Date: Mon, 22 Mar 1999 15:14:34 -0500 From: Dennis <dennis@etinc.com> To: Matthew Dillon <dillon@apollo.backplane.com> Cc: Mike Smith <mike@smith.net.au>, Amancio Hasty <hasty@rah.star-gate.com>, hackers@FreeBSD.ORG Subject: Re: Gigabit ethernet -- what am I doing wrong? Message-ID: <199903222019.PAA21360@etinc.com> In-Reply-To: <199903221834.KAA21361@apollo.backplane.com> References: <Your message of "Sun, 21 Mar 1999 20:10:21 EST." <199903220058.TAA17538@etinc.com> <199903221711.MAA20551@etinc.com>
next in thread | previous in thread | raw e-mail | index | archive | help
At 10:34 AM 3/22/99 -0800, Matthew Dillon wrote: > >:>This has nothing whatever to do with reality, however. Most PCI >:>peripherals are bus masters, and most memory busses these days are at >:>least 64 bits wide, so 64 bit PCI has very real performance benefits. >:> >:>The processor's internal word size has little or nothing to do with the >:>equation. >: >:The ability to do single-cycle transfers IS affected by the internal >:processor's >:word size. If it can't do sustained single-cycle bursts then performance >:suffers >:significantly, so I disagree wholeheartedly on this. If the on-board processor >:doesnt have a 64bit bus it is very difficult to do single cycle transfers. >: >: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 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?199903222019.PAA21360>