Likewise, I tried calling but no one was hosting the meeting.
On Fri, Apr 22, 2016 at 10:04 AM, Kevin Klues wrote:
> I tried calling into this last night, but no one was there. Was it
> post-poned again?
>
> On Mon, Apr 18, 2016 at 12:03 PM, Niklas Nielsen wrote:
> > Hi everyone,
> >
> > Per o
ng to get the talks recorded.
>
> On Wed, Mar 16, 2016 at 9:45 AM, haosdent wrote:
>
>> Would it have youtube live link?
>>
>> On Thu, Mar 17, 2016 at 12:38 AM, Ian Downes wrote:
>>
>> > Hello everyone,
>> >
>> > I'd like to call at
Hello everyone,
I'd like to call attention to an event the Compute group at Twitter is
holding at the end of the month where there will be a few
Aurora/Mesos-related talks:
1. David Robinson, one of our SREs, will talk about how our small team
of SREs manages what is possibly the largest Mesos cl
Apologies, but I'm still on the bus in traffic so I expect to be ~10
minutes late.
On Fri, Mar 4, 2016 at 8:23 AM, Ian Downes wrote:
> Please let me know directly if anyone is attending at Twitter as I need to
> advise security.
>
> Ian
>
> On Fri, Mar 4, 2016 at 12:51 AM
Please let me know directly if anyone is attending at Twitter as I need to
advise security.
Ian
On Fri, Mar 4, 2016 at 12:51 AM, wrote:
> Hi Vipin,
>
> We'll share the hangout in the agenda doc (
> https://docs.google.com/document/d/11mlGPZSABItP47J6VX-zB0fAK6Qr1mCIOI7nhlATMqk/edit#)
> and also
Please use this link:
https://plus.google.com/hangouts/_/twitter.com/mesos-cpu
On Fri, Feb 26, 2016 at 10:09 AM, Ian Downes wrote:
> we're a little late to get started, it will become accessible shortly
>
> > On Feb 26, 2016, at 10:03, Kevin Klues wrote:
> >
> > I
we're a little late to get started, it will become accessible shortly
> On Feb 26, 2016, at 10:03, Kevin Klues wrote:
>
> I'm having trouble joining the call. Keeps saying "Requesting to join
> the video call..."
>
>> On Wed, Feb 24, 2016 at 12:12 PM, Niklas Nielsen wrote:
>> Hi all,
>>
>> We
I'm back today so should get to this tomorrow. Sorry for the delay.
Ian
> On Feb 7, 2016, at 14:54, David Forsythe wrote:
>
> Hi,
>
> Would anyone be able to shepherd these two tickets? They're pretty simple:
>
> https://issues.apache.org/jira/browse/MESOS-4502
> https://issues.apache.org/ji
Hello everyone,
I'd like to propose adding the concept of exclusivity to resources. An
exclusive resource is a) not shared with any other task, b) employs
stronger isolation for more predictable performance, and c) is consequently
not oversubscribed (if enabled). In contrast to normal resources, e
>
> TLDR: We want to use a custom network isolator, but there is no way to
> enable the 'network' namespace from within an isolator module.
>
>
> We are working on creating a custom network isolator as a Mesos module.
> However, the way Mesos Slave is setup, there is no way to enable 'network'
> na
This is something we're interested in exploring as well. Can we ensure the
design thinking get circulated to the community early on? I agree there
will be many different requirements and it would be helpful to understand
those from the onset.
Ian
On Tue, Apr 28, 2015 at 5:48 PM, Christos Kozyraki
views.apache.org/r/32123/#comment131258>
Suggest removing default and calling destroy(containerId, false) here.
- Ian Downes
On March 23, 2015, 12:59 a.m., Timothy Chen wrote:
>
> ---
> This is an automatically genera
g/r/33174/#comment131222>
The CPU_CFS_PERIOD doesn't change by the quota does - adding/removing tasks
with CPU resource will change the CFS quota for the container.
