Re: Readahead regressed with c1f6925e1091("mm: put readahead pages in cache earlier") on multicore arm64 platforms

[Matthew Wilcox <willy@infradead.org>]

On Wed, Oct 06, 2021 at 09:07:56PM +0800, Hsin-Yi Wang wrote:
> On Wed, Oct 6, 2021 at 7:21 PM Matthew Wilcox <willy@infradead.org> wrote:
> >
> > On Wed, Oct 06, 2021 at 05:25:23PM +0800, Hsin-Yi Wang wrote:
> > > Hi Matthew,
> > >
> > > We tested that the performance of readahead is regressed on multicore
> > > arm64 platforms running on the 5.10 kernel.
> > > - The platform we used: 8 cores (4x a53(small), 4x a73(big)) arm64 platform
> > > - The command we used: ureadahead $FILE ($FILE is a 1MB+ pack file,
> > > note that if the file size is small, it's not obvious to see the
> > > regression)
> > >
> > > After we revert the commit c1f6925e1091("mm: put readahead pages in
> > > cache earlier"), the readahead performance is back:
> > > - time ureadahead $FILE:
> > >   - 5.10: 1m23.124s
> > >   - with c1f6925e1091 reverted: 0m3.323s
> > >   - other LTS kernel (eg. 5.4): 0m3.066s
> > >
> > > The slowest part is aops->readpage() in read_pages() called in
> > > read_pages(ractl, &page_pool, false); (the 3rd in
> > > page_cache_ra_unbounded())
> >
> > What filesystem are you using?
> >
> ext4, block size 4096

That's confusing.  ext4 shouldn't hit that path; it has a ->readahead
address space operation.