From: Willem de Bruijn <willemb@google.com>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, eric.dumazet@gmail.com,
david.laight@aculab.com, Willem de Bruijn <willemb@google.com>
Subject: [PATCH net-next v2 0/6] packet: refine rollover
Date: Sat, 9 May 2015 17:24:55 -0400 [thread overview]
Message-ID: <1431206701-5019-1-git-send-email-willemb@google.com> (raw)
From: Willem de Bruijn <willemb@google.com>
efine packet socket rollover:
1. mitigate a case of lock contention
2. avoid exporting resource exhaustion to other sockets,
by migrating only to a victim socket that has ample room
3. avoid reordering of most flows on the socket,
by migrating first the flow responsible for load imbalance
4. help processes detect load imbalance,
by exporting rollover counters
Context: rollover implements flow migration in packet socket fanout
groups in case of extreme load imbalance. It is a specific
implementation of migration that minimizes reordering by selecting
the same victim socket when possible (and by selecting subsequent
victims in a round robin fashion, from which its name derives).
Changes:
v1 -> v2:
- huge flow detection: run lockless
- huge flow detection: replace stored index with random
- contention avoidance: test in packet_poll while lock held
- contention avoidance: clear pressure sooner
packet_poll and packet_recvmsg would clear only if the sock
is empty to avoid taking the necessary lock. But,
* packet_poll already holds this lock, so a lockless variant
__packet_rcv_has_room is cheap.
* packet_recvmsg is usually called only for non-ring sockets,
which also runs lockless.
- preparation: drop "single return" patch
packet_rcv_has_room is now a locked wrapper around
__packet_rcv_has_room, achieving the same (single footer).
Willem de Bruijn (6):
packet: rollover prepare: move code out of callsites
packet: rollover prepare: per-socket state
packet: rollover only to socket with headroom
packet: rollover lock contention avoidance
packet: rollover huge flows before small flows
packet: rollover statistics
include/uapi/linux/if_packet.h | 7 ++
net/packet/af_packet.c | 172 ++++++++++++++++++++++++++++++++++-------
net/packet/internal.h | 12 ++-
3 files changed, 163 insertions(+), 28 deletions(-)
--
2.2.0.rc0.207.ga3a616c
next reply other threads:[~2015-05-09 21:25 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-09 21:24 Willem de Bruijn [this message]
2015-05-09 21:24 ` [PATCH net-next v2 1/6] packet: rollover prepare: move code out of callsites Willem de Bruijn
2015-05-09 21:24 ` [PATCH net-next v2 2/6] packet: rollover prepare: per-socket state Willem de Bruijn
2015-05-09 21:24 ` [PATCH net-next v2 3/6] packet: rollover only to socket with headroom Willem de Bruijn
2015-05-09 21:24 ` [PATCH net-next v2 4/6] packet: rollover lock contention avoidance Willem de Bruijn
2015-05-09 21:25 ` [PATCH net-next v2 5/6] packet: rollover huge flows before small flows Willem de Bruijn
2015-05-09 21:25 ` [PATCH net-next v2 6/6] packet: rollover statistics Willem de Bruijn
2015-05-11 17:09 ` David Miller
2015-05-12 15:04 ` Willem de Bruijn
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1431206701-5019-1-git-send-email-willemb@google.com \
--to=willemb@google.com \
--cc=davem@davemloft.net \
--cc=david.laight@aculab.com \
--cc=eric.dumazet@gmail.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).