- Ian Downes
On April 14, 2015, 1:32 p.m., Steve Ni
129490>
unused?
src/tests/fetcher_tests.cpp
<https://reviews.apache.org/r/32975/#comment129494>
indentation
- Ian Downes
On April 13, 2015, 9:55 a.m., Jim Klucar wrote:
>
> ---
> This is an autom
480/#comment128787>
separate errno string:
s/"'"/"': "/
src/slave/state.cpp
<https://reviews.apache.org/r/31480/#comment128788>
separate errno string:
s/"'"/"': &
swap is enabled."
include/mesos/mesos.proto
<https://reviews.apache.org/r/31915/#comment128780>
Please file a ticket for this.
include/mesos/mesos.proto
<https://reviews.apache.org/r/31915/#comment128781>
Note that neither its type, name nor numeric tag has been change
tests/port_mapping_tests.cpp
<https://reviews.apache.org/r/32664/#comment128746>
Why does it need to be random if we're inside a temporary directory sandbox?
- Ian Downes
On April 1, 2015, 8:45 a.m., Paul Brett wrote:
>
> ---
> On April 2, 2015, 10:24 a.m., Ian Downes wrote:
> > src/linux/perf.cpp, line 188
> > <https://reviews.apache.org/r/32699/diff/1/?file=911392#file911392line188>
> >
> > I thought about this again, and it won't be sufficient for perf: we use
> >
org/r/32956/#comment128711>
s/> >/>>
src/tests/isolator_tests.cpp
<https://reviews.apache.org/r/32956/#comment128718>
Do we need 512 MB? Pull this out to a constant, something more reasonable,
and use again below in the EXPECT
- Ian Downes
On April 7, 2015, 7:
955/#comment128717>
Do you need to reap this process?
- Ian Downes
On April 7, 2015, 7:29 p.m., Chi Zhang wrote:
>
> ---
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.
org/r/32955/#comment128710>
Not yours, but isn't 512 overkill :-) if the limit is 64 then anything >=
64 MB should trigger it? How about actually tying it to the limit, e.g.,
2*limit?
- Ian Downes
On April 7, 2015, 7:29 p.m., C
754/#comment128685>
Please describe the test (see first review in this chain).
src/tests/cgroups_tests.cpp
<https://reviews.apache.org/r/32754/#comment128686>
See first comments in the first review of this chain.
- Ian Downes
On April 1, 2015, 4:14 p.m., Chi
-
>
> (Updated April 1, 2015, 4:13 p.m.)
>
>
> Review request for mesos, Dominic Hamon, Ian Downes, and Jie Yu.
>
>
> Bugs: mesos-2572
> https://issues.apache.org/jira/browse/mesos-2572
>
>
>
.org/r/32757/#comment128701>
Why is the read necessary?
- Ian Downes
On April 1, 2015, 4:18 p.m., Chi Zhang wrote:
>
> ---
> This is an automatically generated e-mail. To reply, visi
755/#comment128687>
Ditto. Comment why we don't need the Megabytes(1).
src/tests/memory_test_helper.cpp
<https://reviews.apache.org/r/32755/#comment128704>
What happens to this test if /tmp is a tmpfs? Do the cache pages get
accounted differently
- Ian Downes
On April
--
>
> (Updated April 1, 2015, 4:17 p.m.)
>
>
> Review request for mesos, Ian Downes and Jie Yu.
>
>
> Bugs: mesos-2572
> https://issues.apache.org/jira/browse/mesos-2572
>
>
> Repository: mesos
>
>
>
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31914/#review79357
---
Ship it!
Ship It!
- Ian Downes
On April 1, 2015, 3:27 p.m., Chi
Description
---
Add os::stat::inode to stout.
Diffs
-
3rdparty/libprocess/3rdparty/stout/include/stout/os/stat.hpp
af940a48b161c194f2efb529b3d589c543b12f61
Diff: https://reviews.apache.org/r/32978/diff/
Testing
---
Thanks,
Ian Downes
/sda0, then devices should be created in /dev
so it would be correct to also prefix /dev/sda0 with the chroot path.
