On 03/10/11 11:36 AM, Les Mikesell wrote: > Sure, UPS's fail, plugs get pulled, etc., but the cards and internal > batteries most likely have their own failure modes. Or the whole box > can fry at once. Did you have any way to tell if your battery-backed > saved any data as the disks lost power or did the filesystems just back > out the incomplete writes anyway? battery backed writeback caches on raid controllers flush any pending data to the disks when power is restored. if for some reason they can't, they flag an error when an application (such as database server) or file system issues a fdatasync or fsync, it expects that when that operation returns success, all data has been committed to non-volatile storage. BBWC exist to speed up that critical operation, as actualy committing data to disk is slow and expensive. This is of particular importance to a transactional database server, each COMMIT; has to be committed to disk. I am intentionally sidestepping the issue of cheap desktop grade storage that ignores buffer flush commands as these really aren't suitable for transactional database servers unless your data just isn't that important. IDE and SATA stuff has always been 'soft' on this, while SCSI, FC, and SAS drives are much more consistent.