Re: [PATCH v3 0/6] Composefs: an opportunistically sharing verified image filesystem

From: Alexander Larsson
Date: Wed Feb 01 2023 - 04:53:31 EST


On Wed, 2023-02-01 at 16:59 +0800, Jingbo Xu wrote:
>
> I redid the test with suggestion from Amir, with all files inside the
> erofs layer are redirected to the same lower block, e.g.
> "/objects/00/014430a0b489d101c8a103ef829dd258448a13eb48b4d1e9ff0731d1
> e82b92".
>
> The result is shown in the fourth line.
>
>                                   | uncached(ms)| cached(ms)
> ----------------------------------|-------------|-----------
> composefs (with digest)           | 326         | 135
> erofs (w/o -T0)                   | 264         | 172
> erofs (w/o -T0) + overlayfs       | 651         | 238
> erofs (hacked and redirect to one |             |
> lower block) + overlayfs          | 400         | 230
>
> It seems that the "lazy lookup" in overlayfs indeed optimizes in this
> situation.
>
>
> The performance gap in cached situation (especially comparing
> composefs
> and standalone erofs) is still under investigation and I will see if
> there's any hint by perf diff.

The fact that plain erofs is faster than composefs uncached, but slower
cached is very strange. Also, see my other mail where erofs+ovl cached
is slower than squashfs+ovl cached for me. Something seems to be off
with the cached erofs case...


--
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
=-=-=
Alexander Larsson Red Hat,
Inc
alexl@xxxxxxxxxx alexander.larsson@xxxxxxxxx
He's a sword-wielding alcoholic barbarian She's a pregnant snooty nun
who
dreams of becoming Elvis. They fight crime!