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 813B4200B21 for ; Thu, 12 May 2016 01:59:07 +0200 (CEST) Received: by cust-asf.ponee.io (Postfix) id 8037F160A19; Wed, 11 May 2016 23:59:07 +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 D20A7160A17 for ; Thu, 12 May 2016 01:59:06 +0200 (CEST) Received: (qmail 54090 invoked by uid 500); 11 May 2016 23:59:06 -0000 Mailing-List: contact dev-help@flink.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@flink.apache.org Delivered-To: mailing list dev@flink.apache.org Received: (qmail 54068 invoked by uid 99); 11 May 2016 23:59:05 -0000 Received: from pnap-us-west-generic-nat.apache.org (HELO spamd4-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 11 May 2016 23:59:05 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd4-us-west.apache.org (ASF Mail Server at spamd4-us-west.apache.org) with ESMTP id 5B989C0187 for ; Wed, 11 May 2016 23:59:05 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd4-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: -0.721 X-Spam-Level: X-Spam-Status: No, score=-0.721 tagged_above=-999 required=6.31 tests=[RCVD_IN_DNSWL_LOW=-0.7, RCVD_IN_MSPIKE_H3=-0.01, RCVD_IN_MSPIKE_WL=-0.01, SPF_PASS=-0.001] autolearn=disabled Received: from mx2-lw-us.apache.org ([10.40.0.8]) by localhost (spamd4-us-west.apache.org [10.40.0.11]) (amavisd-new, port 10024) with ESMTP id fN-PUgGF2ccc for ; Wed, 11 May 2016 23:59:01 +0000 (UTC) Received: from BLU004-OMC1S11.hotmail.com (blu004-omc1s11.hotmail.com [65.55.116.22]) by mx2-lw-us.apache.org (ASF Mail Server at mx2-lw-us.apache.org) with ESMTPS id DC6065F297 for ; Wed, 11 May 2016 23:59:00 +0000 (UTC) Received: from BLU436-SMTP111 ([65.55.116.8]) by BLU004-OMC1S11.hotmail.com over TLS secured channel with Microsoft SMTPSVC(7.5.7601.23008); Wed, 11 May 2016 16:59:00 -0700 X-TMN: [euUJq+9DuuMFL0fcxoGYjtF2qXl3LC+R] X-Originating-Email: [ewright@live.com] Message-ID: Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 (Mac OS X Mail 9.3 \(3124\)) Subject: Re: [QUESTION] thread model in Flink makes me confused From: "Wright, Eron" In-Reply-To: Date: Wed, 11 May 2016 16:58:57 -0700 Content-Transfer-Encoding: quoted-printable References: To: dev@flink.apache.org, Jark Wu X-Mailer: Apple Mail (2.3124) X-OriginalArrivalTime: 11 May 2016 23:58:59.0507 (UTC) FILETIME=[15F8C030:01D1ABE1] archived-at: Wed, 11 May 2016 23:59:07 -0000 One option is to use a separate cluster (JobManager + TaskManagers) for = each job. This is fairly straightforward with the YARN support - = "flink run=E2=80=9D can launch a cluster for a job and tear it down = afterwards. Of course this means you must deploy YARN. That doesn=E2=80=99t = necessarily imply HDFS though a Hadoop-compatible filesystem (HCFS) is = needed to support the YARN staging directory.=20 This approach also facilitates richer scheduling and multi-user = scenarios. =20 One downside is the loss of a unified web UI to view all jobs. > On May 11, 2016, at 8:32 AM, Jark Wu = wrote: >=20 >=20 > As I know, Flink uses thread model, that means one TaskManager process = may run many different operator threads from different jobs. So tasks = from different jobs will compete for memory and CPU in the one process. = In the worst case scenario, the bad job will eat most of CPU and memroy = which may lead to OOM, and then the regular job died too. And there's = another problem, tasks from different jobs will print there logs into = the same file(the taskmanager log file). This increases the difficulty = of debugging. >=20 > As I know, Storm will spawn workers for every job. The tasks in one = worker belong to the same job. So I'm confused the purpose or advantages = of Flink design. One more question, is there any tips to solves the = issues above? Or any suggestions to implemention the similar desgin with = Storm ?=20 >=20 > Thank you for any answers in advance! >=20 > Regards, > Jark Wu >=20 >=20 >=20