- Ian
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org
ATION
Diff: https://reviews.apache.org/r/31444/diff/
Testing
---
Manual testing only so far. This is harder to automate because we need a
self-contained chroot to execute something in... Suggestions welcome.
Thanks,
Ian Downes
g/r/32657/#comment128443>
Why the change in logic here?
Assuming I understand the intent from the comment, would it be clearer to
simply have this?
```c++
// Return true if all metrics are present.
return (p50(o).isSome() && p90(o).isSome() && ... );
gt;
> (Updated April 6, 2015, 11:45 a.m.)
>
>
> Review request for mesos and Ian Downes.
>
>
> Bugs: mesos-1801
> https://issues.apache.org/jira/browse/mesos-1801
>
>
> Repository: mesos
>
>
> Description
> ---
>
> Environment
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32903/#review79208
---
Ship it!
Ship It!
- Ian Downes
On April 6, 2015, 3:09 p.m
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32898/#review79209
---
Ship it!
Ship It!
- Ian Downes
On April 6, 2015, 3:05 p.m
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32906/#review79206
---
Ship it!
Ship It!
- Ian Downes
On April 6, 2015, 4:03 p.m
911/#comment128406>
getExecutorInfo() will return the ExecutorInfo if the TaskInfo includes it,
otherwise it will construct one (for the command executor), taking the user
from the CommandInfo, if present, otherwise this code will fallback to the user
from the FrameworkInfo.
- Ian Downe
/tests/port_mapping_tests.cpp
<https://reviews.apache.org/r/32898/#comment128098>
The argument doesn't need to be quoted if there's no formatting required?
Regardless, should stay consistent with double quotes used elsewhere?
- Ian Downes
On April 6, 2015, 12:27
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31444/#review77524
---
On April 6, 2015, 11:02 a.m., Ian Downes wrote:
>
> ---
> This
is not a shared mount
> > ```
> > which is fine but not as informative as
> > ```
> > Chroot target needs to be a mount point
> > ```
added
- Ian
---
This is an automatically
src/slave/containerizer/mesos/launch.cpp
2f2d60e2011f60ec711d3b29fd2c157e30c83c34
Diff: https://reviews.apache.org/r/31444/diff/
Testing
---
Manual testing only so far. This is harder to automate because we need a
self-contained chroot to execute something in... Suggestions welcome.
Th
1c9cf3f2ffead37148e4f6a81cefdbb97f679b09
Diff: https://reviews.apache.org/r/32891/diff/
Testing
---
Thanks,
Ian Downes
lt;https://reviews.apache.org/r/32655/#comment127942>
Why the change from std{in,out,err}?
src/tests/port_mapping_tests.cpp
<https://reviews.apache.org/r/32655/#comment127941>
keep the newline?
- Ian Downes
On April 3, 2015, 3:36 p.m., Paul Brett wrote:
>
>
c/tests/port_mapping_tests.cpp
<https://reviews.apache.org/r/32656/#comment127931>
IMHO this is clearer:
```c++
Try parse = JSON::parse<>();
if (parse.isError()) {
// Comment on why we return on empty object when parsing fails
return JSON::Object();
}
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32820/#review78832
---
Ship it!
Ship It!
- Ian Downes
On April 3, 2015, 10:01 a.m
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32694/#review78679
---
Ship it!
Ship It!
- Ian Downes
On April 1, 2015, 12:40 p.m
h is a single process.
What *may* work for perf, but is not clearly documented in the prctl
manpage, is to run the processes in a process group and use -SIGKILL as the
DEATHSIG. Depending on how this was implemented, this might signal the entire
process group?
- Ian Downes
On March 31, 20
queries; do you expect
these to be?
also, the name is too generic ;-)
- Ian Downes
On April 1, 2015, 8:45 a.m., Paul Brett wrote:
>
> ---
> This is an automatically genera
dsheets. Columns are separated by the string specified in SEP.
