kernel/linux
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ synced 2026-10-24 19:10:26 +00:00
Code Issues Releases Packages Activity
No description
1,396,346 commits 117 branches 5,803 tags 5.7 GiB
  • C 96.8%
  • Assembly 0.9%
  • Rust 0.7%
  • Shell 0.6%
  • Python 0.5%
  • Other 0.3%
Find a file
Eric Dumazet 4a7708443d net: allow busy connected flows to switch tx queues 
This is a followup of commit 726e9e8b94 ("tcp: refine
skb->ooo_okay setting") and of prior commit in this series
("net: control skb->ooo_okay from skb_set_owner_w()")

skb->ooo_okay might never be set for bulk flows that always
have at least one skb in a qdisc queue of NIC queue,
especially if TX completion is delayed because of a stressed cpu.

The so-called "strange attractors" has caused many performance
issues (see for instance 9b462d02d6 ("tcp: TCP Small Queues
and strange attractors")), we need to do better.

We have tried very hard to avoid reorders because TCP was
not dealing with them nicely a decade ago.

Use the new net.core.txq_reselection_ms sysctl to let
flows follow XPS and select a more efficient queue.

After this patch, we no longer have to make sure threads
are pinned to cpus, they now can be migrated without
adding too much spinlock/qdisc/TX completion pressure anymore.

TX completion part was problematic, because it added false sharing
on various socket fields, but also added false sharing and spinlock
contention in mm layers. Calling skb_orphan() from ndo_start_xmit()
is not an option unfortunately.

Note for later:

1) move sk->sk_tx_queue_mapping closer
to sk_tx_queue_mapping_jiffies for better cache locality.

2) Study if 9b462d02d6 ("tcp: TCP Small Queues
and strange attractors") could be revised.

Tested:

Used a host with 32 TX queues, shared by groups of 8 cores.
XPS setup :

echo ff >/sys/class/net/eth1/queue/tx-0/xps_cpus
echo ff00 >/sys/class/net/eth1/queue/tx-1/xps_cpus
echo ff0000 >/sys/class/net/eth1/queue/tx-2/xps_cpus
echo ff000000 >/sys/class/net/eth1/queue/tx-3/xps_cpus
echo ff,00000000 >/sys/class/net/eth1/queue/tx-4/xps_cpus
echo ff00,00000000 >/sys/class/net/eth1/queue/tx-5/xps_cpus
echo ff0000,00000000 >/sys/class/net/eth1/queue/tx-6/xps_cpus
echo ff000000,00000000 >/sys/class/net/eth1/queue/tx-7/xps_cpus
...

Launched a tcp_stream with 15 threads and 1000 flows, initially affined to core 0-15

taskset -c 0-15 tcp_stream -T15 -F1000 -l1000 -c -H target_host

Checked that only queues 0 and 1 are used as instructed by XPS :
tc -s qdisc show dev eth1|grep backlog|grep -v "backlog 0b 0p"
 backlog 123489410b 1890p
 backlog 69809026b 1064p
 backlog 52401054b 805p

Then force each thread to run on cpu 1,9,17,25,33,41,49,57,65,73,81,89,97,105,113,121

C=1;PID=`pidof tcp_stream`;for P in `ls /proc/$PID/task`; do taskset -pc $C $P; C=$(($C + 8));done

Set txq_reselection_ms to 1000
echo 1000 > /proc/sys/net/core/txq_reselection_ms

Check that the flows have migrated nicely:

tc -s qdisc show dev eth1|grep backlog|grep -v "backlog 0b 0p"
 backlog 130508314b 1916p
 backlog 8584380b 126p
 backlog 8584380b 126p
 backlog 8379990b 123p
 backlog 8584380b 126p
 backlog 8487484b 125p
 backlog 8584380b 126p
 backlog 8448120b 124p
 backlog 8584380b 126p
 backlog 8720640b 128p
 backlog 8856900b 130p
 backlog 8584380b 126p
 backlog 8652510b 127p
 backlog 8448120b 124p
 backlog 8516250b 125p
 backlog 7834950b 115p

