Skip to content

K
Kernel

openeuler / Kernel
大约 1 年 前同步成功

通知 5
Star 0
Fork 0
K
Kernel

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 10 11月, 2017 1 次提交
  3. 05 11月, 2017 1 次提交
    • P
      tcp: higher throughput under reordering with adaptive RACK reordering wnd · 1f255691
      由 Priyaranjan Jha 提交于 
      Currently TCP RACK loss detection does not work well if packets are
being reordered beyond its static reordering window (min_rtt/4).Under
such reordering it may falsely trigger loss recoveries and reduce TCP
throughput significantly.

This patch improves that by increasing and reducing the reordering
window based on DSACK, which is now supported in major TCP implementations.
It makes RACK's reo_wnd adaptive based on DSACK and no. of recoveries.

- If DSACK is received, increment reo_wnd by min_rtt/4 (upper bounded
  by srtt), since there is possibility that spurious retransmission was
  due to reordering delay longer than reo_wnd.

- Persist the current reo_wnd value for TCP_RACK_RECOVERY_THRESH (16)
  no. of successful recoveries (accounts for full DSACK-based loss
  recovery undo). After that, reset it to default (min_rtt/4).

- At max, reo_wnd is incremented only once per rtt. So that the new
  DSACK on which we are reacting, is due to the spurious retx (approx)
  after the reo_wnd has been updated last time.

- reo_wnd is tracked in terms of steps (of min_rtt/4), rather than
  absolute value to account for change in rtt.

In our internal testing, we observed significant increase in throughput,
in scenarios where reordering exceeds min_rtt/4 (previous static value).
Signed-off-by: NPriyaranjan Jha <priyarjha@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      1f255691
  5. 01 11月, 2017 1 次提交
  7. 29 10月, 2017 1 次提交
  9. 28 10月, 2017 13 次提交
  11. 27 10月, 2017 15 次提交
  13. 26 10月, 2017 1 次提交
  15. 24 10月, 2017 1 次提交
    • C
      tcp: Configure TFO without cookie per socket and/or per route · 71c02379
      由 Christoph Paasch 提交于 
      We already allow to enable TFO without a cookie by using the
fastopen-sysctl and setting it to TFO_SERVER_COOKIE_NOT_REQD (or
TFO_CLIENT_NO_COOKIE).
This is safe to do in certain environments where we know that there
isn't a malicous host (aka., data-centers) or when the
application-protocol already provides an authentication mechanism in the
first flight of data.

A server however might be providing multiple services or talking to both
sides (public Internet and data-center). So, this server would want to
enable cookie-less TFO for certain services and/or for connections that
go to the data-center.

This patch exposes a socket-option and a per-route attribute to enable such
fine-grained configurations.
Signed-off-by: NChristoph Paasch <cpaasch@apple.com>
Reviewed-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      71c02379
  17. 20 10月, 2017 2 次提交
  19. 13 10月, 2017 1 次提交
  21. 12 10月, 2017 1 次提交
    • E
      tcp: fix tcp_unlink_write_queue() · 4a269818
      由 Eric Dumazet 提交于 
      Yury reported crash with this signature :

[  554.034021] [<ffff80003ccd5a58>] 0xffff80003ccd5a58
[  554.034156] [<ffff00000888fd34>] skb_release_all+0x14/0x30
[  554.034288] [<ffff00000888fd64>] __kfree_skb+0x14/0x28
[  554.034409] [<ffff0000088ece6c>] tcp_sendmsg_locked+0x4dc/0xcc8
[  554.034541] [<ffff0000088ed68c>] tcp_sendmsg+0x34/0x58
[  554.034659] [<ffff000008919fd4>] inet_sendmsg+0x2c/0xf8
[  554.034783] [<ffff0000088842e8>] sock_sendmsg+0x18/0x30
[  554.034928] [<ffff0000088861fc>] SyS_sendto+0x84/0xf8

Problem is that skb->destructor contains garbage, and this is
because I accidentally removed tcp_skb_tsorted_anchor_cleanup()
from tcp_unlink_write_queue()

This would trigger with a write(fd, <invalid_memory>, len) attempt,
and we will add to packetdrill this capability to avoid future
regressions.

Fixes: 75c119af ("tcp: implement rb-tree based retransmit queue")
Reported-by: NYury Norov <ynorov@caviumnetworks.com>
Tested-by: NYury Norov <ynorov@caviumnetworks.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      4a269818
  23. 07 10月, 2017 2 次提交
    • E
      tcp: implement rb-tree based retransmit queue · 75c119af
      由 Eric Dumazet 提交于 
      Using a linear list to store all skbs in write queue has been okay
for quite a while : O(N) is not too bad when N < 500.

Things get messy when N is the order of 100,000 : Modern TCP stacks
want 10Gbit+ of throughput even with 200 ms RTT flows.

40 ns per cache line miss means a full scan can use 4 ms,
blowing away CPU caches.

SACK processing often can use various hints to avoid parsing
whole retransmit queue. But with high packet losses and/or high
reordering, hints no longer work.

Sender has to process thousands of unfriendly SACK, accumulating
a huge socket backlog, burning a cpu and massively dropping packets.

Using an rb-tree for retransmit queue has been avoided for years
because it added complexity and overhead, but now is the time
to be more resistant and say no to quadratic behavior.

1) RTX queue is no longer part of the write queue : already sent skbs
are stored in one rb-tree.

2) Since reaching the head of write queue no longer needs
sk->sk_send_head, we added an union of sk_send_head and tcp_rtx_queue

Tested:

 On receiver :
 netem on ingress : delay 150ms 200us loss 1
 GRO disabled to force stress and SACK storms.

for f in `seq 1 10`
do
 ./netperf -H lpaa6 -l30 -- -K bbr -o THROUGHPUT|tail -1
done | awk '{print $0} {sum += $0} END {printf "%7u\n",sum}'

Before patch :

323.87
351.48
339.59
338.62
306.72
204.07
304.93
291.88
202.47
176.88
   2840

After patch:

1700.83
2207.98
2070.17
1544.26
2114.76
2124.89
1693.14
1080.91
2216.82
1299.94
  18053
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      75c119af
    • E
      tcp: uninline tcp_write_queue_purge() · ac3f09ba
      由 Eric Dumazet 提交于 
      Since the upcoming rtx rbtree will add some extra code,
it is time to not inline this fat function anymore.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      ac3f09ba