Messages in this thread | | | Date | Thu, 18 Nov 2010 18:05:57 +0000 | From | Jamie Lokier <> | Subject | Re: [PATCH 1/2] fs: Do not dispatch FITRIM through separate super_operation |
| |
Jeff Moyer wrote: > James Bottomley <James.Bottomley@suse.de> writes: > > > Not stepping into the debate: I'm happy to see punch go to the mapping > > data and FITRIM pick it up later. > > > > However, I think it's time to question whether we actually still want to > > allow online discard at all. Most of the benchmarks show it to be a net > > Define online discard, please. > > > lose to almost everything (either SSD or Thinly Provisioned arrays), so > > it's become an "enable this to degrade performance" option with no > > upside. > > Some SSDs very much require TRIMming to perform well as they age. If > you're suggesting that we move from doing discards in journal commits to > a batched discard, like the one Lukas implemented, then I think that's > fine. If we need to reintroduce the finer-grained discards due to some > hardware changes in the future, we can always do that.
"Growable" virtual disks benefit from it too, if it frees up a lot of space.
Windows has some ability to trim unused space in NTFS on virtual disks for this reason; I'm not sure if it's an online or offline procedure.
Online trim may be slow, but offline would be awfully inconvenient when an fs is big and needed for a live system, or when it's your root fs.
-- Jamie
| |