Re: [vpp-dev] Risc-V Compilation Error

[Hrishikesh Karanjikar]

Hi Damjan,

Thanks a lot.
I am already trying a similar fix.
I will get your fix and let you know further progress.

Thanks,
Hrishikesh

On Wed, Jan 19, 2022 at 10:45 PM Damjan Marion  wrote:

>
> This may help you:
>
> https://gerrit.fd.io/r/c/vpp/+/34972
>
> —
> Damjan
>
>
>
> On 19.01.2022., at 11:15, Hrishikesh Karanjikar <
> hrishikesh.karanji...@gmail.com> wrote:
>
> Hi,
>
> I am trying to compile vpp on the SiFive HiFive Unmatched board.
> Following is my build environment
>
> ==
>
>
> ubuntu@ubuntu:~/work/vpp$ uname -a
> Linux ubuntu 5.13.0-1008-generic #8-Ubuntu SMP Fri Jan 7 18:50:29 UTC 2022
> riscv64 riscv64 riscv64 GNU/Linux
>
> ubuntu@ubuntu:~/work/vpp$ lsb_release -a
> No LSB modules are available.
> Distributor ID: Ubuntu
> Description: Ubuntu 21.10
> Release: 21.10
> Codename: impish
>
> ==
> I am using the latest master branch for VPP.
> I am getting the following compilation error. I have changed the
> default-clang format to 11.
>
> ==
> ubuntu@ubuntu:~/work/vpp$ make pkg-deb
> make[1]: Entering directory '/home/ubuntu/work/vpp/build-root'
>  Arch for platform 'vpp' is native 
>  Finding source for external 
>  Makefile fragment found in /home/ubuntu/work/vpp/build-data/packages/
> external.mk 
>  Source found in /home/ubuntu/work/vpp/build 
>  Arch for platform 'vpp' is native 
>  Finding source for vpp 
>  Makefile fragment found in /home/ubuntu/work/vpp/build-data/packages/
> vpp.mk 
>  Source found in /home/ubuntu/work/vpp/src 
> find: ‘/home/ubuntu/work/vpp/build-root/config.site’: No such file or
> directory
>  Configuring external: nothing to do 
>  Building external in
> /home/ubuntu/work/vpp/build-root/build-vpp-native/external 
>
>  Installing external: nothing to do 
> find: ‘/home/ubuntu/work/vpp/build-root/config.site’: No such file or
> directory
>  Configuring vpp: nothing to do 
>  Building vpp in /home/ubuntu/work/vpp/build-root/build-vpp-native/vpp
> 
> [2/1501] Building C object
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o
> FAILED: CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o
> ccache /usr/lib/ccache/clang-13 --target=riscv64-linux-gnu -DHAVE_FCNTL64
> -D_FORTIFY_SOURCE=2 -I/home/ubuntu/work/vpp/src -ICMakeFiles -fPIC
> -fvisibility=hidden -g -Werror -Wall -Wno-address-of-packed-member -O3
> -fstack-protector -fno-common -MD -MT
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o -MF
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o.d -o
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o -c
> /home/ubuntu/work/vpp/src/vppinfra/cpu.c
> /home/ubuntu/work/vpp/src/vppinfra/cpu.c:203:1: error: unused function
> 'flag_skip_prefix' [-Werror,-Wunused-function]
> flag_skip_prefix (char const *flag, const char *pfx, int len)
> ^
> 1 error generated.
> [5/1501] Building C object
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/format.c.o
> ninja: build stopped: subcommand failed.
> make[1]: *** [Makefile:693: vpp-build] Error 1
> make[1]: Leaving directory '/home/ubuntu/work/vpp/build-root'
> make: *** [Makefile:593: pkg-deb] Error 2
>
> ==
>
>
> --
>
> Regards,
> Hrishikesh Karanjikar
>
> 
>
>
>

-- 

Regards,
Hrishikesh Karanjikar

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20765): https://lists.fd.io/g/vpp-dev/message/20765
Mute This Topic: https://lists.fd.io/mt/88531162/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

[vpp-dev] SNAT, nat44 with static mapping of whole subnet

[Adrian Imboden]

Hi all

I'm using vpp only recently and I am very happy with the way it works.

