[jira] [Created] (YARN-810) Support CGroup ceiling enforcement on CPU

["Chris Riccomini (JIRA)" <ji...@apache.org>]

Chris Riccomini created YARN-810:
------------------------------------

             Summary: Support CGroup ceiling enforcement on CPU
                 Key: YARN-810
                 URL: https://issues.apache.org/jira/browse/YARN-810
             Project: Hadoop YARN
          Issue Type: Bug
          Components: nodemanager
    Affects Versions: 2.1.0-beta, 2.0.5-alpha
            Reporter: Chris Riccomini


Problem statement:

YARN currently lets you define an NM's pcore count, and a pcore:vcore ratio. Containers are then allowed to request vcores between the minimum and maximum defined in the yarn-site.xml.

In the case where a single-threaded container requests 1 vcore, with a pcore:vcore ratio of 1:4, the container is still allowed to use up to 100% of the core it's using, provided that no other container is also using it. This happens, even though the only guarantee that YARN/CGroups is making is that the container will get "at least" 1/4th of the core.

If a second container then comes along, the second container can take resources from the first, provided that the first container is still getting at least its fair share (1/4th).

There are certain cases where this is desirable. There are also certain cases where it might be desirable to have a hard limit on CPU usage, and not allow the process to go above the specified resource requirement, even if it's available.

Here's an RFC that describes the problem in more detail:

http://lwn.net/Articles/336127/

Solution:

As it happens, when CFS is used in combination with CGroups, you can enforce a ceiling using two files in cgroups:

{noformat}
cpu.cfs_quota_us
cpu.cfs_period_us
{noformat}

The usage of these two files is documented in more detail here:

https://access.redhat.com/site/documentation/en-US/Red_Hat_Enterprise_Linux/6/html/Resource_Management_Guide/sec-cpu.html

Testing:

I have tested YARN CGroups using the 2.0.5-alpha implementation. By default, it behaves as described above (it is a soft cap, and allows containers to use more than they asked for). I then tested CFS CPU quotas manually with YARN.

First, you can see that CFS is in use in the CGroup, based on the file names:

{noformat}
    [criccomi@eat1-qa464 ~]$ sudo -u app ls -l /cgroup/cpu/hadoop-yarn/
    total 0
    -r--r--r-- 1 app app 0 Jun 13 16:46 cgroup.procs
    drwxr-xr-x 2 app app 0 Jun 13 17:08 container_1371141151815_0004_01_000002
    -rw-r--r-- 1 app app 0 Jun 13 16:46 cpu.cfs_period_us
    -rw-r--r-- 1 app app 0 Jun 13 16:46 cpu.cfs_quota_us
    -rw-r--r-- 1 app app 0 Jun 13 16:46 cpu.rt_period_us
    -rw-r--r-- 1 app app 0 Jun 13 16:46 cpu.rt_runtime_us
    -rw-r--r-- 1 app app 0 Jun 13 16:46 cpu.shares
    -r--r--r-- 1 app app 0 Jun 13 16:46 cpu.stat
    -rw-r--r-- 1 app app 0 Jun 13 16:46 notify_on_release
    -rw-r--r-- 1 app app 0 Jun 13 16:46 tasks
    [criccomi@eat1-qa464 ~]$ sudo -u app cat
    /cgroup/cpu/hadoop-yarn/cpu.cfs_period_us
    100000
    [criccomi@eat1-qa464 ~]$ sudo -u app cat
    /cgroup/cpu/hadoop-yarn/cpu.cfs_quota_us
    -1
{noformat}

Oddly, it appears that the cfs_period_us is set to .1s, not 1s.

We can place processes in hard limits. I have process 4370
running YARN container container_1371141151815_0003_01_000003 on a host. By
default, it's running at ~300% cpu usage.

{noformat}
                                            CPU
    4370 criccomi  20   0 1157m 551m  14m S 240.3  0.8  87:10.91 ...
{noformat}

When I set the CFS quote:

{noformat}
    echo 1000 > /cgroup/cpu/hadoop-yarn/container_1371141151815_0003_01_000003/cpu.cfs_quota_us
                                             CPU
    4370 criccomi  20   0 1157m 563m  14m S  1.0  0.8  90:08.39 ...
{noformat}

It drops to 1% usage, and you can see the box has room to spare:

{noformat}
    Cpu(s):  2.4%us,  1.0%sy,  0.0%ni, 92.2%id,  4.2%wa,  0.0%hi,  0.1%si,
0.0%st
{noformat}

Turning the quota back to -1:

{noformat}
    echo -1 >
/cgroup/cpu/hadoop-yarn/container_1371141151815_0003_01_000003/cpu.cfs_quota_us
{noformat}

Burns the cores again:

{noformat}
    Cpu(s): 11.1%us,  1.7%sy,  0.0%ni, 83.9%id,  3.1%wa,  0.0%hi,  0.2%si, 0.0%st
                                            CPU
    4370 criccomi  20   0 1157m 563m  14m S 253.9  0.8  89:32.31 ...
{noformat}

On my dev box, I was testing CGroups by running a python process eight
times, to burn through all the cores, since it was doing as described above
(giving extra CPU to the process, even with a cpu.shares limit). Toggling
the cfs_quota_us seems to enforce a hard limit.

Implementation:

What do you guys think about introducing a variable to YarnConfiguration:

bq. yarn.nodemanager.linux-container.executor.cgroups.cpu-ceiling-enforcement

The default would be false. Setting to true, would cause YARN's LCE to set:

{noformat}
cpu.cfs_quota_us=(container-request-vcores/nm-vcore-to-pcore-ratio) * 1000000
cpu.cfs_period_us=1000000
{noformat}

For example, if a container asks for 2 vcores, and the vcore:pcore ratio is 4, you'd get:

{noformat}
cpu.cfs_quota_us=(2/4) * 1000000 = 500000
cpu.cfs_period_us=1000000
{noformat}

This would cause CFS to cap the process at 50% of clock cycles.

What do you guys think?

1. Does this seem like a reasonable request? We have some use-cases for it.
2. It's unclear to me how cpu.shares interacts with cpu.cfs_*. I think the ceiling is hard, no matter what shares is set to. I assume shares only comes into play if the CFS quota has not been reached, and the process begins competing with others for CPU resources.
3. Should this be an LCE config (yarn.nodemanager.linux-container-executor), or should it be a generic scheduler config (yarn.scheduler.enforce-ceiling-vcores).


--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira