[jira] [Commented] (MESOS-3161) Document using the gold linker for faster development on linux.
[
https://issues.apache.org/jira/browse/MESOS-3161?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125885#comment-15125885
]
Deshi Xiao commented on MESOS-3161:
---
+1 on documents.
> Document using the gold linker for faster development on linux.
> ---
>
> Key: MESOS-3161
> URL: https://issues.apache.org/jira/browse/MESOS-3161
> Project: Mesos
> Issue Type: Improvement
> Components: build, documentation
>Reporter: Benjamin Mahler
> Labels: newbie
>
> The [gold linker|https://en.wikipedia.org/wiki/Gold_(linker)] seems to
> provide a decent speedup (about ~20%) on a parallel build. From a quick test:
> {noformat: title=timings for make check -j24 GTEST_FILTER="" w/ 24
> hyperthreaded cores}
> gold:
> real 7m18.526s
> user 81m21.213s
> sys 5m17.224s
> default ld:
> real 9m7.908s
> user 85m13.466s
> sys 5m52.199s
> {noformat}
> On CentOS 5 w/ devtoolset-2:
> {noformat}
> sudo /usr/sbin/alternatives --altdir
> /opt/rh/devtoolset-2/root/etc/alternatives --admindir
> /opt/rh/devtoolset-2/root/var/lib/alternatives --set ld
> /opt/rh/devtoolset-2/root/usr/bin/ld.gold
> {noformat}
> On Ubuntu:
> {noformat}
> sudo update-alternatives --install /usr/bin/ld ld /usr/bin/gold 1
> {noformat}
> Ideally we could this out on the website, with instructions for each OS.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Updated] (MESOS-4435) Update `Master::Http::stateSummary` to use `jsonify`.
[
https://issues.apache.org/jira/browse/MESOS-4435?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Michael Park updated MESOS-4435:
Shepherd: Joris Van Remoortere (was: Benjamin Hindman)
> Update `Master::Http::stateSummary` to use `jsonify`.
> -
>
> Key: MESOS-4435
> URL: https://issues.apache.org/jira/browse/MESOS-4435
> Project: Mesos
> Issue Type: Task
> Components: master
>Reporter: Michael Park
>Assignee: Michael Park
> Fix For: 0.28.0
>
>
> Update {{state-summary}} to use {{jsonify}} to stay consistent with {{state}}
> HTTP endpoint.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Commented] (MESOS-4566) Avoid unnecessary temporary `std::string` constructions and copies in `jsonify`.
[
https://issues.apache.org/jira/browse/MESOS-4566?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125777#comment-15125777
]
Michael Park commented on MESOS-4566:
-
{noformat}
commit 5e064503eb519aea3329f65f7ac93370b2910cc7
Author: Michael Park
Date: Sun Jan 31 20:38:34 2016 -0800
Avoid unnecessary string copies in `json` for protobuf messages.
Review: https://reviews.apache.org/r/43024/
{noformat}
{noformat}
commit 8daa9a5c842a90b7b824a053c5f45897044de5fa
Author: Michael Park
Date: Sun Jan 31 20:37:42 2016 -0800
Avoid construction of temporary strings in `NumberWriter` for doubles.
With this + https://reviews.apache.org/r/43024/, the number of calls to
`operator new` and `operator delete` were reduced by roughly 1/3.
Review: https://reviews.apache.org/r/43023/
{noformat}
> Avoid unnecessary temporary `std::string` constructions and copies in
> `jsonify`.
>
>
> Key: MESOS-4566
> URL: https://issues.apache.org/jira/browse/MESOS-4566
> Project: Mesos
> Issue Type: Improvement
> Components: stout
>Reporter: Michael Park
>Assignee: Michael Park
> Labels: mesosphere
> Fix For: 0.28.0
>
>
> A few of the critical code paths in {{jsonify}} involve unnecessary temporary
> string construction and copies (inherited from the {{JSON::*}}). For example,
> {{strings::trim}} is used to remove trailing 0s from printing {{double}}s. We
> print {{double}}s a lot, and therefore constructing a temporary
> {{std::string}} on printing of every double is extremely costly. This ticket
> captures the work involved in avoiding them.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Updated] (MESOS-4566) Avoid unnecessary temporary `std::string` constructions and copies in `jsonify`.