I am currently trying to replace my linux based router with a linux 
based vpp router.


- I use version release 21.10
- I have a small ipv4 /24 network and an additional static ip
- I have multiple subnets (test1, test2 in the example)

What I want to do is:
- Do SNAT
- Map each subnet to a single ipv4 address
- For my test: assume 10.10.100.50-10.10.100.52 are my public ips

What I have now is the following:
```
comment { == setting up testnet1 }
create tap id 1 host-if-name testnet1 host-ip4-addr 192.168.10.1/23
create loopback interface instance 1
set interface ip address loop1 192.168.10.255/23

set int l2 bridge tap1 1
set int l2 bridge loop1 1 bvi
set int l2 bridge TenGigabitEthernet8/0/0 1

comment { == setting up testnet2 }
create tap id 2 host-if-name testnet2 host-ip4-addr 192.168.12.1/23
create loopback interface instance 2
set interface ip address loop2 192.168.12.255/23

set int l2 bridge tap2 2
set int l2 bridge loop2 2 bvi


set interface ip address TenGigabitEtherneta/0/3 10.10.100.50/23
set interface ip address TenGigabitEtherneta/0/3 10.10.100.51/23
set interface ip address TenGigabitEtherneta/0/3 10.10.100.52/23

nat44 enable

nat44 add address 10.10.100.50
nat44 add address 10.10.100.51
nat44 add address 10.10.100.52
set interface nat44 out TenGigabitEtherneta/0/3
set interface nat44 in loop1
set interface nat44 in loop2

ip route add 10.10.100.0/23 via TenGigabitEtherneta/0/3

comment { = port forwarding }
det44 add static mapping udp local 102.168.10.33 1234 external 
10.10.100.51 1234



comment { enable all interfaces }
set int state tap1 up
set int state loop1 up
set int state TenGigabitEthernet8/0/0 up
set int state tap2 up
set int state loop2 up
set int state TenGigabitEtherneta/0/3 up
```



Now I have the problem that only 10.10.100.50 gets used (or until the 
ports are used up I assume).

det44 would support my use case with:
```
det44 add in 192.168.10.0/23 out 10.10.100.51/32
det44 add in 192.168.20.0/23 out 10.10.100.52/32
```

but det44 does not support port forwarding.

and nat44 only supports mapping each host one by one.
In my case I could add all IPs (512 IPs per net). Not pretty, but doable.


My questions:
Do I have an error in my thoughts?

Is there something like this planned?:
```
nat44 add static mapping local 192.168.10.0/23 external 10.10.100.51
```

If not, would this addition be ok? If yes, I may invest some coding time :)


Thanks very much and greetings
Adrian

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20764): https://lists.fd.io/g/vpp-dev/message/20764
Mute This Topic: https://lists.fd.io/mt/88549403/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

[vpp-dev] VPP 22.02 RC1 milestone is complete!

[Andrew Yourtchenko]

Hi all,

the VPP 22.02 RC1 milestone is complete!

The master branch is open for all commits, the stable/2202 is open for
the bugfixes (other than the exception related to the wireguard that
was discussed in the other thread today).

The artifacts are available at the packagecloud.io/fdio/2202

The RC2 milestone is on the 9th of February 2022.

Thanks a lot!

--a /* your friendly 22.02 release manager */

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20763): https://lists.fd.io/g/vpp-dev/message/20763
Mute This Topic: https://lists.fd.io/mt/88543995/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Risc-V Compilation Error

[Damjan Marion via lists.fd.io]

This may help you:

https://gerrit.fd.io/r/c/vpp/+/34972 

— 
Damjan



> On 19.01.2022., at 11:15, Hrishikesh Karanjikar 
>  wrote:
> 
> Hi,
> 
> I am trying to compile vpp on the SiFive HiFive Unmatched board.
> Following is my build environment
> 
> ==
> 
> 
> ubuntu@ubuntu:~/work/vpp$ uname -a
> Linux ubuntu 5.13.0-1008-generic #8-Ubuntu SMP Fri Jan 7 18:50:29 UTC 2022 
> riscv64 riscv64 riscv64 GNU/Linux
> 
> ubuntu@ubuntu:~/work/vpp$ lsb_release -a
> No LSB modules are available.
> Distributor ID: Ubuntu
> Description: Ubuntu 21.10
> Release: 21.10
> Codename: impish
> 
> ==
> I am using the latest master branch for VPP.
> I am getting the following compilation error. I have changed the 
> default-clang format to 11.
> 
> ==
> ubuntu@ubuntu:~/work/vpp$ make pkg-deb
> make[1]: Entering directory '/home/ubuntu/work/vpp/build-root'
>  Arch for platform 'vpp' is native 
>  Finding source for external 
>  Makefile fragment found in 
> /home/ubuntu/work/vpp/build-data/packages/external.mk  
> 
>  Source found in /home/ubuntu/work/vpp/build 
>  Arch for platform 'vpp' is native 
>  Finding source for vpp 
>  Makefile fragment found in 
> /home/ubuntu/work/vpp/build-data/packages/vpp.mk  
>  Source found in /home/ubuntu/work/vpp/src 
> find: ‘/home/ubuntu/work/vpp/build-root/config.site’: No such file or 
> directory
>  Configuring external: nothing to do 
>  Building external in 
> /home/ubuntu/work/vpp/build-root/build-vpp-native/external 
> 
>  Installing external: nothing to do 
> find: ‘/home/ubuntu/work/vpp/build-root/config.site’: No such file or 
> directory
>  Configuring vpp: nothing to do 
>  Building vpp in /home/ubuntu/work/vpp/build-root/build-vpp-native/vpp 
> 
> [2/1501] Building C object 
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o
> FAILED: CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o 
> ccache /usr/lib/ccache/clang-13 --target=riscv64-linux-gnu -DHAVE_FCNTL64 
> -D_FORTIFY_SOURCE=2 -I/home/ubuntu/work/vpp/src -ICMakeFiles -fPIC   
> -fvisibility=hidden -g -Werror -Wall -Wno-address-of-packed-member -O3 
> -fstack-protector -fno-common -MD -MT 
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o -MF 
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o.d -o 
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o -c 
> /home/ubuntu/work/vpp/src/vppinfra/cpu.c
> /home/ubuntu/work/vpp/src/vppinfra/cpu.c:203:1: error: unused function 
> 'flag_skip_prefix' [-Werror,-Wunused-function]
> flag_skip_prefix (char const *flag, const char *pfx, int len)
> ^
> 1 error generated.
> [5/1501] Building C object 
> CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/format.c.o
> ninja: build stopped: subcommand failed.
> make[1]: *** [Makefile:693: vpp-build] Error 1
> make[1]: Leaving directory '/home/ubuntu/work/vpp/build-root'
> make: *** [Makefile:593: pkg-deb] Error 2
> 
> ==
> 
> 
> -- 
> 
> Regards,
> Hrishikesh Karanjikar
> 
> 
> 


-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20762): https://lists.fd.io/g/vpp-dev/message/20762
Mute This Topic: https://lists.fd.io/mt/88531162/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Is it too late for Wireguard patches getting in for VPP22.02?

[Fan Zhang]

Thanks Matthew to point this out.

To add a bit more detail here
Wireguard data-path encryption and decryption uses aad size of 0. Hence we have 
to add new async AEAD op ID to represent this aad size.

Regards,
Fan

From: Matthew Smith 
Sent: Wednesday, January 19, 2022 4:36 PM
To: Andrew  Yourtchenko 
Cc: Zhang, Roy Fan ; vpp-dev ; 
Andrew Yourtchenko (ayourtch) ; Kinsella, Ray 
; Oginski, GabrielX 
Subject: Re: [vpp-dev] Is it too late for Wireguard patches getting in for 
VPP22.02?
Asdfasd
Hi Andrew,

The change in crypto.h that you called out as being whitespace-only actually 
changes more than whitespace... It also appends '_ (CHACHA20_POLY1305, 
"chacha20-poly1305", 32, 16, 0)' to foreach_crypto_aead_async_alg.

-Matt


On Wed, Jan 19, 2022 at 10:21 AM Andrew  Yourtchenko 
mailto:ayour...@gmail.com>> wrote:
Hi Fan,

With my release manager hat on:

the first three patches are solely contained (minus seemingly
whitespace change in 34660? can it be avoided ?) within wireguard
plugin, which has "experimental" status, with which I would be happy
to err on the side of keeping the velocity - so once the nit i pointed
out is taken care of, I would be happy to merge the cherry-picks into
the stable/2202, provided it is "soon" for some very proximate value
of "soon" :)

the last patch  to crypto-dev is an improvement, and looks fairly
straightforward addition, backwards compatible, and was +2'd by Damjan
back in December. So, from the "technical" standpoint it should have
been in, but there was new year break period, etc, etc. So I would
again would be fine with merging the cherry-pick into stable/2202, but
for this one" the value of "soon" should not exceed "end of this
week".

In case no-one from the community objects to the above by this Friday
12:00 UTC, let's get these as cherry-picks into stable/2202.

(p.s.: the 22.02 RC1 is not tagged yet, but the v22.06-rc0 tag is
already on master, I would rather not mess with that).

--a


On 1/19/22, Fan Zhang mailto:roy.fan.zh...@intel.com>> 
wrote:
> Hi,
>
> Sorry for the late notice, but we have a bunch of patches waiting to be
> reviewed/merged if possible for VPP22.02.
>
> The patches do 2 things
>
>   *   Optimizing wireguard performance by introducing burst processing of
> packets and chacha-poly encryption/decryption.
>   *   Adding async mode to wireguard so the crypto can be processed by
> sw-crypto-scheduler or QAT.
>
> They are
> https://gerrit.fd.io/r/c/vpp/+/34324
> https://gerrit.fd.io/r/c/vpp/+/34660/2
> https://gerrit.fd.io/r/c/vpp/+/34661/2
> https://gerrit.fd.io/r/c/vpp/+/34662/4
>
> We know the patches are not perfect - as Matthew already pointed out there
> are some improvements can be done (thank you very much Matthew!).
> The bottom line is
>
>   *   They passed the wireguard unit tests, and we will keep improving
> them.
>   *   The code change had >5% performance improvement with small packets.
>
> But are they too late for VPP22.02? Much appreciate for the help in
> advance!
>
> Regards,
> fan
>
>
>

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20761): https://lists.fd.io/g/vpp-dev/message/20761
Mute This Topic: https://lists.fd.io/mt/88537247/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Is it too late for Wireguard patches getting in for VPP22.02?

[Matthew Smith via lists.fd.io]

Hi Andrew,

The change in crypto.h that you called out as being whitespace-only
actually changes more than whitespace... It also appends '_
(CHACHA20_POLY1305, "chacha20-poly1305", 32, 16, 0)'
to foreach_crypto_aead_async_alg.

-Matt


On Wed, Jan 19, 2022 at 10:21 AM Andrew  Yourtchenko 
wrote:

