Massimo Biancucci wrote: >we've been installing a new application using crypto facility calling services >like 'CSNBKEX' or 'CSNBKIM'. >We've done all the possible (in our understanding) to optimize the >application, so now we can measure more than 150 msg/second per single >application server. >What does sound really strange to me is the elapsed time of the two routines >previously mentioned. >Every call costs more than one millisecond. >Cause the CEC is a z12 and the crypto is in HW, I believe those elapsed should >have been microseconds. >Anybody got a similar experience ?
CPACF is on the CPU chip (hardware). Very fast. While CEX is on a card down in the I/O cage, so like Phil said it's like doing an I/O. Very slow (compared to CPACF) CEX (Secure Key) is so slow, IBM developed Protected Key encryption. It's not as secure as Secure Key but it's faster A millisecond for a CEX call to encrypt 32 bytes of data is what we got before we switched to Protected Key. Steve Finch RPS ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
