lkml.org 
[lkml]   [2016]   [May]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH net-next] tuntap: introduce tx skb ring
On Wed, May 18, 2016 at 10:13:59AM +0200, Jesper Dangaard Brouer wrote:
> On Mon, 16 May 2016 15:51:48 +0800
> Jason Wang <jasowang@redhat.com> wrote:
>
> > On 2016年05月16日 11:56, Eric Dumazet wrote:
> > > On Mon, 2016-05-16 at 09:17 +0800, Jason Wang wrote:
> > >> We used to queue tx packets in sk_receive_queue, this is less
> > >> efficient since it requires spinlocks to synchronize between producer
> > >> and consumer.
> > > ...
> > >
> > >> struct tun_struct *detached;
> > >> + /* reader lock */
> > >> + spinlock_t rlock;
> > >> + unsigned long tail;
> > >> + struct tun_desc tx_descs[TUN_RING_SIZE];
> > >> + /* writer lock */
> > >> + spinlock_t wlock;
> > >> + unsigned long head;
> > >> };
> > >>
> > > Ok, we had these kind of ideas floating around for many other cases,
> > > like qdisc, UDP or af_packet sockets...
> > >
> > > I believe we should have a common set of helpers, not hidden in
> > > drivers/net/tun.c but in net/core/skb_ring.c or something, with more
> > > flexibility (like the number of slots)
> > >
> >
> > Yes, this sounds good.
>
> I agree. It is sad to see everybody is implementing the same thing,
> open coding an array/circular based ring buffer. This kind of code is
> hard to maintain and get right with barriers etc. We can achieve the
> same performance with a generic implementation, by inlining the help
> function calls.
>
> I implemented an array based Lock-Free/cmpxchg based queue, that you
> could be inspired by, see:
> https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/include/linux/alf_queue.h
>
> The main idea behind my implementation is bulking, to amortize the
> locked cmpxchg operation. You might not need it now, but I expect we
> need it in the future.
>
> You cannot use my alf_queue directly as your "struct tun_desc" is
> larger than one-pointer (which the alf_queue works with). But it
> should be possible to extend to handle larger "objects".
>
>
> Maybe Steven Rostedt have an even better ring queue implementation
> already avail in the kernel?

BTW at least for tun, index based isn't really needed.
A simple array seems to be more readable, faster and use less memory.
I have implemented this and it seems to work OK, will
post shortly.



> --
> Best regards,
> Jesper Dangaard Brouer
> MSc.CS, Principal Kernel Engineer at Red Hat
> Author of http://www.iptv-analyzer.org
> LinkedIn: http://www.linkedin.com/in/brouer

\
 
 \ /
  Last update: 2016-05-18 11:01    [W:1.993 / U:0.080 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site