Messages in this thread | | | Date | Thu, 13 Aug 2009 18:45:18 +0100 (BST) | From | Hugh Dickins <> | Subject | Re: [PATCH] swap: send callback when swap slot is freed |
| |
On Thu, 13 Aug 2009, Nitin Gupta wrote: > On 08/13/2009 04:18 AM, Hugh Dickins wrote: > > > But fundamentally, though I can see how this cutdown communication > > path is useful to compcache, I'd much rather deal with it by the more > > general discard route if we can. > > I tried this too -- make discard bio request as soon as a swap slot becomes > free (I can send details if you want). However, I could not get it to work.
I'll send you an updated version of what I experimented with eight months ago: but changes in the swap_map count handling since then mean that it might need some subtle adjustments - I'll need to go over it carefully and retest before sending you.
(But that won't be a waste of my time: I shall soon need to try that experiment again myself, and I do need to examine those intervening swap_map count changes more closely.)
> Also, allocating bio to issue discard I/O request looks like a complete > artifact in compcache case.
Yes, I do understand that feeling.
Hugh
| |