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
streaming live but are working to get the talks recorded.
>
> On Wed, Mar 16, 2016 at 9:45 AM, haosdent <haosd...@gmail.com> wrote:
>
>> Would it have youtube live link?
>>
>> On Thu, Mar 17, 2016 at 12:38 AM, Ian Downes <ian.dow...@gmail.com> wrote:
>>
>
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
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 <idow...@twitter.com> wrote:
> Please let me know directly if anyone is attending at Twitter as I need to
> advise security.
>
> Ian
>
> On Fri,
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 (
>
Please use this link:
https://plus.google.com/hangouts/_/twitter.com/mesos-cpu
On Fri, Feb 26, 2016 at 10:09 AM, Ian Downes <idow...@twitter.com> wrote:
> we're a little late to get started, it will become accessible shortly
>
> > On Feb 26, 2016, at 10:03, Kevin Klues <klu
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
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
>
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,
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'
namespace
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
/#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 generated e-mail. To reply, visit:
https
/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 Niemitz wrote
https://reviews.apache.org/r/32975/#comment129494
indentation
- Ian Downes
On April 13, 2015, 9:55 a.m., Jim Klucar wrote:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32975
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
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 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
---
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
/memory_test_helper.cpp
https://reviews.apache.org/r/32756/#comment128695
Write the memory buffer with different values to ensure the compiler cannot
optimize away this block.
src/tests/memory_test_helper.cpp
https://reviews.apache.org/r/32756/#comment128694
TODO on a new line.
- Ian Downes
/#comment128682
Does the test fixture ensure this process is killed?
src/tests/cgroups_tests.cpp
https://reviews.apache.org/r/31012/#comment128681
No need for a named variable:
```cpp
EXPECT_LT(statistics(rss) - defaultAllocation.bytes(), Megabytes(1));
```
- Ian Downes
/#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 Zhang wrote
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, visit:
https://reviews.apache.org/r/32757
/#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 1, 2015, 4:15 p.m., Chi
/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., Chi Zhang wrote
/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, 7:30 p.m., Chi Zhang 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
perf with a child sleep process to control the sample
if we're inside a temporary directory sandbox?
- Ian Downes
On April 1, 2015, 8:45 a.m., Paul Brett wrote:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32664
/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 changed.
- Ian Downes
On April 1, 2015, 3:28 p.m., Chi Zhang
/#comment128787
separate errno string:
s/'/': /
src/slave/state.cpp
https://reviews.apache.org/r/31480/#comment128788
separate errno string:
s/'/': /
- Ian Downes
On Feb. 26, 2015, 10:54 a.m., Timothy Chen wrote
, 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 variables are case sensitive
Diffs
-
src/deploy/mesos-master-env.sh.template
/#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 Downes
---
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/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/32906/#review79206
---
Ship it!
Ship It!
- Ian Downes
On April 6, 2015, 4:03 p.m
1c9cf3f2ffead37148e4f6a81cefdbb97f679b09
Diff: https://reviews.apache.org/r/32891/diff/
Testing
---
Thanks,
Ian Downes
.
Thanks,
Ian Downes
/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 p.m., Paul Brett wrote
.
- Ian
---
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 an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31444/#review76909
---
On April 6, 2015, 11:02 a.m., Ian Downes wrote
---
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
IMHO this is clearer:
```c++
TryJSON::Object parse = JSON::parse();
if (parse.isError()) {
// Comment on why we return on empty object when parsing fails
return JSON::Object();
}
return parse.get();
```
- Ian Downes
On April 3, 2015, 3:36 p.m., Paul Brett
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:
---
This is an automatically
---
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
.
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, 2015, 1:14 p.m., Jie Yu wrote
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:
---
This is an automatically generated
generic ;-)
- Ian Downes
On April 1, 2015, 8:45 a.m., Paul Brett wrote:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32660
://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.apache.org/r/32454
://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/#comment125805
overwrite a 512 MB file repeatedly
- Ian Downes
On March 18, 2015
://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 Zhang wrote
--gtest_repeat=100
Thanks,
Ian Downes
---
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
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
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 could imagine this would be generally useful; consider adding this to
stout?
- Ian Downes
On March 16, 2015, 4:28 p.m., Paul Brett wrote
present?
- Ian Downes
On March 16, 2015, 12:30 p.m., Timothy Chen wrote:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/32123
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 on limitSwap?
- Ian Downes
On March 10, 2015, 4:55 p.m., Chi
:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31503/
---
(Updated March 10, 2015, 4:26 p.m.)
Review request for mesos, Chi Zhang, Ian Downes, and Jie Yu.
