> On May 26, 2015, 9:54 p.m., Chi Zhang wrote:
> > src/slave/containerizer/isolators/network/port_mapping.cpp, lines 1843-1850
> > <https://reviews.apache.org/r/31505/diff/8/?file=972152#file972152line1843>
> >
> >     this could also happen if we are recovering a container not using this 
> > feature right?

Probably. It hard to mention all the cases in comments.


- Cong


-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31505/#review85268
-----------------------------------------------------------


On May 26, 2015, 8:41 p.m., Cong Wang wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.apache.org/r/31505/
> -----------------------------------------------------------
> 
> (Updated May 26, 2015, 8:41 p.m.)
> 
> 
> Review request for mesos, Chi Zhang, Ian Downes, and Jie Yu.
> 
> 
> Bugs: MESOS-2422
>     https://issues.apache.org/jira/browse/MESOS-2422
> 
> 
> Repository: mesos
> 
> 
> Description
> -------
> 
> Currently we do nothing on the host egress side. By default, kernel uses its 
> own hash function to classify the packets to different TX queues (if the 
> hardware interface supports multiqueue). So packets coming out of different 
> containers could end up queueing in the same TX queue, in this case we saw 
> buffer bloat on some TX queue caused packet drops.
> 
> We need to isolation the egress traffic so that containers will not have 
> interference with each other. The number of hardware TX queues is limited by 
> hardware interface, usually not enough to map our container in 1:1 way, 
> therefore we need some software solution. We choose fq_codel and use tc 
> filters to classify packets coming out of different containers to different 
> fq_codel flows, and the codel algorithm on each flow could also help us to 
> reduce the buffer bloat. Note when the packets leave fq_codel, they still 
> share the physical TX queue(s), this is however (almost) beyond what we can 
> control, we have to rely on the kernel behavior.
> 
> TODO: get some performance numbers
> 
> 
> Diffs
> -----
> 
>   src/linux/routing/filter/basic.cpp 755be7de5c43c2f3b336af6cb47af9c97a21218c 
>   src/linux/routing/filter/filter.hpp 
> 024582cf8274da2e5bcccc4ebd00fcf83d6930e2 
>   src/linux/routing/filter/icmp.cpp 60703e727ecab9557911ab0562773771db51db90 
>   src/linux/routing/filter/ip.hpp 62bb5f89d35fc9622fca303aa01a789fcfbf2f76 
>   src/linux/routing/filter/ip.cpp 0d25e2d4f0ac4c3f151ad40e796dbdbc54dba9fa 
>   src/slave/containerizer/isolators/network/port_mapping.hpp 
> c72fb47f60f40cda8d84a10497b9133f83cf018e 
>   src/slave/containerizer/isolators/network/port_mapping.cpp 
> 49e983edab598e2ac487bb488fdd12840a9e7dfc 
> 
> Diff: https://reviews.apache.org/r/31505/diff/
> 
> 
> Testing
> -------
> 
> Manually start two mesos containers with netperf running side.
> 
> 
> Thanks,
> 
> Cong Wang
> 
>

Reply via email to