> Hi Fan,
>
> With my release manager hat on:
>
> the first three patches are solely contained (minus seemingly
> whitespace change in 34660? can it be avoided ?) within wireguard
> plugin, which has "experimental" status, with which I would be happy
> to err on the side of keeping the velocity - so once the nit i pointed
> out is taken care of, I would be happy to merge the cherry-picks into
> the stable/2202, provided it is "soon" for some very proximate value
> of "soon" :)
>
> the last patch  to crypto-dev is an improvement, and looks fairly
> straightforward addition, backwards compatible, and was +2'd by Damjan
> back in December. So, from the "technical" standpoint it should have
> been in, but there was new year break period, etc, etc. So I would
> again would be fine with merging the cherry-pick into stable/2202, but
> for this one" the value of "soon" should not exceed "end of this
> week".
>
> In case no-one from the community objects to the above by this Friday
> 12:00 UTC, let's get these as cherry-picks into stable/2202.
>
> (p.s.: the 22.02 RC1 is not tagged yet, but the v22.06-rc0 tag is
> already on master, I would rather not mess with that).
>
> --a
>
>
> On 1/19/22, Fan Zhang  wrote:
> > Hi,
> >
> > Sorry for the late notice, but we have a bunch of patches waiting to be
> > reviewed/merged if possible for VPP22.02.
> >
> > The patches do 2 things
> >
> >   *   Optimizing wireguard performance by introducing burst processing of
> > packets and chacha-poly encryption/decryption.
> >   *   Adding async mode to wireguard so the crypto can be processed by
> > sw-crypto-scheduler or QAT.
> >
> > They are
> > https://gerrit.fd.io/r/c/vpp/+/34324
> > https://gerrit.fd.io/r/c/vpp/+/34660/2
> > https://gerrit.fd.io/r/c/vpp/+/34661/2
> > https://gerrit.fd.io/r/c/vpp/+/34662/4
> >
> > We know the patches are not perfect - as Matthew already pointed out
> there
> > are some improvements can be done (thank you very much Matthew!).
> > The bottom line is
> >
> >   *   They passed the wireguard unit tests, and we will keep improving
> > them.
> >   *   The code change had >5% performance improvement with small packets.
> >
> > But are they too late for VPP22.02? Much appreciate for the help in
> > advance!
> >
> > Regards,
> > fan
> >
> >
> >
>

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20760): https://lists.fd.io/g/vpp-dev/message/20760
Mute This Topic: https://lists.fd.io/mt/88537247/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Is it too late for Wireguard patches getting in for VPP22.02?

[Fan Zhang]

Hi Andrew,

Thanks a mil!
Will address them ASAP.

Regards,
Fan

> -Original Message-
> From: vpp-dev@lists.fd.io  On Behalf Of Andrew
> Yourtchenko
> Sent: Wednesday, January 19, 2022 4:21 PM
> To: Zhang, Roy Fan 
> Cc: vpp-dev ; Andrew Yourtchenko (ayourtch)
> ; Kinsella, Ray ; Oginski,
> GabrielX ; Smith, Matthew
> 
> Subject: Re: [vpp-dev] Is it too late for Wireguard patches getting in for
> VPP22.02?
> 
> Hi Fan,
> 
> With my release manager hat on:
> 
> the first three patches are solely contained (minus seemingly
> whitespace change in 34660? can it be avoided ?) within wireguard
> plugin, which has "experimental" status, with which I would be happy
> to err on the side of keeping the velocity - so once the nit i pointed
> out is taken care of, I would be happy to merge the cherry-picks into
> the stable/2202, provided it is "soon" for some very proximate value
> of "soon" :)
> 
> the last patch  to crypto-dev is an improvement, and looks fairly
> straightforward addition, backwards compatible, and was +2'd by Damjan
> back in December. So, from the "technical" standpoint it should have
> been in, but there was new year break period, etc, etc. So I would
> again would be fine with merging the cherry-pick into stable/2202, but
> for this one" the value of "soon" should not exceed "end of this
> week".
> 
> In case no-one from the community objects to the above by this Friday
> 12:00 UTC, let's get these as cherry-picks into stable/2202.
> 
> (p.s.: the 22.02 RC1 is not tagged yet, but the v22.06-rc0 tag is
> already on master, I would rather not mess with that).
> 
> --a
> 
> 
> On 1/19/22, Fan Zhang  wrote:
> > Hi,
> >
> > Sorry for the late notice, but we have a bunch of patches waiting to be
> > reviewed/merged if possible for VPP22.02.
> >
> > The patches do 2 things
> >
> >   *   Optimizing wireguard performance by introducing burst processing of
> > packets and chacha-poly encryption/decryption.
> >   *   Adding async mode to wireguard so the crypto can be processed by
> > sw-crypto-scheduler or QAT.
> >
> > They are
> > https://gerrit.fd.io/r/c/vpp/+/34324
> > https://gerrit.fd.io/r/c/vpp/+/34660/2
> > https://gerrit.fd.io/r/c/vpp/+/34661/2
> > https://gerrit.fd.io/r/c/vpp/+/34662/4
> >
> > We know the patches are not perfect - as Matthew already pointed out
> there
> > are some improvements can be done (thank you very much Matthew!).
> > The bottom line is
> >
> >   *   They passed the wireguard unit tests, and we will keep improving
> > them.
> >   *   The code change had >5% performance improvement with small
> packets.
> >
> > But are they too late for VPP22.02? Much appreciate for the help in
> > advance!
> >
> > Regards,
> > fan
> >
> >
> >

