Re: [vpp-dev] Regarding high speed I/O with kernel

[Damjan Marion via Lists.Fd.Io]

> On 7 Dec 2019, at 04:46, Prashant Upadhyaya  wrote:
> 
> On Fri, Dec 6, 2019 at 9:32 PM Damjan Marion  wrote:
>> 
>> 
>> 
 On 6 Dec 2019, at 07:16, Prashant Upadhyaya  wrote:
>>> 
>>> Hi,
>>> 
>>> I use VPP with DPDK driver for I/O with NIC.
>>> For high speed switching of packets to and from kernel, I use DPDK KNI
>>> (kernel module and user space API's provided by DPDK)
>>> This works well because the vlib buffer is backed by the DPDK mbuf
>>> (KNI uses DPDK mbuf's)
>>> 
>>> Now, if I choose to use a native driver of VPP for I/O with NIC, is
>>> there a native equivalent in VPP to replace KNI as well ? The native
>>> equivalent should not lose out on performance as compared to KNI so I
>>> believe the tap interface can be ruled out here.
>>> 
>>> If I keep using DPDK KNI and VPP native non-dpdk driver, then I fear I
>>> would have to do a data copy between the vlib buffer and an mbuf  in
>>> addition to doing all the DPDK pool maintenance etc. The copies would
>>> be destructive for performance surely.
>>> 
>>> So I believe, the question is -- in presence of native drivers in VPP,
>>> what is the high speed equivalent of DPDK KNI.
>> 
>> You can use dpdk and native drivers on the same time.
>> How KNI performance compares to tap with vhost-net backend?
>> 
>> 
>> --
>> Damjan
>> 
> 
> Thanks Damjan.
> If I use the native driver for NIC, would I get the vlib buffer still
> backed by a DPDK mbuf ?

yes

> I don't know the perf difference between KNI and tap with vhost-net backend.
> I would need to poll the tap to pick the packets from kernel side; and
> write into the tap to send the packets to the kernel in VPP workers.
> I suppose the mere copies from user space into kernel space and vice
> versa would make it more expensive than KNI where just an exchange of
> mbuf's takes place in both directions. Plus, I wonder whether system
> call usage is a good idea at all in a worker which is also
> multiplexing the packet I/O with the NIC.

my question was about vhost-net backed tap interface, not plain one ...

— 
Damjan
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#14836): https://lists.fd.io/g/vpp-dev/message/14836
Mute This Topic: https://lists.fd.io/mt/67470059/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Coverity run FAILED as of 2019-12-07 14:01:55 UTC

[Ed Kern via Lists.Fd.Io]

Hmm…website must have been briefly unavailable during the run this 
morning…seems ok now though after manual sandbox run.

Ed




Coverity run failed today.

Current number of outstanding issues are 2
Newly detected: 0
Eliminated: 0
More details can be found at  
https://scan.coverity.com/projects/fd-io-vpp/view_defects




On Dec 7, 2019, at 7:02 AM, nore...@jenkins.fd.io 
wrote:

Coverity run failed today.

[Error replacing 'FILE' - Workspace is not accessible]

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#14835): https://lists.fd.io/g/vpp-dev/message/14835
Mute This Topic: https://lists.fd.io/mt/67626387/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

[vpp-dev] Coverity run FAILED as of 2019-12-07 15:58:34 UTC

[Noreply Jenkins]

Coverity run failed today.

Current number of outstanding issues are 2
Newly detected: 0
Eliminated: 0
More details can be found at  
https://scan.coverity.com/projects/fd-io-vpp/view_defects
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#14834): https://lists.fd.io/g/vpp-dev/message/14834
Mute This Topic: https://lists.fd.io/mt/67628365/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

[vpp-dev] Coverity run FAILED as of 2019-12-07 14:01:55 UTC

[Noreply Jenkins]

Coverity run failed today.

[Error replacing 'FILE' - Workspace is not accessible]
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#14833): https://lists.fd.io/g/vpp-dev/message/14833
Mute This Topic: https://lists.fd.io/mt/67626387/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

[vpp-dev] A request for crypto framework

[Zhang Yuwei]

Hi Damjan,
   I am trying to use VPP crypto framework to accelerate a TLS 
engine and I found that all the parameters in crypto op are non-const but most 
of external components would like to use the function with const parameter(such 
as input, src, iv, etc). It is OK to be used by internal component such as VPP 
IPSec part because of it can define the calling function itself but hard to be 
used by external components. I noticed the QUIC plugin convert the (const void 
*) to (void *) directly which could work but not a good way. So, is it possible 
to change the crypto op parameter to const type which are necessary? Thanks a 
lot.

Regards,
Yuwei

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#14832): https://lists.fd.io/g/vpp-dev/message/14832
Mute This Topic: https://lists.fd.io/mt/67625634/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Regarding high speed I/O with kernel

[Prashant Upadhyaya]

On Fri, Dec 6, 2019 at 9:32 PM Damjan Marion  wrote:
>
>
>
> > On 6 Dec 2019, at 07:16, Prashant Upadhyaya  wrote:
> >
> > Hi,
> >
> > I use VPP with DPDK driver for I/O with NIC.
> > For high speed switching of packets to and from kernel, I use DPDK KNI
> > (kernel module and user space API's provided by DPDK)
> > This works well because the vlib buffer is backed by the DPDK mbuf
> > (KNI uses DPDK mbuf's)
> >
> > Now, if I choose to use a native driver of VPP for I/O with NIC, is
> > there a native equivalent in VPP to replace KNI as well ? The native
> > equivalent should not lose out on performance as compared to KNI so I
> > believe the tap interface can be ruled out here.
> >
> > If I keep using DPDK KNI and VPP native non-dpdk driver, then I fear I
> > would have to do a data copy between the vlib buffer and an mbuf  in
> > addition to doing all the DPDK pool maintenance etc. The copies would
> > be destructive for performance surely.
> >
> > So I believe, the question is -- in presence of native drivers in VPP,
> > what is the high speed equivalent of DPDK KNI.
>
> You can use dpdk and native drivers on the same time.
> How KNI performance compares to tap with vhost-net backend?
>
>
> --
> Damjan
>

Thanks Damjan.
If I use the native driver for NIC, would I get the vlib buffer still
backed by a DPDK mbuf ?
I don't know the perf difference between KNI and tap with vhost-net backend.
I would need to poll the tap to pick the packets from kernel side; and
write into the tap to send the packets to the kernel in VPP workers.
I suppose the mere copies from user space into kernel space and vice
versa would make it more expensive than KNI where just an exchange of
mbuf's takes place in both directions. Plus, I wonder whether system
call usage is a good idea at all in a worker which is also
multiplexing the packet I/O with the NIC.

Regards
-Prashant
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#14831): https://lists.fd.io/g/vpp-dev/message/14831
Mute This Topic: https://lists.fd.io/mt/67470059/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-