On Sun, 10 June 2007 20:33:05 +0200, Arnd Bergmann wrote: > > Then maybe the submit_bio logic should only be done for the ->write > path, not for ->read. The data that gets written out should already > be present in the page cache for the files, so there is not much point > having again, while you can see the read path as blockdev readahead: > When you read a physical block that contains a logical block, it's > likely to also contain part of another logical block that is going > to be read in the near future. Makes a lot of sense, yes. > This way, you would also get exclusively clean pages in the block > device address_space, which can be easily discarded. > > Also, maintaining correct ordering between write requests can be > done easier if you insert the bios directly, instead of waiting > for the lru writeback. s/easier/only/ ? I don't think logfs on block devices makes too much sense yet, so my personal priority for this is low. Still, an obvious improvement. Jörn -- ...one more straw can't possibly matter... -- Kirby Bakken - 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