czei@accelerator.eng.ohio-state.edu (Michael S. Czeiszperger) (09/30/88)
I was wondering if Aufs worked with ethernet cards in MacII's as well as through the k-box. Does anyone know for sure? Thanks, -- Michael S. Czeiszperger | "Official Sponsor of the television coverage of Systems Analyst | Snail: 2015 Neil Avenue (614) the Olympics" The Ohio State University | Columbus, OH 43210 292- ARPA:czei@accelerator.eng.ohio-state.edu PAN:CZEI 0161
davef@Jessica.stanford.edu (David Finkelstein) (09/30/88)
In article <677@accelerator.eng.ohio-state.edu> czei@accelerator.eng.ohio-state.edu (Michael S. Czeiszperger) writes: >I was wondering if Aufs worked with ethernet cards in MacII's as well >as through the k-box. Does anyone know for sure? > >Thanks, > > >-- >Michael S. Czeiszperger | "Official Sponsor of the television coverage of >Systems Analyst | Snail: 2015 Neil Avenue (614) the Olympics" >The Ohio State University | Columbus, OH 43210 292- >ARPA:czei@accelerator.eng.ohio-state.edu PAN:CZEI 0161 No, it doesn't. Macs on ethertalk can access aufs servers if you're running a version of KIP that understands ethertalk, or if you're using K-Star. But the performance isn't nearly as good as it is for Macs on localtalk. Using fastpath-4s and K-Star makes things faster but still not as fast as a localtalk connection. Sigh. AppleShare over ethertalk is *very* fast, though. -------- David Finkelstein Academic Information Resources Stanford University
czei@phonon.eng.ohio-state.edu (Michael S. Czeiszperger) (09/30/88)
In article <3789@Portia.Stanford.EDU> davef@Jessica.stanford.edu (David Finkelstein) writes: >In article <677@accelerator.eng.ohio-state.edu> czei@accelerator.eng.ohio-state.edu (Michael S. Czeiszperger) writes: >>I was wondering if Aufs worked with ethernet cards in MacII's as well >>as through the k-box. Does anyone know for sure? > >No, it doesn't. Macs on ethertalk can access aufs servers if you're >running a version of KIP that understands ethertalk, or if you're >using K-Star. But the performance isn't nearly as good as it is for >Macs on localtalk. Using fastpath-4s and K-Star makes things faster >but still not as fast as a localtalk connection. Sigh. > >AppleShare over ethertalk is *very* fast, though. > What I don't understand, is that theoretically a connection through an ethertalk card should be much faster than through a localtalk network. Why should Aufs only work *through* a localtalk network when it would be faster and more direct to just communicate with a MacII directly through the ethertalk card? It seems like a huge waste to spend lots of $ on a MacII and ethertalk card, and then have to pay several thousand more dollars for a k-box so we can remote mounting! -=- Michael S. Czeiszperger | "Official Sponsor of the television coverage of Systems Analyst | Snail: 2015 Neil Avenue (614) the Olympics" The Ohio State University | Columbus, OH 43210 292- ARPA:czei@accelerator.eng.ohio-state.edu PAN:CZEI 0161
morgan@JESSICA.STANFORD.EDU (10/01/88)
Aufs can be used from an Ethernet-attached MacII (or SE), but you'll still need the Kbox to do the EtherTalk<-->AppleTalk-in-UDP translation for you, since CAP speaks AT-in-UDP and the Mac speaks EtherTalk. Be prepared for curious performance with a KFPS-[123], as well. We were seeing reasonable performance with transfers from the Aufs machine to a MacII, but terrible performance from the MacII to the Aufs machine. My guess (unconfirmed by traces or anything) is that the MacII was blasting and overloading the Kbox, causing retransmissions, whereas the Aufs machine is throttled down since it expects to be talking to a Mac+ on a LocalTalk. We observed quite good performance in both directions going thru a KFPS-4. - RL "Bob" Morgan Networking Systems Stanford
cck@cunixc.columbia.edu (Charlie C. Kim) (10/01/88)
