Bruce, Right know I don't they are leapfrogging at all - the choke is FICON rather than hardware. Both disk and tape can deliver sustained data rates of 160MB/sec because that's all that FICON can do.
This is the rate for the latest 35392 if you are getting 3:1 compression, and this is the rate for modern arrays if they are using a reasonable array scheme. If the disk is RAID-1 then of course tape is faster, and if the tape is not compressing well then disk will be faster. My opinion is that RAID using 10K and 15K large form factor disks have been staying well ahead of LTO for a few years now. Ron > -----Original Message----- > From: IBM Mainframe Discussion List [mailto:[EMAIL PROTECTED] On > Behalf Of Bruce Black > Sent: Thursday, 27 July 2006 4:53 AM > To: [email protected] > Subject: Re: Blocksize and speed limit on an FICON channel > > > > > This has not been true for a long time. Pre-fetching concurrently of 4 > or 8 > > drives is much faster than a single tape drive can handle. > Ron, I agree, but unless you have a product like ExHPDM to write > multiple concurrent backups to a single tape, it doesn't help. Dumping > 1 disk to 1 tape, or 10 disks to 10 tapes, there seems to always be a > tape drive on the market which is faster than fastest available disk. > They keep leapfrogging, of course. > > -- > Bruce Black > Senior Software Developer > Innovation Data Processing > > ---------------------------------------------------------------------- > 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 ---------------------------------------------------------------------- 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
