You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@mesos.apache.org by Till Toenshoff <to...@me.com> on 2018/05/19 00:05:59 UTC
Review Request 67228: Added allocator benchmark test for various
simulations.
-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/67228/
-----------------------------------------------------------
Review request for mesos, Benjamin Mahler, Greg Mann, Kapil Arya, and Vinod Kone.
Repository: mesos
Description
-------
This benchmark measures the performannce of the DRF allocator.
* Accept rate (`min_accept_rate`, `max_accept_rate`, and
`accept_rate_divisor`): Each framework is initialized with a given
offer accept-rate. This rate determines the number of offers
accepted out of the total received.
The first framework is launched with `max_accept_rate`. Each
subsequent framework is launched with an accept rate of
(previous framework's accept-rate / `accept_rate_divisor`). This
rate will never be below `min_accept_rate`.
For example, with a `max_accept_rate` of 1 and `accept_rate_divisor`
of 2, the framework accept rates will be 1, 0.5, 0.25, 0.125, and
so on.
* Terminating condition(s): the benchmark stops if any of the
following condition is met:
* Number of offers generated reaches `max_offers`.
* Number of total tasks launched reaches `max_tasks`.
* Any single framework launches `max_framework_tasks` tasks.
* Offer decline timeout (`decline_timeout` and
`partial_decline_timeout`): When declining an entire offer, the
offer-filter timeout is set to `decline_timeout` for a given slave.
If an offer is partially accepted, the offer-filter timeout is set
to `partial_decline_timeout`. If the two timeouts are the same,
framework starvation is observed for framework with the highest
accept rate. To avoid such starvation, one can try setting
`decline_timeout` to be significantly higher (e.g., 10x) than
`partial_decline_timeout`.
Diffs
-----
src/Makefile.am c08ac6e2f5deec4d05f59f71ff6c51382f216708
src/tests/master_drf_benchmarks.cpp PRE-CREATION
Diff: https://reviews.apache.org/r/67228/diff/1/
Testing
-------
WIP - still validating results - WIP
Thanks,
Till Toenshoff
Re: Review Request 67228: Added allocator benchmark test for various
simulations.
Posted by Mesos Reviewbot <re...@mesos.apache.org>.
-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/67228/#review212996
-----------------------------------------------------------
Bad review!
Reviews applied: [67228, 67227, 67226, 66994, 66990, 66984, 66983, 66982, 66981]
Error:
2019-02-20 23:11:34 URL:https://reviews.apache.org/r/66981/diff/raw/ [19817/19817] -> "66981.patch" [1]
error: patch failed: include/mesos/allocator/allocator.hpp:95
error: include/mesos/allocator/allocator.hpp: patch does not apply
error: patch failed: src/master/allocator/mesos/allocator.hpp:59
error: src/master/allocator/mesos/allocator.hpp: patch does not apply
error: patch failed: src/master/allocator/mesos/hierarchical.hpp:104
error: src/master/allocator/mesos/hierarchical.hpp: patch does not apply
error: patch failed: src/master/allocator/mesos/hierarchical.cpp:155
error: src/master/allocator/mesos/hierarchical.cpp: patch does not apply
error: patch failed: src/tests/allocator.hpp:45
error: src/tests/allocator.hpp: patch does not apply
error: patch failed: src/tests/api_tests.cpp:1184
error: src/tests/api_tests.cpp: patch does not apply
error: patch failed: src/tests/master_allocator_tests.cpp:164
error: src/tests/master_allocator_tests.cpp: patch does not apply
error: patch failed: src/tests/master_quota_tests.cpp:424
error: src/tests/master_quota_tests.cpp: patch does not apply
error: patch failed: src/tests/reservation_tests.cpp:603
error: src/tests/reservation_tests.cpp: patch does not apply
error: patch failed: src/tests/resource_offers_tests.cpp:284
error: src/tests/resource_offers_tests.cpp: patch does not apply
error: patch failed: src/tests/slave_recovery_tests.cpp:3761
error: src/tests/slave_recovery_tests.cpp: patch does not apply
- Mesos Reviewbot
On May 18, 2018, 5:05 p.m., Till Toenshoff wrote:
>
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.apache.org/r/67228/
> -----------------------------------------------------------
>
> (Updated May 18, 2018, 5:05 p.m.)