{noformat}
src/linux/perf.cpp
<https://reviews.apache.org/r/32698/#comment127388>
ditto
- Ian Downes
On March 31, 2015, 1:04 p.m., Jie Yu wrote:
>
> --
tps://reviews.apache.org/r/30546/#comment125872>
okay, so if you want to continue to call __usage even with a failure then
why not:
listener->counter()
.onAny()
- Ian Downes
On March 24, 2015, 5:03 p.m., Chi Zh
tps://reviews.apache.org/r/32454/#comment125870>
kill the extra ;
- Ian Downes
On March 24, 2015, 2:47 p.m., Vinod Kone wrote:
>
> ---
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.
ear down?
src/tests/cgroups_tests.cpp
<https://reviews.apache.org/r/31012/#comment125866>
why keep trying here but not in the parent...?
src/tests/cgroups_tests.cpp
<https://reviews.apache.org/r/31012/#comment125868>
ditto
src/test
do you require this to be unset?
src/tests/slave_recovery_tests.cpp
<https://reviews.apache.org/r/30546/#comment125804>
This path is where...? You should write into the task's sandbox path rather
than the test's
src/tests/slave_recovery_tests.cpp
<https://reviews.apache.org/r/30546/#comme
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/30545/#review77631
---
Ship it!
Ship It!
- Ian Downes
On March 11, 2015, 3:30 p.m
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32452/#review77630
---
Ship it!
Ship It!
- Ian Downes
On March 24, 2015, 12:47 p.m
_SamplePid" --gtest_repeat=100
Thanks,
Ian Downes
s.cpp 16f32267f694ccaae9d10c2629831e2cca23e0c8
Diff: https://reviews.apache.org/r/32420/diff/
Testing
---
./bin/mesos-tests.sh --gtest_filter="PerfTest.ROOT_SamplePid" --gtest_repeat=100
Thanks,
Ian Downes
rg/r/31444/diff/
Testing
---
Manual testing only so far. This is harder to automate because we need a
self-contained chroot to execute something in... Suggestions welcome.
Thanks,
Ian Downes
g/r/32133/#comment124451>
e.g., src/slave/paths.cpp
- Ian Downes
On March 17, 2015, 11:56 a.m., Paul Brett wrote:
>
> ---
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.
--
On March 10, 2015, 4:26 p.m., Cong Wang wrote:
>
> ---
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.apache.org/r/31503/
> -------
>
&
.cpp
<https://reviews.apache.org/r/31915/#comment124439>
Be explicit that mem_anon_bytes is deprecated, otherwise it could be
interpreted as all of this block.
src/slave/containerizer/isolators/cgroups/mem.cpp
<https://reviews.apache.org/r/31915/#comment124441>
if this conditional
truct to contain? According to above we
should have killed=true and no status present?
- Ian Downes
On March 16, 2015, 12:30 p.m., Timothy Chen wrote:
>
> ---
> This is an automatically gen
https://reviews.apache.org/r/32133/#comment124400>
Better would be if waitForFileCreation() returned a Future that was
ready when the path existed. Then you could do AWAIT_READY() and the
(configurable) timeout would be in the caller waiting on the future, not in the
helper.
I
cally generated e-mail. To reply, visit:
https://reviews.apache.org/r/31444/#review74125
-----------
On Feb. 25, 2015, 2:48 p.m., Ian Downes wrote:
>
> ---
>
is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31444/#review74674
---
On Feb. 25, 2015, 2:48 p.m., Ian Downes wrote:
>
> ---
>
we will not affect the caller (added a check for
this in the code).
- Ian
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31444/#review74657
----------
uot;
src/tests/slave_recovery_tests.cpp
<https://reviews.apache.org/r/30546/#comment123768>
This seems racey - how can you be sure that you don't write all 5 GB while
the first slave is running such that when the next slave starts there aren't
any pressure events?
7e72b34c7bf5f0b96a2f62db138972d44e084c8b
src/slave/containerizer/isolators/network/port_mapping.cpp
5227987cdb7b904c2f4bb2bdf5c5d705a435010d
Diff: https://reviews.apache.org/r/31443/diff/
Testing
---
Thanks,
Ian Downes
and Jie Yu.
