This message is from the T13 list server.
The last paragraph of section 4.20 in ATAPI-7 clearly states that WRITE DMA QUEUED FUA EXT (could we make this name longer) is "unique". It also goes on to state "regardless of the state of any cache". That is the best case I found for our discussions. In most cases this would be ok. The exception would be as in Mark's example, the write happened to overlap queued read or write requests. The main concern was insuring the data from the FUA command was written to the media in a very timely manner. Gary Laatsch [EMAIL PROTECTED] ----- Original Message ----- From: "Hale Landis" <[EMAIL PROTECTED]> To: "T13 List Server" <[EMAIL PROTECTED]> Sent: Monday, June 16, 2003 7:46 AM Subject: Re: [t13] ATA-7 Write DMA Queued FUA EXT problem > This message is from the T13 list server. > > > Does FUA mean access the media ONLY for the single command that > requests FUA or for all data currently in the "write cache" > (basically combining the effect of some writes followed by a FLUSH > CACHE) or is it something far more complex (and therefore more > subject to failure?). > > Did the requester of this "feature" ever provide more info or a > better description of what it was they really wanted? > > Hale > > > > *** Hale Landis *** www.ata-atapi.com *** > > > > >
