[PATCH net] selftests: net: let big_tcp test cope with slow env

[PATCH net] selftests: net: let big_tcp test cope with slow env

[Paolo Abeni]

In very slow environments, most big TCP cases including
segmentation and reassembly of big TCP packets have a good
chance to fail: by default the TCP client uses write size
well below 64K. If the host is low enough autocorking is
unable to build real big TCP packets.

Address the issue using much larger write operations.

Note that is hard to observe the issue without an extremely
slow and/or overloaded environment; reduce the TCP transfer
time to allow for much easier/faster reproducibility.

Fixes: 6bb382bcf742 ("selftests: add a selftest for big tcp")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/big_tcp.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh
index cde9a91c4797..2db9d15cd45f 100755
--- a/tools/testing/selftests/net/big_tcp.sh
+++ b/tools/testing/selftests/net/big_tcp.sh
@@ -122,7 +122,9 @@ do_netperf() {
 	local netns=$1
 
 	[ "$NF" = "6" ] && serip=$SERVER_IP6
-	ip net exec $netns netperf -$NF -t TCP_STREAM -H $serip 2>&1 >/dev/null
+
+	# use large write to be sure to generate big tcp packets
+	ip net exec $netns netperf -$NF -t TCP_STREAM -l 1 -H $serip -- -m 262144 2>&1 >/dev/null
 }
 
 do_test() {
-- 
2.43.0

Re: [PATCH net] selftests: net: let big_tcp test cope with slow env

[Eric Dumazet]

On Fri, Feb 2, 2024 at 5:07 PM Paolo Abeni <pabeni@redhat.com> wrote:
>
> In very slow environments, most big TCP cases including
> segmentation and reassembly of big TCP packets have a good
> chance to fail: by default the TCP client uses write size
> well below 64K. If the host is low enough autocorking is
> unable to build real big TCP packets.
>
> Address the issue using much larger write operations.
>
> Note that is hard to observe the issue without an extremely
> slow and/or overloaded environment; reduce the TCP transfer
> time to allow for much easier/faster reproducibility.
>
> Fixes: 6bb382bcf742 ("selftests: add a selftest for big tcp")
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
>  tools/testing/selftests/net/big_tcp.sh | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh
> index cde9a91c4797..2db9d15cd45f 100755
> --- a/tools/testing/selftests/net/big_tcp.sh
> +++ b/tools/testing/selftests/net/big_tcp.sh
> @@ -122,7 +122,9 @@ do_netperf() {
>         local netns=$1
>
>         [ "$NF" = "6" ] && serip=$SERVER_IP6
> -       ip net exec $netns netperf -$NF -t TCP_STREAM -H $serip 2>&1 >/dev/null
> +
> +       # use large write to be sure to generate big tcp packets
> +       ip net exec $netns netperf -$NF -t TCP_STREAM -l 1 -H $serip -- -m 262144 2>&1 >/dev/null
>  }

Interesting.

I think we set tcp_wmem[1] to 262144 in our hosts. I think netperf
default depends on tcp_wmem[1]

Reviewed-by: Eric Dumazet <edumazet@google.com>

Re: [PATCH net] selftests: net: let big_tcp test cope with slow env

[Xin Long]

On Fri, Feb 2, 2024 at 11:07 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> In very slow environments, most big TCP cases including
> segmentation and reassembly of big TCP packets have a good
> chance to fail: by default the TCP client uses write size
> well below 64K. If the host is low enough autocorking is
> unable to build real big TCP packets.
>
> Address the issue using much larger write operations.
>
> Note that is hard to observe the issue without an extremely
> slow and/or overloaded environment; reduce the TCP transfer
> time to allow for much easier/faster reproducibility.
>
> Fixes: 6bb382bcf742 ("selftests: add a selftest for big tcp")
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Xin Long <lucien.xin@gmail.com>

Re: [PATCH net] selftests: net: let big_tcp test cope with slow env

[Paolo Abeni]

On Fri, 2024-02-02 at 17:13 +0100, Eric Dumazet wrote:
> On Fri, Feb 2, 2024 at 5:07 PM Paolo Abeni <pabeni@redhat.com> wrote:
> > 
> > In very slow environments, most big TCP cases including
> > segmentation and reassembly of big TCP packets have a good
> > chance to fail: by default the TCP client uses write size
> > well below 64K. If the host is low enough autocorking is
> > unable to build real big TCP packets.
> > 
> > Address the issue using much larger write operations.
> > 
> > Note that is hard to observe the issue without an extremely
> > slow and/or overloaded environment; reduce the TCP transfer
> > time to allow for much easier/faster reproducibility.
> > 
> > Fixes: 6bb382bcf742 ("selftests: add a selftest for big tcp")
> > Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> > ---
> >  tools/testing/selftests/net/big_tcp.sh | 4 +++-
> >  1 file changed, 3 insertions(+), 1 deletion(-)
> > 
> > diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh
> > index cde9a91c4797..2db9d15cd45f 100755
> > --- a/tools/testing/selftests/net/big_tcp.sh
> > +++ b/tools/testing/selftests/net/big_tcp.sh
> > @@ -122,7 +122,9 @@ do_netperf() {
> >         local netns=$1
> > 
> >         [ "$NF" = "6" ] && serip=$SERVER_IP6
> > -       ip net exec $netns netperf -$NF -t TCP_STREAM -H $serip 2>&1 >/dev/null
> > +
> > +       # use large write to be sure to generate big tcp packets
> > +       ip net exec $netns netperf -$NF -t TCP_STREAM -l 1 -H $serip -- -m 262144 2>&1 >/dev/null
> >  }
> 
> Interesting.
> 
> I think we set tcp_wmem[1] to 262144 in our hosts. I think netperf
> default depends on tcp_wmem[1]

I haven't dug into the netperf source, but the above would be
consistent with what I observe: in my VM I see 16Kb writes and
tcp_wmem[1] is 16K.

> Reviewed-by: Eric Dumazet <edumazet@google.com>

Thanks!

Paolo

Re: [PATCH net] selftests: net: let big_tcp test cope with slow env

[patchwork-bot+netdevbpf]

Hello:

This patch was applied to netdev/net.git (main)
by David S. Miller <davem@davemloft.net>:

On Fri,  2 Feb 2024 17:06:59 +0100 you wrote:
> In very slow environments, most big TCP cases including
> segmentation and reassembly of big TCP packets have a good
> chance to fail: by default the TCP client uses write size
> well below 64K. If the host is low enough autocorking is
> unable to build real big TCP packets.
> 
> Address the issue using much larger write operations.
> 
> [...]

Here is the summary with links:
  - [net] selftests: net: let big_tcp test cope with slow env
    https://git.kernel.org/netdev/net/c/a19747c3b9bf

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html