>
>
> Review request for mesos, Benjamin Mahler, Greg Mann, Kapil Arya, and Vinod Kone.
>
>
> Repository: mesos
>
>
> Description
> -------
>
> This benchmark measures the performannce of the DRF allocator.
>
> * Accept rate (`min_accept_rate`, `max_accept_rate`, and
> `accept_rate_divisor`): Each framework is initialized with a given
> offer accept-rate. This rate determines the number of offers
> accepted out of the total received.
> The first framework is launched with `max_accept_rate`. Each
> subsequent framework is launched with an accept rate of
> (previous framework's accept-rate / `accept_rate_divisor`). This
> rate will never be below `min_accept_rate`.
> For example, with a `max_accept_rate` of 1 and `accept_rate_divisor`
> of 2, the framework accept rates will be 1, 0.5, 0.25, 0.125, and
> so on.
>
>
> * Terminating condition(s): the benchmark stops if any of the
> following condition is met:
> * Number of offers generated reaches `max_offers`.
> * Number of total tasks launched reaches `max_tasks`.
> * Any single framework launches `max_framework_tasks` tasks.
>
>
> * Offer decline timeout (`decline_timeout` and
> `partial_decline_timeout`): When declining an entire offer, the
> offer-filter timeout is set to `decline_timeout` for a given slave.
> If an offer is partially accepted, the offer-filter timeout is set
> to `partial_decline_timeout`. If the two timeouts are the same,
> framework starvation is observed for framework with the highest
> accept rate. To avoid such starvation, one can try setting
> `decline_timeout` to be significantly higher (e.g., 10x) than
> `partial_decline_timeout`.
>
>
> Diffs
> -----
>
> src/Makefile.am c08ac6e2f5deec4d05f59f71ff6c51382f216708
> src/tests/master_drf_benchmarks.cpp PRE-CREATION
>
>
> Diff: https://reviews.apache.org/r/67228/diff/1/
>
>
> Testing
> -------
>
> WIP - still validating results - WIP
>
>
> Thanks,
>
> Till Toenshoff
>
>
Re: Review Request 67228: Added allocator benchmark test for various
simulations.
Posted by Mesos Reviewbot Windows <re...@mesos.apache.org>.
-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/67228/#review203470
-----------------------------------------------------------
PASS: Mesos patch 67228 was successfully built and tested.
Reviews applied: `['66981', '66982', '66983', '66984', '66990', '66994', '67226', '67227', '67228']`
All the build artifacts available at: http://dcos-win.westus.cloudapp.azure.com/mesos-build/review/67228
- Mesos Reviewbot Windows
On May 19, 2018, 12:05 a.m., Till Toenshoff wrote:
>
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.apache.org/r/67228/
> -----------------------------------------------------------
>
> (Updated May 19, 2018, 12:05 a.m.)
>
>
> Review request for mesos, Benjamin Mahler, Greg Mann, Kapil Arya, and Vinod Kone.
>
>
> Repository: mesos
>
>
> Description
> -------
>
> This benchmark measures the performannce of the DRF allocator.
>
> * Accept rate (`min_accept_rate`, `max_accept_rate`, and
> `accept_rate_divisor`): Each framework is initialized with a given
> offer accept-rate. This rate determines the number of offers
> accepted out of the total received.
> The first framework is launched with `max_accept_rate`. Each
> subsequent framework is launched with an accept rate of
> (previous framework's accept-rate / `accept_rate_divisor`). This
> rate will never be below `min_accept_rate`.
> For example, with a `max_accept_rate` of 1 and `accept_rate_divisor`
> of 2, the framework accept rates will be 1, 0.5, 0.25, 0.125, and
> so on.
