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