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20759): https://lists.fd.io/g/vpp-dev/message/20759
Mute This Topic: https://lists.fd.io/mt/88537247/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Is it too late for Wireguard patches getting in for VPP22.02?

[Andrew Yourtchenko]

Hi Fan,

With my release manager hat on:

the first three patches are solely contained (minus seemingly
whitespace change in 34660? can it be avoided ?) within wireguard
plugin, which has "experimental" status, with which I would be happy
to err on the side of keeping the velocity - so once the nit i pointed
out is taken care of, I would be happy to merge the cherry-picks into
the stable/2202, provided it is "soon" for some very proximate value
of "soon" :)

the last patch  to crypto-dev is an improvement, and looks fairly
straightforward addition, backwards compatible, and was +2'd by Damjan
back in December. So, from the "technical" standpoint it should have
been in, but there was new year break period, etc, etc. So I would
again would be fine with merging the cherry-pick into stable/2202, but
for this one" the value of "soon" should not exceed "end of this
week".

In case no-one from the community objects to the above by this Friday
12:00 UTC, let's get these as cherry-picks into stable/2202.

(p.s.: the 22.02 RC1 is not tagged yet, but the v22.06-rc0 tag is
already on master, I would rather not mess with that).

--a


On 1/19/22, Fan Zhang  wrote:
> Hi,
>
> Sorry for the late notice, but we have a bunch of patches waiting to be
> reviewed/merged if possible for VPP22.02.
>
> The patches do 2 things
>
>   *   Optimizing wireguard performance by introducing burst processing of
> packets and chacha-poly encryption/decryption.
>   *   Adding async mode to wireguard so the crypto can be processed by
> sw-crypto-scheduler or QAT.
>
> They are
> https://gerrit.fd.io/r/c/vpp/+/34324
> https://gerrit.fd.io/r/c/vpp/+/34660/2
> https://gerrit.fd.io/r/c/vpp/+/34661/2
> https://gerrit.fd.io/r/c/vpp/+/34662/4
>
> We know the patches are not perfect - as Matthew already pointed out there
> are some improvements can be done (thank you very much Matthew!).
> The bottom line is
>
>   *   They passed the wireguard unit tests, and we will keep improving
> them.
>   *   The code change had >5% performance improvement with small packets.
>
> But are they too late for VPP22.02? Much appreciate for the help in
> advance!
>
> Regards,
> fan
>
>
>

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20758): https://lists.fd.io/g/vpp-dev/message/20758
Mute This Topic: https://lists.fd.io/mt/88537247/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] test performance of nginx using vpp host stack#nginx

[Florin Coras]

Hi, 

I see that some configs have been changed compared to our private conversation. 
Did that influence results?

Nonetheless I’d try with the configs lower. In particular, I noticed you 
changed default buffer size, numa heap size and remove multi-seg support which 
are not optimal.

