Beginner Questions

Joel Sherrill joel.sherrill at OARcorp.com
Wed Nov 27 17:42:59 UTC 2002



Eric Norum wrote:
> 
> On Wednesday, November 27, 2002, at 03:12  PM, Imran Ali wrote:
> 
> > Me too a beginner in this embedded tech. I can't afford a board just
> > for learning RTEMS. But I have the issue with my network card (an RTL
> > 8139). Is it possible to port the driver from Linux? Or should I go
> > for another NIC? If so which one? Make? Model?
> 
> I wouldn't spend (waste) any time porting the driver.   I looked around
> for PC-104 cards until I found one with a NIC compatible with the
> Intel EtherExpress Pro (if_fxp.c driver).   Thomas Doerfler ported the
> driver and generously made it available.

I would also add that it appears to have very good performance.  Eric
and I have seen very high throughput given the modest horsepower of
the Bobcat.  That machine is approximately a 133/486 with only i386
instructions.  Do you remember the exact ttcp numbers Eric?  I was
thinking they were 70-80% of 100baseT theoretical limits.

> If you *do* want to port a driver you should start from the FreeBSD
> source, not the Linux source, since the RTEMS network stack came from
> FreeBSD.  The licensing issues are simpler, too.
> 
> Quoting from the FreeBSD source for the RTL 8139:
> 
>   * The RealTek 8139 PCI NIC redefines the meaning of 'low end.' This is
>   * probably the worst PCI ethernet controller ever made, with the
> possible
>   * exception of the FEAST chip made by SMC. The 8139 supports bus-master
>   * DMA, but it has a terrible interface that nullifies any performance
>   * gains that bus-master DMA usually offers.
>   *
>   * For transmission, the chip offers a series of four TX descriptor
>   * registers. Each transmit frame must be in a contiguous buffer,
> aligned
>   * on a longword (32-bit) boundary. This means we almost always have to
>   * do mbuf copies in order to transmit a frame, except in the unlikely
>   * case where a) the packet fits into a single mbuf, and b) the packet
>   * is 32-bit aligned within the mbuf's data area. The presence of only
>   * four descriptor registers means that we can never have more than four
>   * packets queued for transmission at any one time.
>   *
>   * Reception is not much better. The driver has to allocate a single
> large
>   * buffer area (up to 64K in size) into which the chip will DMA received
>   * frames. Because we don't know where within this region received
> packets
>   * will begin or end, we have no choice but to copy data from the buffer
>   * area into mbufs in order to pass the packets up to the higher
> protocol
>   * levels.
>   *
>   * It's impossible given this rotten design to really achieve decent
>   * performance at 100Mbps, unless you happen to have a 400Mhz PII or
>   * some equally overmuscled CPU to drive it.
>   *
>   * On the bright side, the 8139 does have a built-in PHY, although
>   * rather than using an MDIO serial interface like most other NICs, the
>   * PHY registers are directly accessible through the 8139's register
>   * space. The 8139 supports autonegotiation, as well as a 64-bit
> multicast
>   * filter.
>   *
> --
> Eric Norum <eric.norum at usask.ca>
> Department of Electrical Engineering
> University of Saskatchewan
> Saskatoon, Canada.
> Phone: (306) 966-5394   FAX:   (306) 966-5407

-- 
Joel Sherrill, Ph.D.             Director of Research & Development
joel at OARcorp.com                 On-Line Applications Research
Ask me about RTEMS: a free RTOS  Huntsville AL 35805
Support Available                (256) 722-9985



More information about the users mailing list