Bugs: MESOS-2422
https
/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
/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.apache.org/r/32133
---
On Feb. 25, 2015, 2:48 p.m., Ian Downes wrote:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31444
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
7e72b34c7bf5f0b96a2f62db138972d44e084c8b
src/slave/containerizer/isolators/network/port_mapping.cpp
5227987cdb7b904c2f4bb2bdf5c5d705a435010d
Diff: https://reviews.apache.org/r/31443/diff/
Testing
---
Thanks,
Ian Downes
- 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?
You should also verify there's enough disk in the offer... and set the disk
resource?
- Ian Downes
On March 11, 2015, 3:32 p.m
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31444/#review74657
---
On Feb. 25, 2015, 2:48 p.m., Ian Downes wrote
---
This 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
/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
---
Thanks,
Ian Downes
8a2d445c2edaa70da0e7b50e14ef88b2d9224a16
Diff: https://reviews.apache.org/r/31441/diff/
Testing
---
Thanks,
Ian Downes
://reviews.apache.org/r/31897/diff/
Testing
---
Added two tests to verify the parsing.
Thanks,
Ian Downes
f4b4f519456dc00a8894c7ce154b28a7ab9ce493
src/tests/isolator_tests.cpp f7323965b94543bfda78afc4f60fc677f4900ecd
Diff: https://reviews.apache.org/r/31895/diff/
Testing
---
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
endif
- Ian
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31897/#review75945
---
On March 10, 2015, 10:22 a.m., Ian Downes wrote
/31897/diff/
Testing
---
Added two tests to verify the parsing.
Thanks,
Ian Downes
. To reply, visit:
https://reviews.apache.org/r/31443/#review74116
---
On Feb. 25, 2015, 2:31 p.m., Ian Downes wrote:
---
This is an automatically generated e-mail. To reply, visit
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31443/#review74359
---
On Feb. 25, 2015, 2:31 p.m., Ian Downes wrote
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 March 3, 2015, 5:47 p.m., Chi Zhang wrote
. .
[root@localhost busybox]# mount --make-private .
[root@localhost busybox]# pivot_root . mnt/
pivot_root: failed to change root from `.' to `mnt/': Device or
resource busy
```
Ian Downes wrote:
The first part works but doesn't enable propagation of mounts from
/Process count/
- Ian Downes
On Feb. 23, 2015, 4:45 p.m., Chi Zhang wrote:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31250
/#comment121910
s/Unpected/Unexpected/
- Ian Downes
On Feb. 25, 2015, 1:59 p.m., Chi Zhang wrote:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31276
:)
added a test
- Ian
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31441/#review74119
---
On Feb. 25, 2015, 2:31 p.m., Ian Downes wrote
?
- 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
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 variable
- Ian Downes
On Feb. 26, 2015, 3:15 p.m., Cong Wang wrote
---
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
://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 Hamon wrote
---
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
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
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
---
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 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
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:
---
This is an automatically generated e
/#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 generated e-mail. To reply
sleep?
- Ian Downes
On Feb. 20, 2015, 5:12 p.m., Chi Zhang wrote:
---
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31250
://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 Kone wrote
On Feb. 9, 2015, 12:07 p.m., Ian Downes wrote:
3rdparty/libprocess/3rdparty/stout/include/stout/os.hpp, line 405
https://reviews.apache.org/r/30609/diff/2/?file=853657#file853657line405
this is leaking the implementation, both that it's using stat and that
it's using lstat
On Feb. 2, 2015, 1:20 p.m., Ian Downes wrote:
src/slave/containerizer/mesos/containerizer.hpp, lines 221-226
https://reviews.apache.org/r/30510/diff/1/?file=843873#file843873line221
In my current working code I've added an Optionstring rootfs to
struct Container. Would
---
This is in preparation for supporting different root filesystems for containers
using the MesosContainerizer.
Diffs
-
src/slave/containerizer/mesos/containerizer.hpp
802988c90ac872b0cefa5e28f06e6fec98e8d032
Diff: https://reviews.apache.org/r/30628/diff/
Testing
---
Thanks,
Ian
?
3rdparty/libprocess/3rdparty/stout/include/stout/os.hpp
https://reviews.apache.org/r/30609/#comment116579
What's the desired behavior if path is a symlink: st_size will be the
length of the pathname it contains... perhaps you want lstat()?
- Ian Downes
On Feb. 4, 2015, 12:12 a.m., Bernd Mathiske
' and specified command executor, both directly as
the value and fetching from file:///. Tested enviroment variables too.
Thanks,
Ian Downes
1 - 100 of 876 matches
Mail list logo