brain-hackers_pepepper-mirror/linux-brain
1
0
Fork 0
mirror of https://github.com/brain-hackers/linux-brain.git synced 2024-06-09 23:36:23 +09:00
Code Issues Projects Releases Wiki Activity
Linux kernel source tree for SHARP Brain series (PW-SH1 or later)
886,484 Commits 19 Branches 467 Tags 3.3 GiB
C 97.8%
Assembly 1.4%
Makefile 0.3%
Shell 0.2%
Python 0.1%
Other 0.1%
043ebbccdd
Go to file
Odin Ugedal 043ebbccdd sched/fair: Fix unfairness caused by missing load decay 
[ Upstream commit 0258bdfaff5bd13c4d2383150b7097aecd6b6d82 ]

This fixes an issue where old load on a cfs_rq is not properly decayed,
resulting in strange behavior where fairness can decrease drastically.
Real workloads with equally weighted control groups have ended up
getting a respective 99% and 1%(!!) of cpu time.

When an idle task is attached to a cfs_rq by attaching a pid to a cgroup,
the old load of the task is attached to the new cfs_rq and sched_entity by
attach_entity_cfs_rq. If the task is then moved to another cpu (and
therefore cfs_rq) before being enqueued/woken up, the load will be moved
to cfs_rq->removed from the sched_entity. Such a move will happen when
enforcing a cpuset on the task (eg. via a cgroup) that force it to move.

The load will however not be removed from the task_group itself, making
it look like there is a constant load on that cfs_rq. This causes the
vruntime of tasks on other sibling cfs_rq's to increase faster than they
are supposed to; causing severe fairness issues. If no other task is
started on the given cfs_rq, and due to the cpuset it would not happen,
this load would never be properly unloaded. With this patch the load
will be properly removed inside update_blocked_averages. This also
applies to tasks moved to the fair scheduling class and moved to another
cpu, and this path will also fix that. For fork, the entity is queued
right away, so this problem does not affect that.

This applies to cases where the new process is the first in the cfs_rq,
issue introduced 3d30544f02 ("sched/fair: Apply more PELT fixes"), and
when there has previously been load on the cgroup but the cgroup was
removed from the leaflist due to having null PELT load, indroduced
in 039ae8bcf7 ("sched/fair: Fix O(nr_cgroups) in the load balancing
path").

For a simple cgroup hierarchy (as seen below) with two equally weighted
groups, that in theory should get 50/50 of cpu time each, it often leads
to a load of 60/40 or 70/30.

parent/
  cg-1/
    cpu.weight: 100
    cpuset.cpus: 1
  cg-2/
    cpu.weight: 100
    cpuset.cpus: 1

If the hierarchy is deeper (as seen below), while keeping cg-1 and cg-2
equally weighted, they should still get a 50/50 balance of cpu time.
This however sometimes results in a balance of 10/90 or 1/99(!!) between
the task groups.

$ ps u -C stress
USER         PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
root       18568  1.1  0.0   3684   100 pts/12   R+   13:36   0:00 stress --cpu 1
root       18580 99.3  0.0   3684   100 pts/12   R+   13:36   0:09 stress --cpu 1

parent/
  cg-1/
    cpu.weight: 100
    sub-group/
      cpu.weight: 1
      cpuset.cpus: 1
  cg-2/
    cpu.weight: 100
    sub-group/
      cpu.weight: 10000
      cpuset.cpus: 1

This can be reproduced by attaching an idle process to a cgroup and
moving it to a given cpuset before it wakes up. The issue is evident in
many (if not most) container runtimes, and has been reproduced
with both crun and runc (and therefore docker and all its "derivatives"),
and with both cgroup v1 and v2.

