On 22.8.2016. 8:20, David Gwynne wrote: > >> On 22 Aug 2016, at 03:36, Hrvoje Popovski <hrv...@srce.hr> wrote: >> >> On 13.8.2016. 10:59, Claudio Jeker wrote: >>> This diff refactors the uio to mbuf code to make use of bigger buffers (up >>> to 64k) and also switches the MCLGET to use M_WAIT like the MGET calls in >>> the same function. I see no point in not waiting for a cluster and instead >>> chain lots of mbufs together as a consequence. >>> >>> This makes in my opinion the code easier to read and allows for further >>> optimizations (like using non-DMA reachable mbufs for AF_UNIX sockets). >>> >>> This increased the preformance of loopback connections significantly when >>> I tested this at n2k16. >>> >> >> Hi, >> >> it seems that this patch speeds up forwarding for about 40kpps. At least >> with my test box and with this setup :) >> Which means that -current can forward full 10Gbps with 1500byte packets :) > > thats kind of nuts cos this shouldnt affect the forwarding path at all. > > im keen for it to go in still though. claudio? > > dlg >
yes, you are right ... this is my stupid mistake, i compared results from 15.08.2016 with results from 21.08.2016 with claudio@ patch without first testing plain source and then test same setup with claudio@ patch ... i'm very sorry for making this stupid mistake ...
