The following message is a courtesy copy of an article that has been posted to bit.listserv.ibm-main,alt.folklore.computers as well.
JimKeo <[EMAIL PROTECTED]> writes: > I remember with great fondness working with VS/Pascal when on contract > to IBM working on VM and MVS implementation of TCPIP. > > Later IBM came out with a C version of much of the TCPIP suite and one > of my duties was to address serious performance issues with TCPIP > stack but mostly with the C FTP Server (and later C FTP Client). > > At some point performance had finally been improved enough to where C > FTP was competitive with the earlier VS/Pascal offering. When I > suggested I could make some of the same improvements to the VS/Pascal > version some folks were positively apoplectic. {smile} > > They, understandably but regretably, wanted the "old" Pascal FTP > buried and replaced by the "new" C FTP and knew renewed performance > issues (Pascal faster than C) would just cause grief to some. > > Hmmm. It's been almost a decade but is anyone able to ascertain > whether IBM FTP Server or client still has some of my assembler CSECTs > with names like WRTFBA** or WRTVB** linked/bound somewhere? Just > curious. re: http://www.garlic.com/~lynn/2007h.html#41 Fast and Safe C Strings: User friendly C macros to Declare and use C Strings the initial implementation and would get about 44kbyte/sec consuming most of a 3090 processor. i then added the support for rfc1044 and some tuning tests at cray research was getting channel speed (1mbyte/sec) between 4341 clone and a cray machine ... using only a modest amount of the 4341 processor ... i.e. about 25 times the aggregate thruput for about 1/20 the pathlength ... about 400-500 times difference in bytes/transferred per instruction executed. re: http://www.garlic.com/~lynn/2007h.html#8 whiny question: Why won't z/OS support the HMC 3270 emulator misc. posts mentioning various compromises, vulnerabilities, exploits, etc related C language http://www.garlic.com/~lynn/subintegrity.html#overflow and misc. past posts mentioning having done rfc1044 support http://www.garlic.com/~lynn/subnetwork.html#1044 for other topic drift ... we had an internal high-speed backbone ... part of our hsdt (high-speed data transport project) http://www.garlic.com/~lynn/subnetwork.html#hsdt and we working with various organizations and NSF for applying it to NSFNET related operations ... various old email from the period http:/www.garlic.com/~lynn/lhwemail.html#nsfnet in various posts http://www.garlic.com/~lynn/subnetwork.html#nsfnet ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html