[
https://issues.apache.org/jira/browse/MESOS-4566?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Michael Park updated MESOS-4566:
Shepherd: Joris Van Remoortere (was: Benjamin Hindman)
> Avoid unnecessary temporary `std::string` constructions and copies in
> `jsonify`.
>
>
> Key: MESOS-4566
> URL: https://issues.apache.org/jira/browse/MESOS-4566
> Project: Mesos
> Issue Type: Improvement
> Components: stout
>Reporter: Michael Park
>Assignee: Michael Park
> Labels: mesosphere
> Fix For: 0.28.0
>
>
> A few of the critical code paths in {{jsonify}} involve unnecessary temporary
> string construction and copies (inherited from the {{JSON::*}}). For example,
> {{strings::trim}} is used to remove trailing 0s from printing {{double}}s. We
> print {{double}}s a lot, and therefore constructing a temporary
> {{std::string}} on printing of every double is extremely costly. This ticket
> captures the work involved in avoiding them.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Commented] (MESOS-4145) Update allocator to get allocation slack resources
[ https://issues.apache.org/jira/browse/MESOS-4145?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125602#comment-15125602 ] Guangya Liu commented on MESOS-4145: A high level design was uploaded here https://docs.google.com/document/d/1B_v52zCOFcwCpqCPhgYi9h630a0NE-QM9Br0nCOZUR4/edit > Update allocator to get allocation slack resources > -- > > Key: MESOS-4145 > URL: https://issues.apache.org/jira/browse/MESOS-4145 > Project: Mesos > Issue Type: Bug >Reporter: Guangya Liu >Assignee: Guangya Liu > > The allocator should be updated to > 1) Report allocation slack resources when add a new agent. > 2) Allocate allocation slack resources when sending offers. > 3) Update allocation slack resources when update agent, update dynamic > reservations with both framework and http endpoint. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (MESOS-4039) PerfEventIsolatorTest.ROOT_CGROUPS_Sample fails
[
https://issues.apache.org/jira/browse/MESOS-4039?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125422#comment-15125422
]
haosdent commented on MESOS-4039:
-
According my test, it have two problem in CentOS 7. One is the perf format
detect in CentOS 7 is incorrect, the anther one is it would remain process when
exit.
> PerfEventIsolatorTest.ROOT_CGROUPS_Sample fails
> ---
>
> Key: MESOS-4039
> URL: https://issues.apache.org/jira/browse/MESOS-4039
> Project: Mesos
> Issue Type: Bug
>Reporter: Greg Mann
>Assignee: Jan Schlicht
> Labels: mesosphere, test-fail
>
> PerfEventIsolatorTest.ROOT_CGROUPS_Sample fails on CentOS 6.6:
> {code}
> [--] 1 test from PerfEventIsolatorTest
> [ RUN ] PerfEventIsolatorTest.ROOT_CGROUPS_Sample
> ../../src/tests/containerizer/isolator_tests.cpp:848: Failure
> isolator: Perf is not supported
> [ FAILED ] PerfEventIsolatorTest.ROOT_CGROUPS_Sample (79 ms)
> [--] 1 test from PerfEventIsolatorTest (79 ms total)
> [--] Global test environment tear-down
> [==] 1 test from 1 test case ran. (86 ms total)
> [ PASSED ] 0 tests.
> [ FAILED ] 1 test, listed below:
> [ FAILED ] PerfEventIsolatorTest.ROOT_CGROUPS_Sample
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Updated] (MESOS-4446) Set Docker labels based on TaskInfo labels.
