2021-03-15 13:45:21 |
Marcelo Cerri |
bug |
|
|
added bug |
2021-03-15 13:45:37 |
Marcelo Cerri |
nominated for series |
|
Ubuntu Focal |
|
2021-03-15 13:45:37 |
Marcelo Cerri |
bug task added |
|
linux (Ubuntu Focal) |
|
2021-03-15 13:45:37 |
Marcelo Cerri |
nominated for series |
|
Ubuntu Groovy |
|
2021-03-15 13:45:37 |
Marcelo Cerri |
bug task added |
|
linux (Ubuntu Groovy) |
|
2021-03-15 13:45:37 |
Marcelo Cerri |
nominated for series |
|
Ubuntu Hirsute |
|
2021-03-15 13:45:37 |
Marcelo Cerri |
bug task added |
|
linux (Ubuntu Hirsute) |
|
2021-03-24 20:53:58 |
Marcelo Cerri |
linux (Ubuntu Groovy): status |
New |
In Progress |
|
2021-03-24 20:54:00 |
Marcelo Cerri |
linux (Ubuntu Focal): status |
New |
In Progress |
|
2021-04-07 22:02:30 |
Marcelo Cerri |
description |
[Impact]
The CONFIG_NO_HZ_FULL=y Kconfig option causes the kernel to avoid
sending scheduling-clock interrupts to CPUs with a single runnable task,
and such CPUs are said to be "adaptive-ticks CPUs". This is important
for applications with aggressive real-time response constraints because
it allows them to improve their worst-case response times by the maximum
duration of a scheduling-clock interrupt. It is also important for
computationally intensive short-iteration workloads: If any CPU is
delayed during a given iteration, all the other CPUs will be forced to
wait idle while the delayed CPU finishes. Thus, the delay is multiplied
by one less than the number of CPUs. In these situations, there is
again strong motivation to avoid sending scheduling-clock interrupts.
[Test Plan]
In order to verify the change will not cause performance issues in context switch we should compare the results for:
./stress-ng --seq 0 --metrics-brief -t 15
Running on a dedicated machine and with the following services disabled: smartd.service, iscsid.service, apport.service, cron.service, anacron.timer, apt-daily.timer, apt-daily-upgrade.timer, fstrim.timer, logrotate.timer, motd-news.timer, man-db.timer.
[Where problems could occur]
Performance degradation might happen for workloads with intensive context switching. |
[Impact]
The CONFIG_NO_HZ_FULL=y Kconfig option causes the kernel to avoid
sending scheduling-clock interrupts to CPUs with a single runnable task,
and such CPUs are said to be "adaptive-ticks CPUs". This is important
for applications with aggressive real-time response constraints because
it allows them to improve their worst-case response times by the maximum
duration of a scheduling-clock interrupt. It is also important for
computationally intensive short-iteration workloads: If any CPU is
delayed during a given iteration, all the other CPUs will be forced to
wait idle while the delayed CPU finishes. Thus, the delay is multiplied
by one less than the number of CPUs. In these situations, there is
again strong motivation to avoid sending scheduling-clock interrupts.
[Test Plan]
In order to verify the change will not cause performance issues in context switch we should compare the results for:
./stress-ng --seq 0 --metrics-brief -t 15
Running on a dedicated machine and with the following services disabled: smartd.service, iscsid.service, apport.service, cron.service, anacron.timer, apt-daily.timer, apt-daily-upgrade.timer, fstrim.timer, logrotate.timer, motd-news.timer, man-db.timer.
