Signed-off-by: Jan-Bernd Themann <[EMAIL PROTECTED]>
drivers/net/ehea/ehea_qmr.c | 604
drivers/net/ehea/ehea_qmr.h | 362 ++
2 files changed, 966 insertions(+)
--- linux-2.6.18-rc6-orig/drivers/net/ehea/ehea_qmr.c 1970
Signed-off-by: Jan-Bernd Themann <[EMAIL PROTECTED]>
drivers/net/ehea/ehea_qmr.c | 605
drivers/net/ehea/ehea_qmr.h | 361 ++
2 files changed, 966 insertions(+)
--- linux-2.6.18-rc6-orig/drivers/net/ehea/ehea_qmr.c 1970
Signed-off-by: Jan-Bernd Themann <[EMAIL PROTECTED]>
drivers/net/ehea/ehea_qmr.c | 607
drivers/net/ehea/ehea_qmr.h | 361 ++
2 files changed, 968 insertions(+)
--- linux-2.6.18-rc4-git1-orig/drivers/net/ehea/ehea_qmr.c
Hi,
On Tuesday 22 August 2006 16:01, Arnd Bergmann wrote:
> > + u64 rpage = 0;
> > + int ret;
> > + int cnt = 0;
> > + void *vpage = NULL;
> > +
> > + ret = hw_queue_ctor(hw_queue, nr_pages, EHEA_PAGESIZE, wqe_size);
> > + if (ret)
> > + return ret
Signed-off-by: Jan-Bernd Themann <[EMAIL PROTECTED]>
drivers/net/ehea/ehea_qmr.c | 634
drivers/net/ehea/ehea_qmr.h | 367 +
2 files changed, 1001 insertions(+)
--- linux-2.6.18-rc4-git1-orig/drivers/net/ehea/ehea_qmr.c
On Friday 18 August 2006 16:24, Christoph Raisch wrote:
> And as always in performance tuning... one size fits all unfortunately is
> not the correct answer.
Ah, good. What is the maximum sensible value that you came up with?
> Therefore we'll leave that open to the user as most other new etherne
On Fri, 18 August 2006 13:31:19 +0200, Jan-Bernd Themann wrote:
>
> + if (queue->current_q_offset > queue->queue_length) {
> + queue->current_q_offset -= queue->pagesize;
> + retvalue = NULL;
> + }
> + else if u64) retvalue) & (EHEA_PAGESIZE-1)) != 0) {
On Fri, 18 August 2006 15:25:11 +0200, Thomas Klein wrote:
> Arjan van de Ven wrote:
> >>+ queue->queue_length = nr_of_pages * pagesize;
> >>+ queue->queue_pages = vmalloc(nr_of_pages * sizeof(void *));
> >
> >
> >wow... is this really so large that it warrants a vmalloc()???
>
> Agreed: Repla
> You should really do some measurements to see what the minimal
> queue sizes are that can get you optimal throughput.
>
>Arnd <><
we did.
And as always in performance tuning... one size fits all unfortunately is
not the correct answer.
Therefore we'll leave that open to the user as most othe
On Friday 18 August 2006 15:25, Thomas Klein wrote:
>
> > wow... is this really so large that it warrants a vmalloc()???
>
> Agreed: Replaced with kmalloc()
My understanding from the previous discussion was that it actually
is a multi-page power of two allocation, so the right choice might
be __
Arjan van de Ven wrote:
+ queue->queue_length = nr_of_pages * pagesize;
+ queue->queue_pages = vmalloc(nr_of_pages * sizeof(void *));
wow... is this really so large that it warrants a vmalloc()???
Agreed: Replaced with kmalloc()
Regards
Thomas
-
To unsubscribe from this list: se
> + queue->queue_length = nr_of_pages * pagesize;
> + queue->queue_pages = vmalloc(nr_of_pages * sizeof(void *));
wow... is this really so large that it warrants a vmalloc()???
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECT
Signed-off-by: Jan-Bernd Themann <[EMAIL PROTECTED]>
drivers/net/ehea/ehea_qmr.c | 643
drivers/net/ehea/ehea_qmr.h | 367 +
2 files changed, 1010 insertions(+)
--- linux-2.6.18-rc4-orig/drivers/net/ehea/ehea_qmr.c 1969
13 matches
Mail list logo
