Re: squashfs performance regression and readahea

[Matthew Wilcox <willy@infradead.org>]

On Tue, May 10, 2022 at 02:11:41AM +0100, Phillip Lougher wrote:
> On 09/05/2022 14:21, Matthew Wilcox wrote:
> > On Mon, May 09, 2022 at 08:43:45PM +0800, Xiongwei Song wrote:
> > > Hi Hsin-Yi and Matthew,
> > > 
> > > With the patch from the attachment on linux 5.10, ran the command as I
> > > mentioned earlier,
> > > got the results below:
> > > 1:40.65 (1m + 40.65s)
> > > 1:10.12
> > > 1:11.10
> > > 1:11.47
> > > 1:11.59
> > > 1:11.94
> > > 1:11.86
> > > 1:12.04
> > > 1:12.21
> > > 1:12.06
> > > 
> > > The performance has improved obviously, but compared to linux 4.18, the
> > > performance is not so good.
> > > 
> > > Moreover, I wanted to test on linux 5.18. But I think I should revert
> > > 9eec1d897139 ("squashfs: provide backing_dev_info in order to disable
> > > read-ahead"),
> > > right?  Otherwise, the patch doesn't work?
> > 
> > I've never seen patch 9eec1d897139 before.  If you're going to point
> > out bugs in my code, at least have the decency to cc me on it.  It
> > should never have gone in, and should be reverted so the problem can
> > be fixed properly.
> 
> You are not in charge of what patches goes into Squashfs, that is my
> perogative as maintainer of Squashfs.

I think you mean 'prerogative'.  And, no, your filesystem is not your
little fiefdom, it's part of a collaborative effort.

> That patch (by Huawei) fixes the performance regression in Squashfs
> by disabling readahead, and it is good workaround until something
> better.

You *didn't even report the problem to me*.  How can it be fixed if I'm
not aware of it?