Re: Doubt on implementation of collecting container resource usage

htop is an extension to OS, or htop is too high to use for Mesos, IMO. 2015-12-11 22:52 GMT+08:00 sujz.buaa : > Hi, all: > > I find that periodical collection of resource usage is implemented by > reading '/proc/pid/stat' file once per second, instead of running htop > command

how to use agent config: docker_mesos_image better? or is it deprecated?

Hi, there, I got this config docker_mesos_image=VALUE with the following description: The docker image used to launch this mesos slave instance. If an image is specified, the docker containerizer assumes the slave is running in a docker container, and launches executors with docker containers in

Re: Spark Job Submitting on Mesos Cluster

At the same time, make sure SPARK_USER is the real one living on slave before execute your spark program. 2015-09-14 16:29 GMT+08:00 SLiZn Liu : > I found the --no-switch_user flag in mesos slave configuration. Will give > it a try. Thanks Tim, and haosdent ! > ​ > > On

Re: service discovery in Mesos on CoreOS

? It would still run in a separate container. *From:* zhou weitao [mailto:zhouwtl...@gmail.com] *Sent:* Monday, June 29, 2015 10:51 PM *To:* user@mesos.apache.org *Subject:* Re: service discovery in Mesos on CoreOS 2015-06-30 6:23 GMT+08:00 Andras Kerekes andras.kere...@ishisystems.com

Re: Introducing the ceph-mesos framework

I got a short talk with Zhongyue at the 2nd Beijing MUG meetup. Any ideas on data transfer network among Ceph nodes? If we try to involve that into Mesos cluster network resource also? 2015-06-29 6:43 GMT+08:00 Zhongyue Luo zhongyue@gmail.com: About the Ceph binary, this framework pulls a

Re: service discovery in Mesos on CoreOS

2015-06-30 6:23 GMT+08:00 Andras Kerekes andras.kere...@ishisystems.com: Hi, Is there a preferred way to do service discovery in Mesos via mesos-dns running on CoreOS? I’m trying to implement a simple app which consists of two docker containers and one of them (A) depends on the other (B).

Re: oom kills lead up to cpu lockup

Thanks for your share. 2015-06-26 4:40 GMT+08:00 Jord Sonneveld j...@moz.com: Upgrading kernel to 3.19.0-21-generic seems to have resolved this. On Wed, Jun 24, 2015 at 12:06 PM, Jord Sonneveld j...@moz.com wrote: Could it be:

Re: git / chronos-marathon integration

And our team is do version control by the docker tag as you said. But you'd better to keep an eye on the disk resource taken by the increasing docker images. 2015-06-24 21:04 GMT+08:00 haosdent haosd...@gmail.com: docker have tag for images. I think you could use it to do version control on

Re: Resource modelling questions

2015-06-17 20:01 GMT+08:00 Alex Rukletsov a...@mesosphere.com: Brian, these are very good and nicely written questions, let me try to ask them. Mesos built-in allocator does the bookkeeping based on the declared resource consumption and not actual (you call it measured). This means the

Re: slave work_dir filling up

BTW, we also configured spark spark.shuffle.consolidateFiles=true to optimize it. 2015-06-10 8:16 GMT+08:00 Jeff Schroeder jeffschroe...@computer.org: http://mesos.apache.org/documentation/latest/configuration/ http://mesos.apache.org/documentation/latest/configuration/#slave-options

Re: Cluster autoscaling in Spark+Mesos ?

Awesome idea, Alex. I am thinking the similar thing also when I read the volatility feedback part of the book Out of Control. 2015-06-06 10:24 GMT+08:00 Alex Gaudio adgau...@gmail.com: Thanks James! I'd love to talk with you further if you have any interesting or specific problems an

Re: How to count *staged task* in mesos?

Related issue I searched on Jira: https://issues.apache.org/jira/browse/MESOS-1332?jql=project%20%3D%20MESOS%20AND%20text%20~%20task_starting weitao zhou @DataMan 2015-06-05 16:38 GMT+08:00 zhou weitao zhouwtl...@gmail.com: Answer my own question. Under version 0.22, the metrics about staged

Re: How to count *staged task* in mesos?

need the consistent state names between frontend and backend. weitao zhou @DataMan 2015-06-05 9:49 GMT+08:00 zhou weitao zhouwtl...@gmail.com: HI, jiansheng, I prefer it is my misunderstanding on staged_task instead bug, so I didn't trace logs. :-) weitao @DataMan 2015-06-04 20:58 GMT

Re: How to count *staged task* in mesos?

and depending software info. 1、How did you operation happened for this. 2、Could you provide some logs? Thanks. 2015-06-04 20:52 GMT+08:00 zhou weitao zhouwtl...@gmail.com: HI, Can anybody give me a hand about the definition of amount of *staged task* at left sidebar of mesos-master web

Re: [DISCUSS] Renaming Mesos Slave

+1 master/slave, no change needed. 2015-06-05 0:10 GMT+08:00 Ankur Chauhan an...@malloc64.com: -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 +1 master/slave James made some very good points and there is no technical reason for wasting time on this. On 04/06/2015 08:45, James Vanns

Re: /state.json /sumary-state /slaves /tasks.json endpoints

I am often using /state.json by the command 'curl -s IP:5050/state.json | python -m json.tool | grep sth' or 'curl -s IP:5050/state.json | python -m json.tool | less' About if adequate, I think more is better of course, BTW, we need render it better on WEB-UI. Some real-time report chart is sexy

How to count *staged task* in mesos?

HI, Can anybody give me a hand about the definition of amount of *staged task* at left sidebar of mesos-master web-ui? In the mesos-master web-ui, I saw that staged_task=43 and started_task=0 at the left sidebar, while the right content is showing that there are about 100 active tasks.

Re: EXECUTOR_SIGNAL_ESCALATION_TIMEOUT vs EXECUTOR_SHUTDOWN_GRACE_PERIOD vs docker_stop_timeout

+1, I'd like to know that also. 2015-06-01 23:36 GMT+08:00 Maciej Strzelecki maciej.strzele...@crealytics.com: Hi, EXECUTOR_SIGNAL_ESCALATION_TIMEOUT is set to 3 seconds, hard-coded. EXECUTOR_SHUTDOWN_GRACE_PERIOD has a default of 5, and can be configured docker_stop_timeout -