Re: zero-copy TCP fileserving

Artur Skawina (skawina@geocities.com)
Thu, 03 Jun 1999 17:49:51 +0200

Bjorn Wesen wrote:
>
> On Thu, 3 Jun 1999, Richard B. Johnson wrote:
> > > But for the hardware I'm running this on, a checksum + copy takes at least
> > > twice the time as a checksum (simple - read vs read/write). And this is
> > ^^^^^^^^^^^^^^^^^^^^^^^^^^^
> >
> > No, not at all. With memory-to-memory copy, you are I/O bound. With any
> > CPU that runs faster than memory access (anything faster than a
> > 486-DX/66), you get the checksumming for free if the code is properly
> > written, which Linux's checksum while copy sees to be.

> If your CPU needs to read 100 MByte and then write it back to ram, it does
> take twice the time as just reading it.

no, Richard is right - on modern cpus the additional writes don't slow
you down that much (eg on pii - only ~7% for fullsized eth frames).

TIME-N+S TIME32 TIME33 TIME1480 TIMEXXXX CKSUM FUNCTION ( rdtsc_overhead=2 null=-1 )
20320 8205 8987 17502 18492 : 51252 csum_partial_686as1s
22109 9978 13303 18693 25684 : 51252 csum_partial_copy_generic_686as2
17609 12194 12748 10207 22893 : 0 kernel_memcpy686as2

> Fact: our HW, while sending TCP on a 100 mbit/s ethernet, spends 70% of
> the time in csum_partial_copy. I'd be surprised if the performance of the
> transfers wouldn't go up quite alot if that call was eliminated.

what hw is that?

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/