Regards,
Florin

startup.conf 

session {
  enable
  use-app-socket-api
  event-queue-length 1024000
 }

cpu {
 main-core 0
 corelist-workers 1
}

buffers {
 buffers-per-numa 16384
}

 dpdk {
dev  {
num-rx-queues 1
num-rx-desc 256
num-tx-desc 256
 }
}

vcl.conf
segment-size 80
add-segment-size 80
rx-fifo-size 400 
tx-fifo-size 400

nginx.conf
worker_processes 4

> On Jan 19, 2022, at 2:21 AM, weizhen9...@163.com wrote:
> 
> The version of vpp is:
> 
> The config of vpp and nginx is the attachment. The vcl config is attachment.
> 
> 
> The type of nic is:
> 
> 
> 
> 


-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20757): https://lists.fd.io/g/vpp-dev/message/20757
Mute This Topic: https://lists.fd.io/mt/88456731/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

[vpp-dev] Is it too late for Wireguard patches getting in for VPP22.02?

[Fan Zhang]

Hi,

Sorry for the late notice, but we have a bunch of patches waiting to be 
reviewed/merged if possible for VPP22.02.

The patches do 2 things

  *   Optimizing wireguard performance by introducing burst processing of 
packets and chacha-poly encryption/decryption.
  *   Adding async mode to wireguard so the crypto can be processed by 
sw-crypto-scheduler or QAT.

They are
https://gerrit.fd.io/r/c/vpp/+/34324
https://gerrit.fd.io/r/c/vpp/+/34660/2
https://gerrit.fd.io/r/c/vpp/+/34661/2
https://gerrit.fd.io/r/c/vpp/+/34662/4

We know the patches are not perfect - as Matthew already pointed out there are 
some improvements can be done (thank you very much Matthew!).
The bottom line is

  *   They passed the wireguard unit tests, and we will keep improving them.
  *   The code change had >5% performance improvement with small packets.

But are they too late for VPP22.02? Much appreciate for the help in advance!

Regards,
fan



-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20756): https://lists.fd.io/g/vpp-dev/message/20756
Mute This Topic: https://lists.fd.io/mt/88537247/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Request: Help in selecting interface for inter-container networking.

[Pragya Nand Bhagat]

Hi Ben,

Thanks a lot for the reply.

could you please briefly elaborate on what scenarios do people use virto-user
- vhost-user ?

I see that DPDK document lists virtio_user for container networking.

I'm referring the following link:
https://doc.dpdk.org/guides/howto/virtio_user_for_container_networking.html

Thank You
Pragya Nand



On Wed, Jan 19, 2022 at 2:33 PM Benoit Ganne (bganne) 
wrote:

> Hi,
>
> > I'm trying to create an inter-container link A<-->B for high speed data
> > transfer.
> > I'm having a Container application on one side and Virtual-router(based
> on
> > vpp) on the other side.
> > I have a choice between a virtio-user - vhost-user pair or use a MemIf
> > interface.
>
> We usually use memif which was designed exactly for this. Memif is lighter
> than virtio and your application can use eg. libmemif.
>
> Best
> ben
>

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20755): https://lists.fd.io/g/vpp-dev/message/20755
Mute This Topic: https://lists.fd.io/mt/88530304/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] test performance of nginx using vpp host stack#nginx

[weizhen9612]

The version of vpp is:

The config of vpp and nginx is the attachment. The vcl config is attachment.

The type of nic is:


nginx.conf
Description: Binary data


startup.conf
Description: Binary data


vcl_test.conf
Description: Binary data

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20754): https://lists.fd.io/g/vpp-dev/message/20754
Mute This Topic: https://lists.fd.io/mt/88456731/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

[vpp-dev] Risc-V Compilation Error

[Hrishikesh Karanjikar]

Hi,

I am trying to compile vpp on the SiFive HiFive Unmatched board.
Following is my build environment

==


ubuntu@ubuntu:~/work/vpp$ uname -a
Linux ubuntu 5.13.0-1008-generic #8-Ubuntu SMP Fri Jan 7 18:50:29 UTC 2022
riscv64 riscv64 riscv64 GNU/Linux

ubuntu@ubuntu:~/work/vpp$ lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description: Ubuntu 21.10
Release: 21.10
Codename: impish

==
I am using the latest master branch for VPP.
I am getting the following compilation error. I have changed the
default-clang format to 11.