[ https://issues.apache.org/jira/browse/MESOS-4446?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Abhishek Dasgupta updated MESOS-4446: - Summary: Set Docker labels based on TaskInfo labels. (was: Set Docker labels based on TaskStatus labels.) > Set Docker labels based on TaskInfo labels. > --- > > Key: MESOS-4446 > URL: https://issues.apache.org/jira/browse/MESOS-4446 > Project: Mesos > Issue Type: Story > Components: docker >Reporter: Gennady Feldman >Assignee: Abhishek Dasgupta > > So looks like MESOS-3076 added support for Labels to TaskStatus. Would it be > possible to pass those onto the docker container? > This would really help with doing "docker inspect" on the mesos-slave nodes > as well as allow us to better collect docker metrics about the > tasks/containers that are currently running on the slave. > docker supports labels out of the box. See here: > https://docs.docker.com/engine/userguide/labels-custom-metadata/ -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (MESOS-4561) Investigate `std::string` to C string comparison.
[
https://issues.apache.org/jira/browse/MESOS-4561?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125337#comment-15125337
]
Klaus Ma commented on MESOS-4561:
-
Just checked the {{operator==}} in Mac, it's using {{string::compare}}. And it
seems no performance impact of 5e618ac, is there any test result about it?
> Investigate `std::string` to C string comparison.
> -
>
> Key: MESOS-4561
> URL: https://issues.apache.org/jira/browse/MESOS-4561
> Project: Mesos
> Issue Type: Bug
>Reporter: Michael Park
> Labels: mesosphere
>
> [~jvanremoortere] identified a large performance bottleneck in role
> validation logic and submitted a
> [fix|https://github.com/apache/mesos/commit/5e618ac2197e856f09511850bebe51fea71c1844]
> for the 0.27.0 release.
> However, templated versions of {{bool operator==(const std::string&, const
> char \*)}} and {{bool operator==(const char\*, const std::string&)}} are part
> of the standard library
> http://en.cppreference.com/w/cpp/string/basic_string/operator_cmp, and
> therefore should not have triggered temporary string constructions.
> The first thought was perhaps they don't happen to be implemented in
> {{libstdc++}}, but having looked at its implementation, I was able to find
> the definitions of these operators.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Commented] (MESOS-3049) Failing CGROUPS_ROOT_PerfRollForward test
[
https://issues.apache.org/jira/browse/MESOS-3049?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125332#comment-15125332
]
haosdent commented on MESOS-3049:
-
Could I reopen this? Because I still met this in CentOS 7.1.
> Failing CGROUPS_ROOT_PerfRollForward test
> -
>
> Key: MESOS-3049
> URL: https://issues.apache.org/jira/browse/MESOS-3049
> Project: Mesos
> Issue Type: Bug
> Components: containerization, test
>Affects Versions: 0.23.0
> Environment: CentOS Linux release 7.1.1503
> 0.23.0-rc3
>Reporter: Adam B
>Assignee: Timothy Chen
>
> {code}
> [ RUN ] MesosContainerizerSlaveRecoveryTest.CGROUPS_ROOT_PerfRollForward
> I0715 00:28:42.600359 17919 exec.cpp:132] Version: 0.23.0
> I0715 00:28:42.609073 17983 exec.cpp:206] Executor registered on slave
> 20150715-002842-201330860-41108-794-S0
> Registered executor on srv2.hw.ca1.mesosphere.com
> Starting task b675699c-8427-4934-8bb5-62f91f3d74d0
> Forked command at 17988
> sh -c 'sleep 1000'
> ../../src/tests/slave_recovery_tests.cpp:3446: Failure
> containerizer2: Could not create isolator cgroups/perf_event: Failed to
> create PerfEvent isolator, invalid events: { cycles, task-clock }
> ../../3rdparty/libprocess/include/process/gmock.hpp:353: Failure
> Actual function call count doesn't match EXPECT_CALL(filter->mock,
> filter(testing::A()))...
> Expected args: dispatch matcher (1-byte object <04>, 16-byte object
> <29-00 00-00 00-00 00-00 00-00 00-00 00-00 00-00>)
> Expected: to be called once
>Actual: never called - unsatisfied and active
> [ FAILED ] MesosContainerizerSlaveRecoveryTest.CGROUPS_ROOT_PerfRollForward
> (462 ms)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Commented] (MESOS-3049) Failing CGROUPS_ROOT_PerfRollForward test
[
https://issues.apache.org/jira/browse/MESOS-3049?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125331#comment-15125331
]
haosdent commented on MESOS-3049:
-
Could I reopen this? Because I still met this in CentOS 7.1.