Repository: mesos
Description
---
Add os::getmode() wrapper.
Diffs (updated)
-
3rdparty/libprocess/3rdparty/stout/include/stout/os/stat.hpp PRE-CREATION
Diff: https://reviews.apache.org/r/31440/diff/
Testing
---
Thanks,
Ian Downes
ws.apache.org/r/31897/diff/
Testing
---
Added two tests to verify the parsing.
Thanks,
Ian Downes
he.org/r/31897/#review75945
---
On March 10, 2015, 10:22 a.m., Ian Downes wrote:
>
> ---
> This is an automatically generated e-mail. To reply, visit:
> https://rev
8a2d445c2edaa70da0e7b50e14ef88b2d9224a16
Diff: https://reviews.apache.org/r/31441/diff/
Testing
---
Thanks,
Ian Downes
---
Thanks,
Ian Downes
and Jie Yu.
Repository: mesos
Description
---
Add os::getrdev() wrapper.
Diffs (updated)
-
3rdparty/libprocess/3rdparty/stout/include/stout/os/stat.hpp PRE-CREATION
Diff: https://reviews.apache.org/r/31438/diff/
Testing
---
Thanks,
Ian Downes
f4b4f519456dc00a8894c7ce154b28a7ab9ce493
src/tests/isolator_tests.cpp f7323965b94543bfda78afc4f60fc677f4900ecd
Diff: https://reviews.apache.org/r/31895/diff/
Testing
---
Thanks,
Ian Downes
://reviews.apache.org/r/31897/diff/
Testing
---
Added two tests to verify the parsing.
Thanks,
Ian Downes
/os.hpp
d28f3f7aaa59eb1ec223b76b5377956df9b58158
3rdparty/libprocess/3rdparty/stout/include/stout/os/stat.hpp PRE-CREATION
Diff: https://reviews.apache.org/r/31894/diff/
Testing
---
Thanks,
Ian Downes
,
Ian Downes
t as original code for this review.
- Ian
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31443/#review74359
-------
On
you're modifying an
existing mount.
- Ian
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31443/#review74116
---
On Feb. 25, 2015
cs, i.e., we already have
"network_enable_socket_statistics_summary" and
"network_enable_socket_statistics_details", so perhaps something like
"cgroups_cpu_enable_pids_and_tids_count"?
- Ian Downes
On
ot@localhost vagrant]# unshare -m
> > [root@localhost vagrant]# mount --make-rslave /
> > [root@localhost vagrant]# cd busybox/
> > [root@localhost busybox]# mount --bind . .
> > [root@localhost busybox]# mount --make-private .
> > [root@localhost busybox]#
rify that works under your
setup?
- Ian
-----------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31444/#review74382
---
On Feb. 25, 2015, 2:48 p.m., Ian Downes wrote:
>
> -
3rdparty/stout/include/stout/os.hpp
> 8a4fda97ee29c185471a69f60803efc193cbe922
>
> Diff: https://reviews.apache.org/r/31441/diff/
>
>
> Testing
> ---
>
>
> Thanks,
>
> Ian Downes
>
>
s/memory_test_helper.cpp
<https://reviews.apache.org/r/31276/#comment121910>
s/Unpected/Unexpected/
- Ian Downes
On Feb. 25, 2015, 1:59 p.m., Chi Zhang wrote:
>
> ---
> This is an automatically ge
1250/#comment121890>
s/Process/Process count/
- Ian Downes
On Feb. 23, 2015, 4:45 p.m., Chi Zhang wrote:
>
> ---
> This is an automatically generated e-mail. To reply, visi
g/r/31505/#comment121047>
why this change? prior code used the eth0 instance variable
src/slave/containerizer/isolators/network/port_mapping.cpp
<https://reviews.apache.org/r/31505/#comment121046>
why this change? prior code used the eth0 instance var
tps://reviews.apache.org/r/31489/#comment120858>
buffer.data()?