==
ubuntu@ubuntu:~/work/vpp$ make pkg-deb
make[1]: Entering directory '/home/ubuntu/work/vpp/build-root'
 Arch for platform 'vpp' is native 
 Finding source for external 
 Makefile fragment found in /home/ubuntu/work/vpp/build-data/packages/
external.mk 
 Source found in /home/ubuntu/work/vpp/build 
 Arch for platform 'vpp' is native 
 Finding source for vpp 
 Makefile fragment found in /home/ubuntu/work/vpp/build-data/packages/
vpp.mk 
 Source found in /home/ubuntu/work/vpp/src 
find: ‘/home/ubuntu/work/vpp/build-root/config.site’: No such file or
directory
 Configuring external: nothing to do 
 Building external in
/home/ubuntu/work/vpp/build-root/build-vpp-native/external 

 Installing external: nothing to do 
find: ‘/home/ubuntu/work/vpp/build-root/config.site’: No such file or
directory
 Configuring vpp: nothing to do 
 Building vpp in /home/ubuntu/work/vpp/build-root/build-vpp-native/vpp

[2/1501] Building C object
CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o
FAILED: CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o
ccache /usr/lib/ccache/clang-13 --target=riscv64-linux-gnu -DHAVE_FCNTL64
-D_FORTIFY_SOURCE=2 -I/home/ubuntu/work/vpp/src -ICMakeFiles -fPIC
-fvisibility=hidden -g -Werror -Wall -Wno-address-of-packed-member -O3
-fstack-protector -fno-common -MD -MT
CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o -MF
CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o.d -o
CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/cpu.c.o -c
/home/ubuntu/work/vpp/src/vppinfra/cpu.c
/home/ubuntu/work/vpp/src/vppinfra/cpu.c:203:1: error: unused function
'flag_skip_prefix' [-Werror,-Wunused-function]
flag_skip_prefix (char const *flag, const char *pfx, int len)
^
1 error generated.
[5/1501] Building C object
CMakeFiles/vppinfra/CMakeFiles/vppinfra_objs.dir/format.c.o
ninja: build stopped: subcommand failed.
make[1]: *** [Makefile:693: vpp-build] Error 1
make[1]: Leaving directory '/home/ubuntu/work/vpp/build-root'
make: *** [Makefile:593: pkg-deb] Error 2

==


-- 

Regards,
Hrishikesh Karanjikar

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20753): https://lists.fd.io/g/vpp-dev/message/20753
Mute This Topic: https://lists.fd.io/mt/88531162/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Request: Help in selecting interface for inter-container networking.

[Benoit Ganne (bganne) via lists.fd.io]

Hi,

> I'm trying to create an inter-container link A<-->B for high speed data
> transfer.
> I'm having a Container application on one side and Virtual-router(based on
> vpp) on the other side.
> I have a choice between a virtio-user - vhost-user pair or use a MemIf
> interface.

We usually use memif which was designed exactly for this. Memif is lighter than 
virtio and your application can use eg. libmemif.

Best
ben

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20752): https://lists.fd.io/g/vpp-dev/message/20752
Mute This Topic: https://lists.fd.io/mt/88530304/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

[vpp-dev] Request: Help in selecting interface for inter-container networking.

[Pragya Nand Bhagat]

Hi All,

I'm trying to create an inter-container link A<-->B for high speed data
transfer.

[image: image.png]


I'm having a Container application on one side and Virtual-router(based on
vpp) on the other side.
I have a choice between a virtio-user - vhost-user pair or use a MemIf
interface.

Can anyone suggest which approach is better and support it with reason ?

Thank You
Pragya Nand Bhagat

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20751): https://lists.fd.io/g/vpp-dev/message/20751
Mute This Topic: https://lists.fd.io/mt/88530304/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-