> Failing CGROUPS_ROOT_PerfRollForward test
> -
>
> Key: MESOS-3049
> URL: https://issues.apache.org/jira/browse/MESOS-3049
> Project: Mesos
> Issue Type: Bug
> Components: containerization, test
>Affects Versions: 0.23.0
> Environment: CentOS Linux release 7.1.1503
> 0.23.0-rc3
>Reporter: Adam B
>Assignee: Timothy Chen
>
> {code}
> [ RUN ] MesosContainerizerSlaveRecoveryTest.CGROUPS_ROOT_PerfRollForward
> I0715 00:28:42.600359 17919 exec.cpp:132] Version: 0.23.0
> I0715 00:28:42.609073 17983 exec.cpp:206] Executor registered on slave
> 20150715-002842-201330860-41108-794-S0
> Registered executor on srv2.hw.ca1.mesosphere.com
> Starting task b675699c-8427-4934-8bb5-62f91f3d74d0
> Forked command at 17988
> sh -c 'sleep 1000'
> ../../src/tests/slave_recovery_tests.cpp:3446: Failure
> containerizer2: Could not create isolator cgroups/perf_event: Failed to
> create PerfEvent isolator, invalid events: { cycles, task-clock }
> ../../3rdparty/libprocess/include/process/gmock.hpp:353: Failure
> Actual function call count doesn't match EXPECT_CALL(filter->mock,
> filter(testing::A()))...
> Expected args: dispatch matcher (1-byte object <04>, 16-byte object
> <29-00 00-00 00-00 00-00 00-00 00-00 00-00 00-00>)
> Expected: to be called once
>Actual: never called - unsatisfied and active
> [ FAILED ] MesosContainerizerSlaveRecoveryTest.CGROUPS_ROOT_PerfRollForward
> (462 ms)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Commented] (MESOS-4039) PerfEventIsolatorTest.ROOT_CGROUPS_Sample fails
[
https://issues.apache.org/jira/browse/MESOS-4039?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125330#comment-15125330
]
haosdent commented on MESOS-4039:
-
Today I try this in CentOS 7 which perf version is "perf version
3.10.0-229.11.1.el7.x86_64.debug". Still failed.
> PerfEventIsolatorTest.ROOT_CGROUPS_Sample fails
> ---
>
> Key: MESOS-4039
> URL: https://issues.apache.org/jira/browse/MESOS-4039
> Project: Mesos
> Issue Type: Bug
>Reporter: Greg Mann
>Assignee: Jan Schlicht
> Labels: mesosphere, test-fail
>
> PerfEventIsolatorTest.ROOT_CGROUPS_Sample fails on CentOS 6.6:
> {code}
> [--] 1 test from PerfEventIsolatorTest
> [ RUN ] PerfEventIsolatorTest.ROOT_CGROUPS_Sample
> ../../src/tests/containerizer/isolator_tests.cpp:848: Failure
> isolator: Perf is not supported
> [ FAILED ] PerfEventIsolatorTest.ROOT_CGROUPS_Sample (79 ms)
> [--] 1 test from PerfEventIsolatorTest (79 ms total)
> [--] Global test environment tear-down
> [==] 1 test from 1 test case ran. (86 ms total)
> [ PASSED ] 0 tests.
> [ FAILED ] 1 test, listed below:
> [ FAILED ] PerfEventIsolatorTest.ROOT_CGROUPS_Sample
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
[jira] [Comment Edited] (MESOS-4561) Investigate `std::string` to C string comparison.
[
https://issues.apache.org/jira/browse/MESOS-4561?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125320#comment-15125320
]
haosdent edited comment on MESOS-4561 at 1/31/16 12:58 PM:
---
I am not sure how to test, but I think it may related to this [Why '==' is slow
on
std::string|http://stackoverflow.com/questions/28734684/why-is-slow-on-stdstring]
when you benchmark. According my test, the result are nearly same.
