Yes, we have hosts that want to use the list form. I don't see how it doesn't match T13 TRIM command? Both can do single ranges. In both cases, you can have 1 LBA and 1 length. There is nothing requiring > 1 range to be sent via the SCSI proposal. In both cases, you pass the same values to the H/W driver. In one H/W driver it will load a bunch of values (including the LBA/length) into a set of registers (PATA) of a memory structure (SATA). In the other H/W driver, it will load a bunch of values into memory structures (CDB/buffer), and then tweek the H/W to send the memory structures. Most SCSI drivers I've seen that have tagged queuing enabled turn off their elevator algorithms (since the drive itself is doing it's own optimizations) There is no difference at the filesystem de-allocator level. The only difference is how the H/W sends the values to the other end of the wire, and there will always be differences at that layer. Fred Knight -----Original Message----- From: David Woodhouse [mailto:dwmw2@xxxxxxxxxxxxx] Sent: Tuesday, August 12, 2008 2:56 PM To: Knight, Frederick Cc: Matthew Wilcox; ricwheeler@xxxxxxxxx; linux-fsdevel@xxxxxxxxxxxxxxx; Christoph Hellwig Subject: RE: Thin device provisioning On Sat, 2008-08-09 at 13:12 -0400, Knight, Frederick wrote: > You are free to create a single pair API between your filesystems and > drivers and send SCSI commands one LBA/length pair at a time. > However, I'm afraid the voting members of T10 (representing a number > of other operating systems and their multitude of filesystems) > preferred the list approach. That seems like unneeded complexity to me. Admittedly the sample set of file systems I've converted to use this is small so far -- only 2 -- but it seems to me that it's always likely to be done in the 'free extent' code path as we mark blocks free, and I can't see the file system really taking advantage of the ability to pack multiple regions into the same request. It's hard for I/O elevators to merge these requests when they're not contiguous, too -- it would require a lot of special-casing to make it happen at that level. It's also somewhat suboptimal that it doesn't match the T13 'TRIM' proposal, which allows only a single range to be specified. That'll be fun for anyone doing SCSI<->ATA conversion... Has anyone actually claimed that they can and will use the list form, and have they also told the T13 forum the same thing? -- David Woodhouse Open Source Technology Centre David.Woodhouse@xxxxxxxxx Intel Corporation -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
