Disk reliability (Was: Node cloning)
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Greg Lindahl lindahl at conservativecomputer.comWed Apr 11 21:08:27 PDT 2001
- Previous message: Disk reliability (Was: Node cloning)
- Next message: Node cloning
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
> When they say "heal", they actually mean "remap to substitute disk > blocks reserved for this purpose". They must have thought that the > concept of remapping disk blocks was too confusing. Don, I was under the impression that modern IDE disks automagically remap disk sectors. The IBM tool looked like it was returning bad blocks to service if they passed a simple test. Also, don't modern chipsets do retry for IDE disks without letting the OS see the retry? SCSI retries show up in syslog, but IDE ones are hidden. Perhaps I'm wrong about both of these, but they appear to be common knowledge... -- g
- Previous message: Disk reliability (Was: Node cloning)
- Next message: Node cloning
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