My test code:
{code}
TEST(RolesTest, Benchmark)
{
int64_t ops = 1000;
int64_t cycles = 100;
string validateNames[ops];
for (int64_t i = 0; i < ops; ++i) {
validateNames[i] = stringify(i);
}
Stopwatch watch;
watch.start();
for (int64_t i = 0; i < ops * cycles; ++i) {
roles::validate(validateNames[i % ops]);
}
Duration elapsed = watch.elapsed();
cout << "Estimated Total: " << (elapsed.ns() / ops / cycles)
<< " nanos / ops" << endl;
}
{code}
The result when use [new
version|https://github.com/apache/mesos/blob/5e618ac2197e856f09511850bebe51fea71c1844/src/common/roles.cpp]
to test.
{code}
[==] Running 1 test from 1 test case.
[--] Global test environment set-up.
[--] 1 test from RolesTest
[ RUN ] RolesTest.Benchmark
Estimated Total: 49 nanos / ops
[ OK ] RolesTest.Benchmark (49196 ms)
[--] 1 test from RolesTest (49196 ms total)
[--] Global test environment tear-down
[==] 1 test from 1 test case ran. (49208 ms total)
[ PASSED ] 1 test.
{code}
After revert to [old
version|https://github.com/apache/mesos/blob/ffcef51f06f41f707e7026070f2335b956ed9d2c/src/common/roles.cpp],
the result looks don't have big different:
{code}
[==] Running 1 test from 1 test case.
[--] Global test environment set-up.
[--] 1 test from RolesTest
[ RUN ] RolesTest.Benchmark
Estimated Total: 46 nanos / ops
[ OK ] RolesTest.Benchmark (46327 ms)
[--] 1 test from RolesTest (46327 ms total)
[--] Global test environment tear-down
[==] 1 test from 1 test case ran. (46339 ms total)
[ PASSED ] 1 test.
{code}
was (Author: haosd...@gmail.com):
I am not sure how to test, but I think it may related to this {{Why '==' is
slow on
std::string|http://stackoverflow.com/questions/28734684/why-is-slow-on-stdstring}}
when you benchmark. According my test, the result are nearly same.
My test code:
{code}
TEST(RolesTest, Benchmark)
{
int64_t ops = 1000;
int64_t cycles = 100;
string validateNames[ops];
for (int64_t i = 0; i < ops; ++i) {
validateNames[i] = stringify(i);
}
Stopwatch watch;
watch.start();
for (int64_t i = 0; i < ops * cycles; ++i) {
roles::validate(validateNames[i % ops]);
}
Duration elapsed = watch.elapsed();
cout << "Estimated Total: " << (elapsed.ns() / ops / cycles)
<< " nanos / ops" << endl;
}
{code}
The result when use {{new
version|https://github.com/apache/mesos/blob/5e618ac2197e856f09511850bebe51fea71c1844/src/common/roles.cpp}}
to test.
{code}
[==] Running 1 test from 1 test case.
[--] Global test environment set-up.
[--] 1 test from RolesTest
[ RUN ] RolesTest.Benchmark
Estimated Total: 49 nanos / ops
[ OK ] RolesTest.Benchmark (49196 ms)
[--] 1 test from RolesTest (49196 ms total)
[--] Global test environment tear-down
[==] 1 test from 1 test case ran. (49208 ms total)
[ PASSED ] 1 test.
{code}
After revert to {{old
version|https://github.com/apache/mesos/blob/ffcef51f06f41f707e7026070f2335b956ed9d2c/src/common/roles.cpp}},
the result looks don't have big different:
{code}
[==] Running 1 test from 1 test case.
[--] Global test environment set-up.
[--] 1 test from RolesTest
[ RUN ] RolesTest.Benchmark
Estimated Total: 46 nanos / ops
[ OK ] RolesTest.Benchmark (46327 ms)
[--] 1 test from RolesTest (46327 ms total)
[--] Global test environment tear-down
[==] 1 test from 1 test case ran. (46339 ms total)
[ PASSED ] 1 test.
