
ed configs
> which are added)
>
> - Sunil
>
> On Wed, Oct 9, 2019 at 6:23 PM Lars Francke
> wrote:
>
>> Hi,
>>
>> I've got a question about behavior we're seeing.
>>
>> Two queues: Preemption enabled, CapacityScheduler (happy to provide mor
Hi,
I've got a question about behavior we're seeing.
Two queues: Preemption enabled, CapacityScheduler (happy to provide more
config if needed), 50% of resources to each
Submit a job to queue 1 which uses 100% of the cluster.
Submit a job to queue 2 which doesn't get allocated because there are
Just pinging to see if anyone has any insight here?
On Mon, May 13, 2019 at 10:31 PM Lars Francke
wrote:
> Hi,
>
> I'm working with a few clusters of 100+ nodes and I've been wondering how
> exactly the failover, as well as a cold start, works in respect to the
> block
Hi,
I'm working with a few clusters of 100+ nodes and I've been wondering how
exactly the failover, as well as a cold start, works in respect to the
block reports.
I sometimes see failover times of 15-45 minutes waiting in the safe mode
for all blocks to report in.
Datanodes usually send a repor
rote:
> On Tue, Feb 20, 2018 at 3:09 AM, Lars Francke
> wrote:
> > Is this intentional or just oversight/inconsistencies?
>
> The release candidate (RC) tags are created during votes. They can
> probably be cleaned up after the release is published.
>
> At a glance, rel
Hi,
can anyone tell me what the policies are around tags in git these days? I
see from the HowToRelease[1] wiki that everything should be tagged in
"rel/" but looking at the last releases I see:
* release-3.0.1-RC0
* rel/release-3.0.0
...
* release-3.0.0-RC1
...
* rel/release-3.0.0-alpha4
etc.
<
Hi,
I've been using Hadoop for years and have always just taken for granted
that FairScheduler = Cloudera and CapacityScheduler = Hortonworks/Yahoo.
There are some comparisons but all of them are years old and somewhat (if
not entirely) outdated.
The documentation doesn't really help and neither