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251013152234.842065-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
History 2025-10-15 09:04:22 -07:00
arch more s390 updates for 6.18 merge window 2025-10-09 10:51:43 -07:00
block Summary of significant series in this pull request: 2025-10-02 18:18:33 -07:00
certs sign-file,extract-cert: use pkcs11 provider for OPENSSL MAJOR >= 3 2024-09-20 19:52:48 +03:00
crypto This push contains the following changes: 2025-10-08 09:38:31 -07:00
Documentation net: add /proc/sys/net/core/txq_reselection_ms control 2025-10-15 09:04:21 -07:00
drivers net: airoha: Add get_link ethtool callback 2025-10-14 19:35:45 -07:00
fs for-6.18-tag 2025-10-06 13:53:19 -07:00
include net: allow busy connected flows to switch tx queues 2025-10-15 09:04:22 -07:00
init printk changes for 6.18 2025-10-04 11:13:11 -07:00
io_uring Summary of significant series in this pull request: 2025-10-02 18:18:33 -07:00
ipc namespace-6.18-rc1 2025-09-29 11:20:29 -07:00
kernel hyperv-next for v6.18 2025-10-07 08:40:15 -07:00
lib integrity-v6.18 2025-10-05 10:48:33 -07:00
LICENSES LICENSES: Replace the obsolete address of the FSF in the GFDL-1.2 2025-07-24 11:15:39 +02:00
mm slab fixes for 6.18-rc1 2025-10-09 10:33:50 -07:00
net net: allow busy connected flows to switch tx queues 2025-10-15 09:04:22 -07:00
rust More power management updates for 6.18-rc1 2025-10-07 09:39:51 -07:00
samples Char/Misc/IIO/Binder changes for 6.18-rc1 2025-10-04 16:26:32 -07:00
scripts kconfig: Avoid prompting for transitional symbols 2025-10-07 08:21:23 -07:00
security integrity-v6.18 2025-10-05 10:48:33 -07:00
sound platform-drivers-x86 for v6.18-1 2025-10-04 15:28:18 -07:00
tools Including fixes from netfilter. 2025-10-09 11:13:08 -07:00
usr gen_init_cpio: add -a <data_align> as reflink optimization 2025-08-20 16:02:56 -07:00
virt hyperv-next for v6.18 2025-10-07 08:40:15 -07:00
.clang-format memblock: drop for_each_free_mem_pfn_range_in_zone_from() 2025-09-14 08:49:03 +03:00
.clippy.toml rust: clean Rust 1.88.0's warning about clippy::disallowed_macros configuration 2025-05-07 00:11:47 +02:00
.cocciconfig scripts: add Linux .cocciconfig for coccinelle 2016-07-22 12:13:39 +02:00
.editorconfig .editorconfig: remove trim_trailing_whitespace option 2024-06-13 16:47:52 +02:00
.get_maintainer.ignore MAINTAINERS: remove Alyssa Rosenzweig 2025-09-18 21:17:31 +02:00
.gitattributes .gitattributes: set diff driver for Rust source code files 2023-05-31 17:48:25 +02:00
.gitignore .gitignore: ignore compile_commands.json globally 2025-08-12 15:53:55 -07:00
.mailmap VFIO updates for v6.18-rc1 2025-10-04 08:24:54 -07:00
.pylintrc tools: docs: parse-headers.py: move it from sphinx dir 2025-08-29 15:54:42 -06:00
.rustfmt.toml rust: add .rustfmt.toml 2022-09-28 09:02:20 +02:00
COPYING COPYING: state that all contributions really are covered by this file 2020-02-10 13:32:20 -08:00
CREDITS USB/Thunderbolt changes for 6.18-rc1 2025-10-04 16:07:08 -07:00
Kbuild sched: Make migrate_{en,dis}able() inline 2025-09-25 09:57:16 +02:00
Kconfig io_uring: Rename KConfig to Kconfig 2025-02-19 14:53:27 -07:00
MAINTAINERS perf tools improvements and fixes for Linux v6.18: 2025-10-08 19:24:24 -07:00
Makefile It has been a relatively busy cycle in docsland, with changes all over: 2025-10-03 17:16:13 -07:00
README README: Fix spelling 2024-03-18 03:36:32 -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 reStructuredText 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.