mesos-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Chi Zhang" <chzhc...@gmail.com>
Subject Re: Review Request 31505: Add flow classifiers for fq_codel on egress
Date Tue, 02 Jun 2015 00:57:58 GMT

-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31505/#review86133
-----------------------------------------------------------


Cong, is this the patch the requires code from 3.2.26 for the first time? If so, should we
add a compile-time flag to config.ac? That way Paul can safely back off the code for the "stat
string conversion" from the other patch you commented on.

- Chi Zhang


On June 1, 2015, 10:45 p.m., Cong Wang wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.apache.org/r/31505/
> -----------------------------------------------------------
> 
> (Updated June 1, 2015, 10:45 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 4ce8acb7040f2ed8ec3834dd7702a20f5316c20f 
>   src/linux/routing/filter/filter.hpp aaca57fbe80e3ffa3dd2c2bbed93849013b7a382 
>   src/linux/routing/filter/icmp.cpp 76877fb94a1c1e79133b8975419d2ea7d0300650 
>   src/linux/routing/filter/ip.hpp 9645f9488938c55fec253b36d9fa30eae72a8ca2 
>   src/linux/routing/filter/ip.cpp 0f3b856bd04f6a881e35452a24399715cd8a174f 
>   src/slave/containerizer/isolators/network/port_mapping.hpp 6579286b779882bec493a8e0f10486adc316dc6e

>   src/slave/containerizer/isolators/network/port_mapping.cpp 843e52d6f9923d0ee0a0297cd5c464b8b72f5de3

> 
> Diff: https://reviews.apache.org/r/31505/diff/
> 
> 
> Testing
> -------
> 
> Manually start two mesos containers with netperf running side.
> 
> 
> Thanks,
> 
> Cong Wang
> 
>


Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message