The results didn't show any performance regression:
https://kernel.ubuntu.com/~mhcerri/lp1919154/
[Where problems could occur]
Performance degradation might happen for workloads with intensive context switching. |
|
2021-07-28 23:18:25 |
Brian Murray |
linux (Ubuntu Groovy): status |
In Progress |
Won't Fix |
|
2021-12-15 21:11:45 |
Dominique Poulain |
bug |
|
|
added subscriber Dominique Poulain |
2023-10-16 04:15:23 |
gerald.yang |
nominated for series |
|
Ubuntu Jammy |
|
2023-10-16 04:15:23 |
gerald.yang |
bug task added |
|
linux (Ubuntu Jammy) |
|
2023-10-16 04:15:23 |
gerald.yang |
nominated for series |
|
Ubuntu Mantic |
|
2023-10-16 04:15:23 |
gerald.yang |
bug task added |
|
linux (Ubuntu Mantic) |
|
2023-10-16 04:15:23 |
gerald.yang |
nominated for series |
|
Ubuntu Lunar |
|
2023-10-16 04:15:23 |
gerald.yang |
bug task added |
|
linux (Ubuntu Lunar) |
|
2023-10-16 04:15:33 |
gerald.yang |
linux (Ubuntu Jammy): status |
New |
In Progress |
|
2023-10-16 04:15:36 |
gerald.yang |
linux (Ubuntu Lunar): status |
New |
In Progress |
|
2023-10-16 04:15:40 |
gerald.yang |
linux (Ubuntu Jammy): assignee |
|
gerald.yang (gerald-yang-tw) |
|
2023-10-16 04:15:44 |
gerald.yang |
linux (Ubuntu Lunar): assignee |
|
gerald.yang (gerald-yang-tw) |
|
2023-10-16 04:17:36 |
gerald.yang |
linux (Ubuntu Mantic): assignee |
Marcelo Cerri (mhcerri) |
gerald.yang (gerald-yang-tw) |
|
2023-10-18 07:17:47 |
gerald.yang |
attachment added |
|
syscall-time.c https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1919154/+attachment/5710594/+files/syscall-time.c |
|
2023-10-25 16:14:37 |
dann frazier |
bug |
|
|
added subscriber dann frazier |
2023-10-25 17:51:03 |
Jay Vosburgh |
bug |
|
|
added subscriber Jay Vosburgh |
2023-10-26 13:47:56 |
gerald.yang |
attachment added |
|
log.tgz https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1919154/+attachment/5713511/+files/log.tgz |
|
2023-10-26 13:48:48 |
gerald.yang |
attachment added |
|
nohz-log.tgz https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1919154/+attachment/5713512/+files/nohz-log.tgz |
|
2023-10-26 13:51:14 |
gerald.yang |
attachment added |
|
nohz-log-isolcpu.tgz https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1919154/+attachment/5713513/+files/nohz-log-isolcpu.tgz |
|
2023-10-26 13:53:00 |
gerald.yang |
attachment added |
|
nohz-log-noisolcpu.tgz https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1919154/+attachment/5713517/+files/nohz-log-noisolcpu.tgz |
|
2023-11-08 08:04:07 |
Dimitri John Ledkov |
linux (Ubuntu Focal): status |
In Progress |
Won't Fix |
|
2023-11-08 08:04:29 |
Dimitri John Ledkov |
linux (Ubuntu Hirsute): status |
In Progress |
Won't Fix |
|
2023-11-08 08:04:33 |
Dimitri John Ledkov |
linux (Ubuntu Jammy): status |
In Progress |
Won't Fix |
|
2023-11-08 08:04:36 |
Dimitri John Ledkov |
linux (Ubuntu Lunar): status |
In Progress |
Won't Fix |
|
2023-11-08 08:04:44 |
Dimitri John Ledkov |
linux (Ubuntu Mantic): status |
In Progress |
Won't Fix |
|
2023-11-08 08:06:34 |
Dimitri John Ledkov |
bug task added |
|
linux-lowlatency (Ubuntu) |
|
2023-11-08 08:06:43 |
Dimitri John Ledkov |
linux-lowlatency (Ubuntu): status |
New |
Fix Released |
|
2023-11-08 08:06:51 |
Dimitri John Ledkov |
linux-lowlatency (Ubuntu Mantic): status |
New |
Fix Released |
|
2023-11-08 08:07:00 |
Dimitri John Ledkov |
linux-lowlatency (Ubuntu Lunar): status |
New |
Won't Fix |
|
2023-11-08 08:07:08 |
Dimitri John Ledkov |
linux-lowlatency (Ubuntu Jammy): status |
New |
Won't Fix |
|
2023-11-09 08:42:52 |
Juerg Haefliger |
linux-lowlatency (Ubuntu Hirsute): status |
New |
Won't Fix |
|
2023-11-09 08:43:05 |
Juerg Haefliger |
linux-lowlatency (Ubuntu Groovy): status |
New |
Won't Fix |
|
2023-11-09 08:44:28 |
Juerg Haefliger |
linux-lowlatency (Ubuntu Focal): status |
New |
Won't Fix |
|
2024-04-30 13:07:47 |
Heitor Alves de Siqueira |
linux (Ubuntu): status |
In Progress |
Fix Released |
|