Re: [PATCH] phonet: Check input from user before allocating

[Rick Jones]

On 04/02/2012 07:34 PM, Eric Dumazet wrote:
> On Mon, 2012-04-02 at 19:29 -0700, Rick Jones wrote:
> > I don't know it isn't entirely bitrotted, but there are streaming and
> > datagram AF_UNIX tests in netperf - they require conditional inclusion
> > via ./configure --enable-unixdomain:
> >
> > http://www.netperf.org/svn/netperf2/trunk/doc/netperf.html#DG_005fSTREAM
>
> Ah yes of course, I'll try that.
>
> BTW, do you have plans to support vmsplice()/splice() as a way to
> provide 0-copy to TCP_STREAM ?

I'd probably plead "too platform specific" but I've already got some 
platform-specific stuff in there like TCP_INFO so I probably cannot hide 
behind that.  Particularly if I ever do make "native" WSA calls for 
Windows...

Until now I'd not thought of vmsplice/splice though - only sendfile for 
zero copy, which should be there for TCP in the form of the TCP_SENDFILE 
test (unmigrated, so none of the omni output selection is available)

> I ask this because I am currently working on fixing splice(pipe ->
> socket) performance problem and need a standard benchmark to publish
> performance results.

I'll start to ponder, without promises.

rick
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/