Re: [Nbd] Question about the expected behaviour of nbd-server for async ops
Brought to you by:
yoe
|
From: Alex B. <al...@al...> - 2011-05-28 19:40:14
|
Goswin, --On 28 May 2011 17:35:22 +0100 Alex Bligh <al...@al...> wrote: >> As such >> the server has to internally ensure the proper order of overlapping >> requests. > > Slightly surprisingly, the fsdevel folk's answer to this is that you > can disorder both reads and writes and do what is natural, i.e. do > not maintain ordering. A file system which cares about the result > should not issue reads of blocks for which the writes have not > completed. I should add that if you do not process overlapping writes and reads in order, you a) will fail the integrity test suite. b) will fall foul of any filing system which does not stick precisely by the letter of the law. I thus recommend not exploiting this. -- Alex Bligh |