[
https://issues.apache.org/jira/browse/MESOS-3156?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
haosdent reassigned MESOS-3156:
-------------------------------
Assignee: haosdent
> Inconsistency between mesos master UI and mesos slave /metrics/snapshot
> -----------------------------------------------------------------------
>
> Key: MESOS-3156
> URL: https://issues.apache.org/jira/browse/MESOS-3156
> Project: Mesos
> Issue Type: Bug
> Components: master, slave, statistics, webui
> Affects Versions: 0.22.1
> Environment: Test environment runs on vagrant
> Master: Centos 7 + mesos 0.22.1 + marathon 0.9.0 = 1 vcpu + 1gb ram
> Slave: Centos 7 + mesos 0.22.1 = 3vcpus + 2048mb
> (1 master + 1 slave)
> Reporter: Sebastian Otaegui
> Assignee: haosdent
>
> We recently began doing some tests with kibana to graph some of the stats of
> the slaves and the masters.
> We found something pretty odd:
> Test case:
> In my example my slave has 1840 mb free, of which mesos reserves 920mb for
> tasks.
> 1. create N (in my case 14) marathon tasks with the following configuration
> {noformat}
> command: while true; do sleep 1 ; echo "heloo"; done
> mem: 64mb
> cpu: 0.1
> {noformat}
> 2. check the mesos master web UI
> {noformat}
> Total 3 920 MB
> Used 1.4 896 MB
> {noformat}
> 3. check the <slave host>:5051/metrics/snapshot
> {noformat}
> "slave/mem_total":920,
> "slave/mem_used”:1344
> {noformat}
> Is this correct? I discussed this issue on the DCOS community slack channel
> with Adam and he told me that the correct numbers are in the #3 he explained
> that for each task, there are about 32mb + 0.1 cpu that is assigned to a
> default executor.
> I also changed the slave to enable cgroups_limit_swap:
> {noformat}
> /etc/mesos-slave/
> ├── attributes
> ├── cgroups_limit_swap
> ├── containerizers
> ├── executor_registration_timeout
> ├── hostname
> ├── isolation
> ├── resources
> └── work_dir
> {noformat}
> {noformat}
> cat /etc/mesos-slave/cgroups_limit_swap
> true
> {noformat}
> {noformat}
> ps ax | grep slave
> 26810 ? Ssl 0:02 /usr/sbin/mesos-slave
> --master=zk://172.41.5.11:2181/mesos --ip=172.41.6.11
> --cgroups_limit_swap=true --containerizers=docker,mesos
> --executor_registration_timeout=30mins --hostname=172.41.6.11
> --isolation=cgroups/cpu,cgroups/mem --work_dir=/tmp/mesos
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