>
>
> * Terminating condition(s): the benchmark stops if any of the
> following condition is met:
> * Number of offers generated reaches `max_offers`.
> * Number of total tasks launched reaches `max_tasks`.
> * Any single framework launches `max_framework_tasks` tasks.
>
>
> * Offer decline timeout (`decline_timeout` and
> `partial_decline_timeout`): When declining an entire offer, the
> offer-filter timeout is set to `decline_timeout` for a given slave.
> If an offer is partially accepted, the offer-filter timeout is set
> to `partial_decline_timeout`. If the two timeouts are the same,
> framework starvation is observed for framework with the highest
> accept rate. To avoid such starvation, one can try setting
> `decline_timeout` to be significantly higher (e.g., 10x) than
> `partial_decline_timeout`.
>
>
> Diffs
> -----
>
> src/Makefile.am c08ac6e2f5deec4d05f59f71ff6c51382f216708
> src/tests/master_drf_benchmarks.cpp PRE-CREATION
>
>
> Diff: https://reviews.apache.org/r/67228/diff/1/
>
>
> Testing
> -------
>
> WIP - still validating results - WIP
>
>
> Thanks,
>
> Till Toenshoff
>
>
Re: Review Request 67228: Added allocator benchmark test for various
simulations.
Posted by Greg Mann <gr...@mesosphere.io>.
-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/67228/#review203596
-----------------------------------------------------------
src/tests/master_drf_benchmarks.cpp
Lines 60 (patched)
<https://reviews.apache.org/r/67228/#comment285883>
s/performannce/performance/
- Greg Mann
On May 19, 2018, 12:05 a.m., Till Toenshoff wrote:
>
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.apache.org/r/67228/
> -----------------------------------------------------------
>
> (Updated May 19, 2018, 12:05 a.m.)
>
>
> Review request for mesos, Benjamin Mahler, Greg Mann, Kapil Arya, and Vinod Kone.
>
>
> Repository: mesos
>
>
> Description
> -------
>
> This benchmark measures the performannce of the DRF allocator.
>
> * Accept rate (`min_accept_rate`, `max_accept_rate`, and
> `accept_rate_divisor`): Each framework is initialized with a given
> offer accept-rate. This rate determines the number of offers
> accepted out of the total received.
> The first framework is launched with `max_accept_rate`. Each
> subsequent framework is launched with an accept rate of
> (previous framework's accept-rate / `accept_rate_divisor`). This
> rate will never be below `min_accept_rate`.
> For example, with a `max_accept_rate` of 1 and `accept_rate_divisor`
> of 2, the framework accept rates will be 1, 0.5, 0.25, 0.125, and
> so on.
>
>
> * Terminating condition(s): the benchmark stops if any of the
> following condition is met:
> * Number of offers generated reaches `max_offers`.
> * Number of total tasks launched reaches `max_tasks`.
> * Any single framework launches `max_framework_tasks` tasks.
>
>
> * Offer decline timeout (`decline_timeout` and
> `partial_decline_timeout`): When declining an entire offer, the
> offer-filter timeout is set to `decline_timeout` for a given slave.
> If an offer is partially accepted, the offer-filter timeout is set
> to `partial_decline_timeout`. If the two timeouts are the same,
> framework starvation is observed for framework with the highest
> accept rate. To avoid such starvation, one can try setting
> `decline_timeout` to be significantly higher (e.g., 10x) than
> `partial_decline_timeout`.
>
>
> Diffs
> -----
>
> src/Makefile.am c08ac6e2f5deec4d05f59f71ff6c51382f216708
> src/tests/master_drf_benchmarks.cpp PRE-CREATION
>
>
> Diff: https://reviews.apache.org/r/67228/diff/1/
>
>
> Testing
> -------
>
> WIP - still validating results - WIP
>
>
> Thanks,
>
> Till Toenshoff
>
>