linux/include
Eric Dumazet 46d3ceabd8 tcp: TCP Small Queues
This introduce TSQ (TCP Small Queues)

TSQ goal is to reduce number of TCP packets in xmit queues (qdisc &
device queues), to reduce RTT and cwnd bias, part of the bufferbloat
problem.

sk->sk_wmem_alloc not allowed to grow above a given limit,
allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a
given time.

TSO packets are sized/capped to half the limit, so that we have two
TSO packets in flight, allowing better bandwidth use.

As a side effect, setting the limit to 40000 automatically reduces the
standard gso max limit (65536) to 40000/2 : It can help to reduce
latencies of high prio packets, having smaller TSO packets.

This means we divert sock_wfree() to a tcp_wfree() handler, to
queue/send following frames when skb_orphan() [2] is called for the
already queued skbs.

Results on my dev machines (tg3/ixgbe nics) are really impressive,
using standard pfifo_fast, and with or without TSO/GSO.

Without reduction of nominal bandwidth, we have reduction of buffering
per bulk sender :
< 1ms on Gbit (instead of 50ms with TSO)
< 8ms on 100Mbit (instead of 132 ms)

I no longer have 4 MBytes backlogged in qdisc by a single netperf
session, and both side socket autotuning no longer use 4 Mbytes.

As skb destructor cannot restart xmit itself ( as qdisc lock might be
taken at this point ), we delegate the work to a tasklet. We use one
tasklest per cpu for performance reasons.

If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag.
This flag is tested in a new protocol method called from release_sock(),
to eventually send new segments.

[1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable
[2] skb_orphan() is usually called at TX completion time,
  but some drivers call it in their start_xmit() handler.
  These drivers should at least use BQL, or else a single TCP
  session can still fill the whole NIC TX ring, since TSQ will
  have no effect.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Dave Taht <dave.taht@bufferbloat.net>
Cc: Tom Herbert <therbert@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 18:12:59 -07:00
..
acpi ACPI: fix acpi_bus.h build warnings when ACPI is not enabled 2012-06-04 00:29:11 -04:00
asm-generic bug.h: Fix up CONFIG_BUG=n implicit function declarations. 2012-06-25 10:32:49 -07:00
crypto
drm drm: drop comment about this header being autogenerated. 2012-06-22 11:04:55 +01:00
keys
linux tcp: TCP Small Queues 2012-07-11 18:12:59 -07:00
math-emu
media [media] patch for Asus My Cinema PS3-100 (1043:48cd) 2012-05-20 16:05:02 -03:00
memory
misc
mtd UBI: amend commentaries WRT dtype 2012-05-20 20:25:59 +03:00
net tcp: TCP Small Queues 2012-07-11 18:12:59 -07:00
pcmcia
rdma Merge branches 'core', 'cxgb4', 'ipath', 'iser', 'lockdep', 'mlx4', 'nes', 'ocrdma', 'qib' and 'raw-qp' into for-linus 2012-05-21 09:00:47 -07:00
rxrpc
scsi SCSI & usb-storage: add try_rc_10_first flag 2012-06-22 22:05:31 -07:00
sound Merge branch 'v4l_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media 2012-06-25 14:53:09 -07:00
target target: Add TFO->put_session() caller for HW fabric session shutdown 2012-06-12 19:33:05 -07:00
trace rcu: Update RCU_FAST_NO_HZ tracing for lazy callbacks 2012-06-06 20:43:27 -07:00
video fbdev updates for 3.5 2012-06-01 16:57:51 -07:00
xen xen: do not map the same GSI twice in PVHVM guests. 2012-05-21 14:11:36 -04:00
Kbuild