On 2018年02月28日 23:43, Michael S. Tsirkin wrote:
On Wed, Feb 28, 2018 at 10:20:33PM +0800, Jason Wang wrote:
On 2018年02月28日 22:01, Michael S. Tsirkin wrote:
On Wed, Feb 28, 2018 at 02:28:21PM +0800, Jason Wang wrote:
On 2018年02月28日 12:09, Michael S. Tsirkin wrote:
Or we can add plist to a u
On Wed, Feb 28, 2018 at 10:20:33PM +0800, Jason Wang wrote:
>
>
> On 2018年02月28日 22:01, Michael S. Tsirkin wrote:
> > On Wed, Feb 28, 2018 at 02:28:21PM +0800, Jason Wang wrote:
> > >
> > > On 2018年02月28日 12:09, Michael S. Tsirkin wrote:
> > > > > > Or we can add plist to a union:
> > > > > >
>
On 2018年02月28日 22:01, Michael S. Tsirkin wrote:
On Wed, Feb 28, 2018 at 02:28:21PM +0800, Jason Wang wrote:
On 2018年02月28日 12:09, Michael S. Tsirkin wrote:
Or we can add plist to a union:
struct sk_buff {
union {
struct {
/* These tw
On Wed, Feb 28, 2018 at 02:28:21PM +0800, Jason Wang wrote:
>
>
> On 2018年02月28日 12:09, Michael S. Tsirkin wrote:
> > > > Or we can add plist to a union:
> > > >
> > > >
> > > > struct sk_buff {
> > > > union {
> > > > struct {
> > > > /* Th
On 2018年02月28日 12:09, Michael S. Tsirkin wrote:
Or we can add plist to a union:
struct sk_buff {
union {
struct {
/* These two members must be first. */
struct sk_buff *next;
str
On Wed, Feb 28, 2018 at 11:39:15AM +0800, Jason Wang wrote:
>
>
> On 2018年02月28日 11:28, Jason Wang wrote:
> > > > Well I believe the main user for this is qdisc, which use skb
> > > > array. And we
> > > > can not use what implemented in this patch directly for sk_buff
> > > > without some
> > >
On Wed, Feb 28, 2018 at 11:28:57AM +0800, Jason Wang wrote:
>
>
> On 2018年02月28日 01:12, Michael S. Tsirkin wrote:
> > On Tue, Feb 27, 2018 at 10:29:26AM +0800, Jason Wang wrote:
> > >
> > > On 2018年02月27日 04:34, Michael S. Tsirkin wrote:
> > > > On Mon, Feb 26, 2018 at 11:15:42AM +0800, Jason Wa
On 2018年02月28日 11:28, Jason Wang wrote:
Well I believe the main user for this is qdisc, which use skb array.
And we
can not use what implemented in this patch directly for sk_buff
without some
changes on the data structure.
Why not? skb has next and prev pointers at 1st two fields:
struct s
On 2018年02月28日 01:12, Michael S. Tsirkin wrote:
On Tue, Feb 27, 2018 at 10:29:26AM +0800, Jason Wang wrote:
On 2018年02月27日 04:34, Michael S. Tsirkin wrote:
On Mon, Feb 26, 2018 at 11:15:42AM +0800, Jason Wang wrote:
On 2018年02月26日 09:17, Michael S. Tsirkin wrote:
So pointer rings work fine
On Tue, Feb 27, 2018 at 09:53:49AM -0800, Eric Dumazet wrote:
> On Mon, 2018-02-26 at 03:17 +0200, Michael S. Tsirkin wrote:
> > So pointer rings work fine, but they have a problem: make them too small
> > and not enough entries fit. Make them too large and you start flushing
> > your cache and ru
On Mon, 2018-02-26 at 03:17 +0200, Michael S. Tsirkin wrote:
> So pointer rings work fine, but they have a problem: make them too small
> and not enough entries fit. Make them too large and you start flushing
> your cache and running out of memory.
>
> This is a new idea of mine: a ring backed by
On Tue, Feb 27, 2018 at 10:29:26AM +0800, Jason Wang wrote:
>
>
> On 2018年02月27日 04:34, Michael S. Tsirkin wrote:
> > On Mon, Feb 26, 2018 at 11:15:42AM +0800, Jason Wang wrote:
> > > On 2018年02月26日 09:17, Michael S. Tsirkin wrote:
> > > > So pointer rings work fine, but they have a problem: make
On 2018年02月27日 04:34, Michael S. Tsirkin wrote:
On Mon, Feb 26, 2018 at 11:15:42AM +0800, Jason Wang wrote:
On 2018年02月26日 09:17, Michael S. Tsirkin wrote:
So pointer rings work fine, but they have a problem: make them too small
and not enough entries fit. Make them too large and you start f
On Mon, Feb 26, 2018 at 11:15:42AM +0800, Jason Wang wrote:
>
>
> On 2018年02月26日 09:17, Michael S. Tsirkin wrote:
> > So pointer rings work fine, but they have a problem: make them too small
> > and not enough entries fit. Make them too large and you start flushing
> > your cache and running out
On 2018年02月26日 09:17, Michael S. Tsirkin wrote:
So pointer rings work fine, but they have a problem: make them too small
and not enough entries fit. Make them too large and you start flushing
your cache and running out of memory.
This is a new idea of mine: a ring backed by a linked list. Onc
So pointer rings work fine, but they have a problem: make them too small
and not enough entries fit. Make them too large and you start flushing
your cache and running out of memory.
This is a new idea of mine: a ring backed by a linked list. Once you run
out of ring entries, instead of a drop you
16 matches
Mail list logo
