Return-Path: X-Original-To: archive-asf-public-internal@cust-asf2.ponee.io Delivered-To: archive-asf-public-internal@cust-asf2.ponee.io Received: from cust-asf.ponee.io (cust-asf.ponee.io [163.172.22.183]) by cust-asf2.ponee.io (Postfix) with ESMTP id E623B200D3C for ; Mon, 9 Oct 2017 17:12:57 +0200 (CEST) Received: by cust-asf.ponee.io (Postfix) id E47F3160BE0; Mon, 9 Oct 2017 15:12:57 +0000 (UTC) Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by cust-asf.ponee.io (Postfix) with SMTP id C96751609CE for ; Mon, 9 Oct 2017 17:12:56 +0200 (CEST) Received: (qmail 58890 invoked by uid 500); 9 Oct 2017 15:12:52 -0000 Mailing-List: contact user-help@flink.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Delivered-To: mailing list user@flink.apache.org Received: (qmail 58855 invoked by uid 99); 9 Oct 2017 15:12:52 -0000 Received: from mail-relay.apache.org (HELO mail-relay.apache.org) (140.211.11.15) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 09 Oct 2017 15:12:52 +0000 Received: from mail-qt0-f171.google.com (mail-qt0-f171.google.com [209.85.216.171]) by mail-relay.apache.org (ASF Mail Server at mail-relay.apache.org) with ESMTPSA id 34A9F1A0413 for ; Mon, 9 Oct 2017 15:12:50 +0000 (UTC) Received: by mail-qt0-f171.google.com with SMTP id f15so43728266qtf.7 for ; Mon, 09 Oct 2017 08:12:50 -0700 (PDT) X-Gm-Message-State: AMCzsaUWSWWKI+A8JLaDwe+N0PO3jtAjTzpbNtUQY9NwRuye0oZ/ipta JFCQsPg3O4QTI5i4e9Te7ASQ0d4Y8pgqPQod1ps= X-Google-Smtp-Source: AOwi7QC5ASnFCqiw8GtzwwHNm9LXEAbpNt5C8aoaSBugZnXIGiG4gGa73WxbHoSnt6JiY4FiwIdf5qaSQIqOPNMkOX8= X-Received: by 10.237.62.53 with SMTP id l50mr4205637qtf.270.1507561969226; Mon, 09 Oct 2017 08:12:49 -0700 (PDT) MIME-Version: 1.0 Received: by 10.12.172.70 with HTTP; Mon, 9 Oct 2017 08:12:08 -0700 (PDT) In-Reply-To: <475D836E-9FF9-4ABE-962D-F6B4E4A0EF0C@gmail.com> References: <475D836E-9FF9-4ABE-962D-F6B4E4A0EF0C@gmail.com> From: Till Rohrmann Date: Mon, 9 Oct 2017 17:12:08 +0200 X-Gmail-Original-Message-ID: Message-ID: Subject: Re: Consult about flink on mesos cluster To: yubo Cc: "Tzu-Li (Gordon) Tai" , user , Eron Wright Content-Type: multipart/alternative; boundary="001a113b4a38a71d5f055b1e9f7b" archived-at: Mon, 09 Oct 2017 15:12:58 -0000 --001a113b4a38a71d5f055b1e9f7b Content-Type: text/plain; charset="UTF-8" Hi Bo, you can still use Flink with Marathon, because Marathon will only schedule the cluster entrypoint which is the MesosApplicationMasterRunner. Everything else will be scheduled via Fenzo. Moreover, by using Marathon you gain high availability because Marathon makes sure that the ApplicationMaster is restarted in case of a failure. Cheers, Till On Mon, Oct 9, 2017 at 2:59 PM, yubo wrote: > Thanks for your reply, Till > We will use without Marathon, and hope the PR is merged to latest version > soon. > > Best regards, > Bo > > On Oct 9, 29 Heisei, at 6:36 PM, Till Rohrmann > wrote: > > Hi Bo, > > Flink uses internally Fenzo to match tasks and offers. Fenzo does not > support the Marathon constraints syntax you are referring to. At the > moment, Flink only allows to define hard host attribute constraints which > means that you define a host attribute which has to match exactly. Fenzo > also supports constraints that work on a set of tasks [1], but this is not > yet exposed to the user. With that you should be able to evenly spread your > tasks across multiple machines. > > There is actually a PR [2] trying to add this functionality. However, it > is not yet in the shape to be merged. > > [1] https://github.com/Netflix/Fenzo/wiki/Constraints#constraints-that- > operate-on-groups-of-tasks > [2] https://github.com/apache/flink/pull/4628 > > Cheers, > Till > > On Fri, Oct 6, 2017 at 10:54 AM, Tzu-Li (Gordon) Tai > wrote: > >> Hi Bo, >> >> I'm not familiar with Mesos deployments, but I'll forward this to Till or >> Eron (in CC) who perhaps could provide some help here. >> >> Cheers, >> Gordon >> >> >> On 2 October 2017 at 8:49:32 PM, Bo Yu (yubo1983@gmail.com) wrote: >> >> Hello all, >> This is Bo, I met some problems when I tried to use flink in my mesos >> cluster (1 master, 2 slaves (cpu has 32 cores)). >> I tried to start the mesos-appmaster.sh in marathon, the job manager is >> started without problem. >> >> mesos-appmaster.sh -Djobmanager.heap.mb=1024 -Dtaskmanager.heap.mb=1024 >> -Dtaskmanager.numberOfTaskSlots=32 >> >> My problem is the task managers are all located in one single slave. >> 1. (log1) >> The initial tasks in "/usr/local/flink/conf/flink-conf.yaml" is setted >> as "mesos.initial-tasks: 2" >> And also set the "mesos.constraints.hard.hostattribute: rack:ak09-27", >> which is the master node of mesos cluster. >> >> 2. (log2) >> I tried many ways to distribute the tasks to all the available slaves, >> and without any success. >> So I decide to try add a group_by operator which I referenced from >> https://mesosphere.github.io/marathon/docs/constraints.html >> "mesos.constraints.hard.hostattribute: rack:ak09-27,GROUP_BY:2" >> According to the log, flink keep waiting for more offers and the tasks >> never been launched. >> >> Sorry, I am a newbie to flink, also on mesos. Please reply if my problem >> is not clear, and I will be appreciate on any hint about how to distribute >> task evenly on available resources. >> >> Thank you in advance. >> >> Best regards, >> >> Bo >> >> > > --001a113b4a38a71d5f055b1e9f7b Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Bo,

