On Thu, 2009-04-02 at 14:44 -0700, Anna Neal wrote:
> Currently, the libertas main thread contends with the spi driver thread
> in the TX path. To improve throughput, ensure that the driver thread
> has higher scheduling priority than the libertas main thread. Do this
> by making the libertas spi driver thread a low priority real time
> thread.
>
> We measured an average throughput improvement of 13%.
>
> Signed-off-by: Anna Neal <anna@xxxxxxxxxxx>
> Signed-off-by: Andrey Yurovsky <andrey@xxxxxxxxxxx>
Sure; looks fine to me.
Acked-by: Dan Williams <dcbw@xxxxxxxxxx>
> ---
> drivers/net/wireless/libertas/if_spi.c | 4 ++++
> 1 files changed, 4 insertions(+), 0 deletions(-)
>
> diff --git a/drivers/net/wireless/libertas/if_spi.c b/drivers/net/wireless/libertas/if_spi.c
> index 07311e7..97493e2 100644
> --- a/drivers/net/wireless/libertas/if_spi.c
> +++ b/drivers/net/wireless/libertas/if_spi.c
> @@ -1020,6 +1020,7 @@ static int __devinit if_spi_probe(struct spi_device *spi)
> struct libertas_spi_platform_data *pdata = spi->dev.platform_data;
> int err = 0;
> u32 scratch;
> + struct sched_param param = { .sched_priority = 1 };
>
> lbs_deb_enter(LBS_DEB_SPI);
>
> @@ -1123,6 +1124,9 @@ static int __devinit if_spi_probe(struct spi_device *spi)
> lbs_pr_err("error creating SPI thread: err=%d\n", err);
> goto remove_card;
> }
> + if (sched_setscheduler(card->spi_thread, SCHED_FIFO, ¶m))
> + lbs_pr_err("Error setting scheduler, using default.\n");
> +
> err = request_irq(spi->irq, if_spi_host_interrupt,
> IRQF_TRIGGER_FALLING, "libertas_spi", card);
> if (err) {
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