Fixes: 3d30544f02 ("sched/fair: Apply more PELT fixes")
Fixes: 039ae8bcf7 ("sched/fair: Fix O(nr_cgroups) in the load balancing path")
Signed-off-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210501141950.23622-2-odin@uged.al
Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-05-19 10:08:28 +02:00
arch RISC-V: Fix error code returned by riscv_hartid_to_cpuid() 2021-05-19 10:08:26 +02:00
block block: only update parent bi_status when bio fail 2021-04-16 11:46:38 +02:00
certs certs: Fix blacklist flag type confusion 2021-03-04 10:26:29 +01:00
crypto crypto: rng - fix crypto_rng_reset() refcounting when !CRYPTO_STATS 2021-05-11 14:04:15 +02:00
Documentation dt-bindings: net: ethernet-controller: fix typo in NVMEM 2021-04-14 08:24:18 +02:00
drivers can: m_can: m_can_tx_work_queue(): fix tx_skb race condition 2021-05-19 10:08:28 +02:00
fs ceph: fix inode leak on getattr error in __fh_to_dentry 2021-05-19 10:08:26 +02:00
include netfilter: xt_SECMARK: add new revision to fix structure layout 2021-05-19 10:08:27 +02:00
init init/Kconfig: make COMPILE_TEST depend on HAS_IOMEM 2021-04-10 13:34:32 +02:00
ipc ipc/util.c: sysvipc_find_ipc() incorrectly updates position index 2020-05-20 08:20:16 +02:00
kernel sched/fair: Fix unfairness caused by missing load decay 2021-05-19 10:08:28 +02:00
lib net: fix nla_strcmp to handle more then one trailing null character 2021-05-19 10:08:27 +02:00
LICENSES LICENSES: Rename other to deprecated 2019-05-03 06:34:32 -06:00
mm ksm: fix potential missing rmap_item for stable_node 2021-05-19 10:08:27 +02:00
net netfilter: nfnetlink_osf: Fix a missing skb_header_pointer() NULL check 2021-05-19 10:08:28 +02:00
samples samples/bpf: Fix broken tracex1 due to kprobe argument change 2021-05-19 10:08:23 +02:00
scripts kconfig: nconf: stop endless search loops 2021-05-19 10:08:23 +02:00
security security: commoncap: fix -Wstringop-overread warning 2021-05-11 14:04:16 +02:00
sound ASoC: rt286: Make RT286_SET_GPIO_* readable and writable 2021-05-19 10:08:24 +02:00
tools selftests: Set CC to clang in lib.mk if LLVM is set 2021-05-19 10:08:22 +02:00
usr initramfs: restore default compression behavior 2020-04-08 09:08:38 +02:00
virt KVM: Stop looking for coalesced MMIO zones if the bus is destroyed 2021-05-14 09:44:15 +02:00
.clang-format clang-format: Update with the latest for_each macro list 2019-08-31 10:00:51 +02:00
.cocciconfig scripts: add Linux .cocciconfig for coccinelle 2016-07-22 12:13:39 +02:00
.get_maintainer.ignore Opt out of scripts/get_maintainer.pl 2019-05-16 10:53:40 -07:00
.gitattributes .gitattributes: set git diff driver for C source code files 2016-10-07 18:46:30 -07:00
.gitignore Modules updates for v5.4 2019-09-22 10:34:46 -07:00
.mailmap ARM: SoC fixes 2019-11-10 13:41:59 -08:00
COPYING COPYING: use the new text with points to the license files 2018-03-23 12:41:45 -06:00
CREDITS MAINTAINERS: Remove Simon as Renesas SoC Co-Maintainer 2019-10-10 08:12:51 -07:00
Kbuild kbuild: do not descend to ./Kbuild when cleaning 2019-08-21 21:03:58 +09:00
Kconfig docs: kbuild: convert docs to ReST and rename to *.rst 2019-06-14 14:21:21 -06:00
MAINTAINERS Documentation/llvm: add documentation on building w/ Clang/LLVM 2020-08-26 10:40:46 +02:00
Makefile Linux 5.4.119 2021-05-14 09:44:33 +02:00
README Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00

README 

Linux kernel
============

There are several guides for kernel developers and users. These guides can
be rendered in a number of formats, like HTML and PDF. Please read
Documentation/admin-guide/README.rst first.

In order to build the documentation, use ``make htmldocs`` or
``make pdfdocs``.  The formatted documentation can also be read online at:

    https://www.kernel.org/doc/html/latest/

There are various text files in the Documentation/ subdirectory,
several of them using the Restructured Text markup notation.

Please read the Documentation/process/changes.rst file, as it contains the
requirements for building and running the kernel, and information about
the problems which may result by upgrading your kernel.