you can still use Flink with Mar= athon, because Marathon will only schedule the cluster entrypoint which is = the MesosApplicationMasterRunner. Everything else will be scheduled via Fen= zo. Moreover, by using Marathon you gain high availability because Marathon= makes sure that the ApplicationMaster is restarted in case of a failure.

Cheers,
Till

On Mon, Oct 9, 2017 at 2:59 PM, yu= bo <yubo1983@gmail.com> wrote:
Thanks for = your reply, Till
We will use without Marathon, and hope the PR is= merged to latest version soon.
=C2=A0
Best regards,
Bo

On Oct 9, 29 Heisei, at 6:36 PM, Till Rohrmann <trohrmann@apache.org= > wrote:

Hi Bo,

Flink uses internally Fenzo to match tasks and offers. Fenzo does no= t support the Marathon constraints syntax you are referring to. At the mome= nt, Flink only allows to define hard host attribute constraints which means= that you define a host attribute which has to match exactly. Fenzo also su= pports constraints that work on a set of tasks [1], but this is not yet exp= osed to the user. With that you should be able to evenly spread your tasks = across multiple machines.

There is actually a PR [= 2] trying to add this functionality. However, it is not yet in the shape to= be merged.


Cheers,
Till

On Fri, Oct 6, 2017 at 10:54 AM, Tzu-Li (Gordon) Tai <= tzulitai@apache.org> wrote:
Hi Bo,

I= 9;m not familiar with Mesos deployments, but I'll forward this to Till = or Eron (in CC) who perhaps could provide some help here.

Cheers,
Gordon<= /div>


=

On 2 Oc= tober 2017 at 8:49:32 PM, Bo Yu (yubo1983@gmail.com) wrote:

<= div>
Hello all,
This is Bo, I met some problems when I tried to use flink in my mesos cluster (1 master, 2 slaves (cpu has 32 cores)).
I tried to start the mesos-appmaster.sh in marathon, the job manager is started without problem.

mesos-appmaster.sh -Djobmanager.heap.mb=3D1024 -Dtaskmanager.heap.mb=3D1024 -Dtaskmanager.numberOfTaskSlots=3D32

My problem is the task managers are all located in one single slave.
1. (log1)
The initial tasks in "/usr/local/flink/conf/flink-conf.yaml" is setted as "mesos.initial-tasks: 2"
And also set the "mesos.constraints.hard.hostattribute: rack:ak09-27", which is the master node of mesos cluster.

2. (log2)
I tried many ways to distribute the tasks to all the available slaves, and without any success.
So I decide to try add a group_by operator which I referenced from https://mesosphere.github.io/marathon/docs/constra= ints.html
"mesos.constraints.hard.hostattribute: rack:ak09-27,GROUP_BY:2"
According to the log, flink keep waiting for more offers and the tasks never been launched.

Sorry, I am a newbie to flink, also on mesos. Please reply if my problem is not clear, and I will be appreciate on any hint about how to distribute task evenly on available resources.

Thank you in advance.

Best regards,

Bo




--001a113b4a38a71d5f055b1e9f7b--