Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 22 Mar 1999 17:36:16 -0500
From:      Dennis <dennis@etinc.com>
To:        Matthew Dillon <dillon@apollo.backplane.com>
Cc:        hackers@freebsd.org
Subject:   Re: Gigabit ethernet -- what am I doing wrong? 
Message-ID:  <199903222241.RAA21975@etinc.com>
In-Reply-To: <199903222045.MAA24353@apollo.backplane.com>
References:  <Your message of "Sun, 21 Mar 1999 20:10:21 EST."             <199903220058.TAA17538@etinc.com> <199903221711.MAA20551@etinc.com> <199903222019.PAA21360@etinc.com>

next in thread | previous in thread | raw e-mail | index | archive | help
At 12:45 PM 3/22/99 -0800, you wrote:
>
>:>:Dennis
>:>
>:>    All PCI card chipsets implement internal read and write 
>:>    DMA FIFO's.  Thus a 64 bit PCI card can easily burst 64 bit
>:>    words over the PCI bus.  If the processor on the card
>:>    itself cannot stuff the FIFO quickly enough to hold the burst
>:>    for a period longer then the size of the FIFO, it's no big deal
>:>    because the processor on the card can obviously pump data 
>:>    sufficiently to handle the physical I/O it is supporting for
>:>    that card , and the FIFO is large enough such that the 
>:>    shorter higher-speed burst on the PCI bus will be sufficient
>:>    enough to use the PCI bus bandwidth efficiently.  What bandwidth 
>:>    cannot be used by one card will certainly be used by another.
>:>
>:>    This just isn't an issue.
>:Shorter bursts are less efficient, which implies that 64bit PCI transfers
>:can be not much better than 32bit with sustained bursts, which is
>:my point. You could easily have  a 64-bit pci card that was slower than
>:(or the same as) a 32-bit one due to this factor. Im not arguing that it
>:doesnt work, only that its not a cureall to the throughput problem.
>:
>:Dennis
>
>    Dennis, please read my response more carefully and you will understand
>    why your concerns are unfounded.  I will paraphrase:  "The FIFOs are
>    large enough such that the burst is going to be relatively efficient
>    no matter what the PCI bus width and no matter how slow the card".
>
>    The problem that is being solved here is not a card's ability to sustain
>    a long burst, but instead the bandwidth available on the PCI bus when
>    multiple cards are operating.  There is no advantage to any single card 
>    being able to do long sustained bursts on a faster PCI bus because they
>    are already limited to the speed physical media they were built to
handle.
>    The requirement is for the card to be able to sustain a reasonably-sized
>    burst so the PCI bus's transactional overhead remains small verses the
>    actual data transfer.  This is what the FIFO accomplishes.

What i mean by "sustained" is more than 1 or 2 words...I believe that 32bit
engines would have a problem doing single cycle transfers at 64bits...and 
that implies substantial setup overhead, more than double or triple, which 
significantly effects available bandwidth and device perfornance. I've done
a lot of empirical testing and if you miss the burst performance really sucks
wind. Controllers with external logic on the board, for example,  often
can't do
single-cycle transfers and bus performance severely suffers. I dont know how
you can say that it doesnt.

Dennis




To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199903222241.RAA21975>