In article <693@accelerator.eng.ohio-state.edu> czei@phonon.eng.ohio-state.edu (Michael S. Czeiszperger) writes: >.... >network. Why should Aufs only work *through* a localtalk network >when it would be faster and more direct to just communicate with >a MacII directly through the ethertalk card? It seems like a huge >waste to spend lots of $ on a MacII and ethertalk card, and then >have to pay several thousand more dollars for a k-box so we can >remote mounting! > Aufs is NOT limited to working through a LocalTalk network. However, the CAP libraries do NOT, as distributed, allow a transport method other than KIP. Since your Mac II with an EtherTalk card does not support KIP, it must route through an AppleTalk bridge supporting both the KIP UDP encapsulation method and EtherTalk. The CAP libraries do not support a transport other than KIP, because, in general, it would required kernel modifications to support EtherTalk on the various unix hosts. A very important goal was not to have to install kernel modifications to use CAP. Of course, times change and some unix systems come with EtherTalk in the kernel or via another method. For those systems, it is quite possible to make the CAP libraries use EtherTalk as their transport. It requires replacement of one module (abkip.c) with well-defined interfaces to the rest of the libraries (though it could be nicer) with possible replacment/dropping of atalkdbm.c. So, if you have EtherTalk in your kernel, feel free to replace abkip.c. Making Macintoshes support the KIP UDP encapsulation is a possibility, but a lot of work and results in a system that requires will probably require far more configuration than any other Macintosh software (you would have to assign an IP address, specify nearest router, figure out broadcast address, etc). Charlie C. Kim Academic Computing and Communications Group Center for Computing Activities Columbia University
liam@cs.qmc.ac.uk (William Roberts) (10/10/88)
In article <Added.8XEvG2y00UkTEA0U8j@andrew.cmu.edu> morgan@JESSICA.STANFORD.EDU writes: > >.. but terrible performance from the MacII to >the Aufs machine. My guess (unconfirmed by traces or anything) is >that the MacII was blasting and overloading the Kbox, causing >retransmissions, whereas the Aufs machine is throttled down since it >expects to be talking to a Mac+ on a LocalTalk. We observed quite >good performance in both directions going thru a KFPS-4. Exactly right - the problem is that the KBox drops roughly alternate packets so if the flow quantum is large (i.e. >1) then the Mac->AUFS process goes like this (confirmed by traces): Time (secs) AUFS Server EtherTalk Mac 0 Send 8x512 bytes 0.1 chunk0 0.1 chunk1 (gets lost) 0.1 chunk2 0.1 chunk3 (gets lost) 0.1 chunk4 0.1 chunk5 (gets lost) 0.1 chunk6 0.1 chunk7 (gets lost) 5.0 Are you still there? 5.1 Yes I am 10.0 Are you still there? 10.1 Yes I am 15.0 Send missing chunks 1,3,5,7 15.1 chunk1 15.1 chunk3 (gets lost) 15.1 chunk5 15.1 chunk7 20.0 Are you still there? 20.1 Yes I am 25.0 Are you still there? 25.1 Yes I am 30.0 Send missing chunk 3 30.1 chunk3 30.2 Thank you 30.2 Send next 8x512 bytes and so on. This example takes 30 seconds to transfer 4k, less than 1200 baud! I discovered this when trying to work out why printing was so S...L....O....W from our whizzo MacIIs to our whizzo Sequent Balance. The 5 second status queries can't be used because they are not addressed to the same bit of the program (in fact, not even to the same program), so I am stuck with changing either a) The "flow quantum" which is the multiple of 512 that the receiver asks for, thus avoiding the lost packets and the timeouts b) The 15 second timeout (and put up with the dropped packets) I tried changing a) - after fixing the bugs in the CAP software, I discover that the Mac seems to insist on calling PAPWrite with 4k at a time. Unfortunately "if the data size is bigger than the flow quantum of the other end, the call will return with an error" so the stupid *@*#!* gives up. That only leaves changing b), but I haven't the time to do it now and it seems like the wrong solution anyway. I guess that the gateway loses packets just through lack of buffer space: my Sun code has no trouble seeing all of the packets involved. Anyone know how we send bug-reports to Apple themselves? (this is the fault of their Printer Manager stuff) -- William Roberts ARPA: liam@cs.qmc.ac.uk (gw: cs.ucl.edu) Queen Mary College UUCP: liam@qmc-cs.UUCP LONDON, UK Tel: 01-975 5250