Re: [osv-dev] Re: raw socket support ?

Thanks Pekka, I will explore the memcached server to see how it works! In a fast first look, it seems to be very useful for solving the problem too. :-) Em sex., 24 de jul. de 2020 às 02:38, Pekka Enberg escreveu: > > > On Fri, Jul 24, 2020 at 3:35 AM Vladislav Zolotarov > wrote: > >> >> >> On

Re: [osv-dev] Re: raw socket support ?

On 7/23/20 5:38 AM, Nadav Har'El wrote: On Thu, Jul 23, 2020 at 12:05 PM Rick Payne > wrote: Another alternative (for me and maybe others) would be to have a standard way to hook packets direct from the virtio interface. We did have something like

Re: [osv-dev] Re: raw socket support ?

Very nice ideas! Take control of the VirtIO interfaces, as Rick and Nadav suggested, can be a good solution for me too. In my particular case, I have a management interface that DHCPs, but the other interfaces (that are used for the data plane) are isolated and manually configured. I will

Re: [osv-dev] Re: raw socket support ?

On Thu, 2020-07-23 at 12:38 +0300, Nadav Har'El wrote: > We also had until recently something more general, "assigned virtio", > where the application > gets access directly to the viritio rings (and needs to work with > them - the kernel doesn't > touch them any more). Waldek recently removed it

Re: [osv-dev] Re: raw socket support ?

On Thu, Jul 23, 2020 at 12:05 PM Rick Payne wrote: > > Another alternative (for me and maybe others) would be to have a > standard way to hook packets direct from the virtio interface. > We did have something like that in the past, and I remember Vlad used it to write some sort of

Re: [osv-dev] Re: raw socket support ?

Another alternative (for me and maybe others) would be to have a standard way to hook packets direct from the virtio interface. Especially if we could ensure that we don't dhcp on that interface. For instance, setup 2 interfaces from the host - 1 for OSv-y stuff, and one just for an application

Re: [osv-dev] Re: raw socket support ?

Honestly, I am not familiar enough in this subject domain so I cannot give any authoritative advice. But it seems to me that the latter idea of introducing and supporting LINUX_AF_PACKET may be less effort and more in line with what Charles did. I am not familiar with BPF so I do not know if

Re: [osv-dev] Re: raw socket support ?

Hi, I think that the type of raw sockets (SOCK_RAW) works well in OSv, it is possible to hook L3 packets (assuming an INET domain) with no problems. I guess that BSD does not support the PACKET domain, thus the OSv does not support too. If I remember well, we can hook frames in BSD by using

Re: [osv-dev] Re: raw socket support ?

Hi, On Wed, Jul 15, 2020 at 6:13 PM Waldek Kozaczuk wrote: > Hi, > > Unfortunately, I have no idea what it would take to add raw sockets > support. Please be aware that we maintain another IPV6 branch - > https://github.com/cloudius-systems/osv/tree/ipv6 - which besides IPV6 > might have better

Re: [osv-dev] Re: raw socket support ?

Hi, Unfortunately, I have no idea what it would take to add raw sockets support. Please be aware that we maintain another IPV6 branch - https://github.com/cloudius-systems/osv/tree/ipv6 - which besides IPV6 might have better networking support but I doubt it supports raw sockets. I am also

[osv-dev] Re: raw socket support ?

Hi, I have a similar problem, I need to get ethernet frames in userspace (a raw sockets bound in an interface or something similar to this). Did you get any advance on it guys? Thanks! Em quarta-feira, 11 de julho de 2018 às 04:48:51 UTC-3, frederic...@gmail.com escreveu: > Thanks for the