| From: |
| Eric Dumazet <edumazet-AT-google.com> |
| To: |
| "David S . Miller" <davem-AT-davemloft.net>, Jakub Kicinski <kuba-AT-kernel.org>, Paolo Abeni <pabeni-AT-redhat.com> |
| Subject: |
| [PATCH RFC net-next 0/4] net: deal with strange attractors tx queues |
| Date: |
| Wed, 08 Oct 2025 10:46:07 +0000 |
| Message-ID: |
| <20251008104612.1824200-1-edumazet@google.com> |
| Cc: |
| Simon Horman <horms-AT-kernel.org>, Kuniyuki Iwashima <kuniyu-AT-google.com>, Willem de Bruijn <willemb-AT-google.com>, netdev-AT-vger.kernel.org, eric.dumazet-AT-gmail.com, Eric Dumazet <edumazet-AT-google.com> |
| Archive-link: |
| Article |
Back 2010, Tom Herbert added skb->ooo_okay to TCP flows.
Extend the feature to connected flows for other protocols like UDP.
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, we need to do better now that TCP deals better with
potential reorders.
Add new net.core.txq_reselection_ms sysctl to let
flows follow XPS and select a more efficient queue.
After this series, 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.
Eric Dumazet (4):
net: add SK_WMEM_ALLOC_BIAS constant
net: control skb->ooo_okay from skb_set_owner_w()
net: add /proc/sys/net/core/txq_reselection_ms control
net: allow busy connected flows to switch tx queues
Documentation/admin-guide/sysctl/net.rst | 15 +++++++++
include/net/netns/core.h | 1 +
include/net/sock.h | 43 ++++++++++++------------
net/atm/common.c | 2 +-
net/core/dev.c | 27 +++++++++++++--
net/core/net_namespace.c | 1 +
net/core/sock.c | 17 +++++++---
net/core/sysctl_net_core.c | 7 ++++
8 files changed, 84 insertions(+), 29 deletions(-)
--
2.51.0.710.ga91ca5db03-goog