3rdparty/libprocess/3rdparty/stout/include/stout/os.hpp
<https://reviews.apache.org/r/31489/#comment120856>
ditto
- Ian Downes
On Feb. 26, 2015, 9:53 a.m., Dominic
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31479/#review74294
---
Ship it!
Ship It!
- Ian Downes
On Feb. 26, 2015, 1:10 a.m
h.cpp
2f2d60e2011f60ec711d3b29fd2c157e30c83c34
Diff: https://reviews.apache.org/r/31444/diff/
Testing
---
Manual testing only so far. This is harder to automate because we need a
self-contained chroot to execute something in... Suggestions welcome.
Thanks,
Ian Downes
Description
---
Add Linux pivot_root() wrapper.
Diffs
-
src/linux/fs.hpp ac8b5f416dae0a9388a3839b6f078abdcd42edae
src/linux/fs.cpp b01d14c3a1b296566b2b17a7f540097bd7cc53dd
Diff: https://reviews.apache.org/r/31442/diff/
Testing
---
Thanks,
Ian Downes
Description
---
Add os::getrdev() wrapper.
Diffs
-
3rdparty/libprocess/3rdparty/stout/include/stout/os.hpp
8a4fda97ee29c185471a69f60803efc193cbe922
Diff: https://reviews.apache.org/r/31438/diff/
Testing
---
Thanks,
Ian Downes
Description
---
Add os::getmode() wrapper.
Diffs
-
3rdparty/libprocess/3rdparty/stout/include/stout/os.hpp
8a4fda97ee29c185471a69f60803efc193cbe922
Diff: https://reviews.apache.org/r/31440/diff/
Testing
---
Thanks,
Ian Downes
Description
---
Accept dummy arguments for fs::mount().
Diffs
-
src/linux/fs.hpp ac8b5f416dae0a9388a3839b6f078abdcd42edae
src/linux/fs.cpp b01d14c3a1b296566b2b17a7f540097bd7cc53dd
Diff: https://reviews.apache.org/r/31443/diff/
Testing
---
Thanks,
Ian Downes
Description
---
Add os::mknod() wrapper.
Diffs
-
3rdparty/libprocess/3rdparty/stout/include/stout/os.hpp
8a4fda97ee29c185471a69f60803efc193cbe922
Diff: https://reviews.apache.org/r/31441/diff/
Testing
---
Thanks,
Ian Downes
Description
---
Add os::chroot() wrapper.
Diffs
-
3rdparty/libprocess/3rdparty/stout/include/stout/os.hpp
8a4fda97ee29c185471a69f60803efc193cbe922
Diff: https://reviews.apache.org/r/31439/diff/
Testing
---
Thanks,
Ian Downes
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31378/#review74054
---
Ship it!
Ship It!
- Ian Downes
On Feb. 25, 2015, 10:37 a.m
res or wait until they're complete and then call cleanup() on each
isolator, i.e., the normal destroy path.
Tim, can you take look a this.
- Ian Downes
On Nov. 21, 2014, 3:20 p.m., Timothy Chen wrote:
>
> ---
>
urpose of the while loop - can't you just block on the last
sleep?
- Ian Downes
On Feb. 20, 2015, 5:12 p.m., Chi Zhang wrote:
>
> ---
> This is an automatically generat
545/#comment119984>
from *the* user
src/linux/cgroups.cpp
<https://reviews.apache.org/r/30545/#comment119985>
indentation
- Ian Downes
On Feb. 22, 2015, 8:43 p.m., Chi Zhang wrote:
>
> ---
> This is an automatically
tps://reviews.apache.org/r/30906/#comment118054>
We'll likely be adding more metrics so what about moving the ctor and dtor
definitions to the cpp file, this matches the style in the port_mapping
isolator too.
- Ian Downes
On Feb. 11, 2015, 5:34 p.m., Vinod
1 - 100 of 1000 matches
Mail list logo