{code}
> Investigate `std::string` to C string comparison.
> -
>
> Key: MESOS-4561
> URL: https://issues.apache.org/jira/browse/MESOS-4561
> Project: Mesos
> Issue Type: Bug
>Reporter: Michael Park
> Labels: mesosphere
>
> [~jvanremoortere] identified a large performance bottleneck in role
> validation logic and submitted a
> [fix|https://github.com/apache/mesos/commit/5e618ac2197e856f09511850bebe51fea71c1844]
> for the 0.27.0 release.
> However, templated versions of {{bool operator==(const std::string&, const
> char \*)}} and {{bool operator==(const char\*, const std::string&)}} are part
> of the standard library
> http://en.cppreference.com/w/cpp/string/basic_string/operator_cmp, and
> therefore should not have trigg
[jira] [Commented] (MESOS-4561) Investigate `std::string` to C string comparison.
[
https://issues.apache.org/jira/browse/MESOS-4561?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125320#comment-15125320
]
haosdent commented on MESOS-4561:
-
I am not sure how to test, but I think it may related to this {{Why '==' is
slow on
std::string|http://stackoverflow.com/questions/28734684/why-is-slow-on-stdstring}}
when you benchmark. According my test, the result are nearly same.
My test code:
{code}
TEST(RolesTest, Benchmark)
{
int64_t ops = 1000;
int64_t cycles = 100;
string validateNames[ops];
for (int64_t i = 0; i < ops; ++i) {
validateNames[i] = stringify(i);
}
Stopwatch watch;
watch.start();
for (int64_t i = 0; i < ops * cycles; ++i) {
roles::validate(validateNames[i % ops]);
}
Duration elapsed = watch.elapsed();
cout << "Estimated Total: " << (elapsed.ns() / ops / cycles)
<< " nanos / ops" << endl;
}
{code}
The result when use {{new
version|https://github.com/apache/mesos/blob/5e618ac2197e856f09511850bebe51fea71c1844/src/common/roles.cpp}}
to test.
{code}
[==] Running 1 test from 1 test case.
[--] Global test environment set-up.
[--] 1 test from RolesTest
[ RUN ] RolesTest.Benchmark
Estimated Total: 49 nanos / ops
[ OK ] RolesTest.Benchmark (49196 ms)
[--] 1 test from RolesTest (49196 ms total)
[--] Global test environment tear-down
[==] 1 test from 1 test case ran. (49208 ms total)
[ PASSED ] 1 test.
{code}
After revert to {{old
version|https://github.com/apache/mesos/blob/ffcef51f06f41f707e7026070f2335b956ed9d2c/src/common/roles.cpp}},
the result looks don't have big different:
{code}
[==] Running 1 test from 1 test case.
[--] Global test environment set-up.
[--] 1 test from RolesTest
[ RUN ] RolesTest.Benchmark
Estimated Total: 46 nanos / ops
[ OK ] RolesTest.Benchmark (46327 ms)
[--] 1 test from RolesTest (46327 ms total)
[--] Global test environment tear-down
[==] 1 test from 1 test case ran. (46339 ms total)
[ PASSED ] 1 test.
{code}
> Investigate `std::string` to C string comparison.
> -
>
> Key: MESOS-4561
> URL: https://issues.apache.org/jira/browse/MESOS-4561
> Project: Mesos
> Issue Type: Bug
>Reporter: Michael Park
> Labels: mesosphere
>
> [~jvanremoortere] identified a large performance bottleneck in role
> validation logic and submitted a
> [fix|https://github.com/apache/mesos/commit/5e618ac2197e856f09511850bebe51fea71c1844]
> for the 0.27.0 release.
> However, templated versions of {{bool operator==(const std::string&, const
> char \*)}} and {{bool operator==(const char\*, const std::string&)}} are part
> of the standard library
> http://en.cppreference.com/w/cpp/string/basic_string/operator_cmp, and
> therefore should not have triggered temporary string constructions.
> The first thought was perhaps they don't happen to be implemented in
> {{libstdc++}}, but having looked at its implementation, I was able to find
> the definitions of these operators.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
