No description
  • C 98.2%
  • Assembly 1%
  • Makefile 0.3%
  • Shell 0.2%
  • Python 0.1%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Eric Dumazet e80054ea0c tcp: fix potential xmit stalls caused by TCP_NOTSENT_LOWAT
[ Upstream commit 4bfe744ff1644fbc0a991a2677dc874475dd6776 ]

I had this bug sitting for too long in my pile, it is time to fix it.

Thanks to Doug Porter for reminding me of it!

We had various attempts in the past, including commit
0cbe6a8f089e ("tcp: remove SOCK_QUEUE_SHRUNK"),
but the issue is that TCP stack currently only generates
EPOLLOUT from input path, when tp->snd_una has advanced
and skb(s) cleaned from rtx queue.

If a flow has a big RTT, and/or receives SACKs, it is possible
that the notsent part (tp->write_seq - tp->snd_nxt) reaches 0
and no more data can be sent until tp->snd_una finally advances.

What is needed is to also check if POLLOUT needs to be generated
whenever tp->snd_nxt is advanced, from output path.

This bug triggers more often after an idle period, as
we do not receive ACK for at least one RTT. tcp_notsent_lowat
could be a fraction of what CWND and pacing rate would allow to
send during this RTT.

In a followup patch, I will remove the bogus call
to tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED)
from tcp_check_space(). Fact that we have decided to generate
an EPOLLOUT does not mean the application has immediately
refilled the transmit queue. This optimistic call
might have been the reason the bug seemed not too serious.

Tested:

200 ms rtt, 1% packet loss, 32 MB tcp_rmem[2] and tcp_wmem[2]

$ echo 500000 >/proc/sys/net/ipv4/tcp_notsent_lowat
$ cat bench_rr.sh
SUM=0
for i in {1..10}
do
 V=`netperf -H remote_host -l30 -t TCP_RR -- -r 10000000,10000 -o LOCAL_BYTES_SENT | egrep -v "MIGRATED|Bytes"`
 echo $V
 SUM=$(($SUM + $V))
done
echo SUM=$SUM

Before patch:
$ bench_rr.sh
130000000
80000000
140000000
140000000
140000000
140000000
130000000
40000000
90000000
110000000
SUM=1140000000

After patch:
$ bench_rr.sh
430000000
590000000
530000000
450000000
450000000
350000000
450000000
490000000
480000000
460000000
SUM=4680000000  # This is 410 % of the value before patch.

Fixes: c9bee3b7fd ("tcp: TCP_NOTSENT_LOWAT socket option")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Doug Porter <dsp@fb.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2022-05-09 09:03:25 +02:00
arch arm64: dts: imx8mn-ddr4-evk: Describe the 32.768 kHz PMIC clock 2022-05-09 09:03:25 +02:00
block block/compat_ioctl: fix range check in BLKGETSIZE 2022-04-27 13:50:50 +02:00
certs
crypto crypto: authenc - Fix sleep in atomic context in decrypt_tail 2022-04-15 14:18:04 +02:00
Documentation ext4, doc: fix incorrect h_reserved size 2022-04-27 13:50:50 +02:00
drivers net: hns3: add validity check for message data length 2022-05-09 09:03:25 +02:00
fs jbd2: fix a potential race while discarding reserved buffers after an abort 2022-04-27 13:50:50 +02:00
include tcp: fix potential xmit stalls caused by TCP_NOTSENT_LOWAT 2022-05-09 09:03:25 +02:00
init init/main.c: return 1 from handled __setup() functions 2022-04-15 14:18:35 +02:00
ipc shm: extend forced shm destroy to support objects from several IPC nses 2021-12-01 09:23:35 +01:00
kernel tracing: Dump stacktrace trigger to the corresponding instance 2022-04-27 13:50:45 +02:00
lib hex2bin: fix access beyond string end 2022-05-09 09:03:22 +02:00
LICENSES
mm oom_kill.c: futex: delay the OOM reaper to allow time for proper futex cleanup 2022-04-27 13:50:48 +02:00
net tcp: fix potential xmit stalls caused by TCP_NOTSENT_LOWAT 2022-05-09 09:03:25 +02:00
samples samples/kretprobes: Fix return value if register_kretprobe() failed 2021-11-17 09:48:39 +01:00
scripts gcc-plugins: latent_entropy: use /dev/urandom 2022-04-20 09:19:38 +02:00
security Fix incorrect type in assignment of ipv6 port for audit 2022-04-15 14:18:22 +02:00
sound ASoC: soc-dapm: fix two incorrect uses of list iterator 2022-04-27 13:50:49 +02:00
tools selftests: mlxsw: vxlan_flooding: Prevent flooding of unwanted packets 2022-04-27 13:50:47 +02:00
usr
virt KVM: Prevent module exit until all VMs are freed 2022-04-15 14:18:27 +02:00
.clang-format
.cocciconfig
.get_maintainer.ignore
.gitattributes
.gitignore
.mailmap
COPYING
CREDITS
Kbuild
Kconfig
MAINTAINERS
Makefile Linux 5.4.191 2022-04-27 13:50:51 +02:00
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.