[Linux-cachefs] [PATCH 1/1] NFS: Convert from readpages() to readahead()

[David Wysochanski]

On Fri, Oct 8, 2021 at 10:10 AM Chuck Lever III <chuck.lever at oracle.com> wrote:
>
>
>
> > On Oct 7, 2021, at 7:32 PM, Dave Wysochanski <dwysocha at redhat.com> wrote:
> >
> > Convert to the new VM readahead() API which is the preferred API
> > to read multiple pages, and rename the NFSIOS_* counters and the
> > tracepoint as needed.
> >
> > Signed-off-by: Dave Wysochanski <dwysocha at redhat.com>
> > ---
> > fs/nfs/file.c              |  2 +-
> > fs/nfs/nfstrace.h          |  2 +-
> > fs/nfs/read.c              | 21 +++++++++++++++------
> > include/linux/nfs_fs.h     |  3 +--
> > include/linux/nfs_iostat.h |  6 +++---
> > 5 files changed, 21 insertions(+), 13 deletions(-)
> >
> > diff --git a/fs/nfs/file.c b/fs/nfs/file.c
> > index 209dac208477..cc76d17fa97f 100644
> > --- a/fs/nfs/file.c
> > +++ b/fs/nfs/file.c
> > @@ -519,7 +519,7 @@ static void nfs_swap_deactivate(struct file *file)
> >
> > const struct address_space_operations nfs_file_aops = {
> >       .readpage = nfs_readpage,
> > -     .readpages = nfs_readpages,
> > +     .readahead = nfs_readahead,
> >       .set_page_dirty = __set_page_dirty_nobuffers,
> >       .writepage = nfs_writepage,
> >       .writepages = nfs_writepages,
> > diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
> > index 78b0f649dd09..d2b2080765a6 100644
> > --- a/fs/nfs/nfstrace.h
> > +++ b/fs/nfs/nfstrace.h
> > @@ -915,7 +915,7 @@
> >               )
> > );
> >
> > -TRACE_EVENT(nfs_aops_readpages,
> > +TRACE_EVENT(nfs_aops_readahead,
>
> In v2 and v3 of my patch, this tracepoint has already been
> renamed to nfs_aop_readahead.
>

Ack.

>
> >               TP_PROTO(
> >                       const struct inode *inode,
> >                       unsigned int nr_pages
> > diff --git a/fs/nfs/read.c b/fs/nfs/read.c
> > index 927504605e0f..5c2aab47cf1d 100644
> > --- a/fs/nfs/read.c
> > +++ b/fs/nfs/read.c
> > @@ -395,15 +395,19 @@ int nfs_readpage(struct file *file, struct page *page)
> >       return ret;
> > }
> >
> > -int nfs_readpages(struct file *file, struct address_space *mapping,
> > -             struct list_head *pages, unsigned nr_pages)
> > +void nfs_readahead(struct readahead_control *ractl)
> > {
> > +     struct file *file = ractl->file;
> > +     struct address_space *mapping = ractl->mapping;
> > +     struct page *page;
> > +     unsigned int nr_pages = readahead_count(ractl);
> > +
> >       struct nfs_readdesc desc;
> >       struct inode *inode = mapping->host;
> >       int ret;
> >
> > -     trace_nfs_aops_readpages(inode, nr_pages);
> > -     nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
> > +     trace_nfs_aops_readahead(inode, nr_pages);
> > +     nfs_inc_stats(inode, NFSIOS_VFSREADAHEAD);
> >
> >       ret = -ESTALE;
> >       if (NFS_STALE(inode))
> > @@ -420,13 +424,18 @@ int nfs_readpages(struct file *file, struct address_space *mapping,
> >       nfs_pageio_init_read(&desc.pgio, inode, false,
> >                            &nfs_async_read_completion_ops);
> >
> > -     ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
> > +     ret = 0;
> > +     while (!ret && (page = readahead_page(ractl))) {
> > +             prefetchw(&page->flags);
> > +             ret = readpage_async_filler(&desc, page);
> > +             put_page(page);
> > +     }
> >
> >       nfs_pageio_complete_read(&desc.pgio);
> >
> >       put_nfs_open_context(desc.ctx);
> > out:
> > -     return ret;
> > +     return;
> > }
> >
> > int __init nfs_init_readpagecache(void)
> > diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
> > index b9a8b925db43..6cbe3f2c5669 100644
> > --- a/include/linux/nfs_fs.h
> > +++ b/include/linux/nfs_fs.h
> > @@ -580,8 +580,7 @@ extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, s
> >  * linux/fs/nfs/read.c
> >  */
> > extern int  nfs_readpage(struct file *, struct page *);
> > -extern int  nfs_readpages(struct file *, struct address_space *,
> > -             struct list_head *, unsigned);
> > +extern void nfs_readahead(struct readahead_control *);
> >
> > /*
> >  * inline functions
> > diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h
> > index 027874c36c88..418145f23700 100644
> > --- a/include/linux/nfs_iostat.h
> > +++ b/include/linux/nfs_iostat.h
> > @@ -22,7 +22,7 @@
> > #ifndef _LINUX_NFS_IOSTAT
> > #define _LINUX_NFS_IOSTAT
> >
> > -#define NFS_IOSTAT_VERS              "1.1"
> > +#define NFS_IOSTAT_VERS              "1.2"
> >
> > /*
> >  * NFS byte counters
> > @@ -53,7 +53,7 @@
> >  * NFS page counters
> >  *
> >  * These count the number of pages read or written via nfs_readpage(),
> > - * nfs_readpages(), or their write equivalents.
> > + * nfs_readahead(), or their write equivalents.
> >  *
> >  * NB: When adding new byte counters, please include the measured
> >  * units in the name of each byte counter to help users of this
> > @@ -98,7 +98,7 @@ enum nfs_stat_eventcounters {
> >       NFSIOS_VFSACCESS,
> >       NFSIOS_VFSUPDATEPAGE,
> >       NFSIOS_VFSREADPAGE,
> > -     NFSIOS_VFSREADPAGES,
> > +     NFSIOS_VFSREADAHEAD,
>
> I'm wondering if you should add NFSIOS_VFSREADAHEAD
> but leave NFSIOS_VFSREADPAGES? I don't remember exactly
> how the mountstats API versioning is supposed to work.
>

I don't think we need to keep this but correct me if I'm wrong.
That would mean we would have a 0 count for later kernels and I'm not
sure about that given the similarities.
You can see my nfs-utils patch for the attempt to use the versioning
in nfs-iostat.

>
> >       NFSIOS_VFSWRITEPAGE,
> >       NFSIOS_VFSWRITEPAGES,
> >       NFSIOS_VFSGETDENTS,
> > --
> > 1.8.3.1
> >
>
> --
> Chuck Lever
>
>
>