On Mon, Jan 29 2024 at 5:12P -0500,
Dave Chinner <david@xxxxxxxxxxxxx> wrote:
> On Mon, Jan 29, 2024 at 12:19:02PM -0500, Mike Snitzer wrote:
> > While I'm sure this legacy application would love to not have to
> > change its code at all, I think we can all agree that we need to just
> > focus on how best to advise applications that have mixed workloads
> > accomplish efficient mmap+read of both sequential and random.
> >
> > To that end, I heard Dave clearly suggest 2 things:
> >
> > 1) update MADV/FADV_SEQUENTIAL to set file->f_ra.ra_pages to
> > bdi->io_pages, not bdi->ra_pages * 2
> >
> > 2) Have the application first issue MADV_SEQUENTIAL to convey that for
> > the following MADV_WILLNEED is for sequential file load (so it is
> > desirable to use larger ra_pages)
> >
> > This overrides the default of bdi->ra_pages and _should_ provide the
> > required per-file duality of control for readahead, correct?
>
> I just discovered MADV_POPULATE_READ - see my reply to Ming
> up-thread about that. The applicaiton should use that instead of
> MADV_WILLNEED because it gives cache population guarantees that
> WILLNEED doesn't. Then we can look at optimising the performance of
> MADV_POPULATE_READ (if needed) as there is constrained scope we can
> optimise within in ways that we cannot do with WILLNEED.
Nice find! Given commit 4ca9b3859dac ("mm/madvise: introduce
MADV_POPULATE_(READ|WRITE) to prefault page tables"), I've cc'd David
Hildenbrand just so he's in the loop.
FYI, I proactively raised feedback and questions to the reporter of
this issue:
CONTEXT: madvise(WILLNEED) doesn't convey the nature of the access,
sequential vs random, just the range that may be accessed.
Q1: Is your application's sequential vs random (or smaller sequential)
access split on a per-file basis? Or is the same file accessed both
sequentially and randomly?
A1: The same files can be accessed either randomly or sequentially,
depending on certain access patterns and optimizing logic.
Q2: Can the application be changed to use madvise() MADV_SEQUENTIAL
and MADV_RANDOM to indicate its access pattern?
A2: No, the application is a Java application. Java does not expose
MADVISE API directly. Our application uses Java NIO API via
MappedByteBuffer.load()
(https://docs.oracle.com/javase/8/docs/api/java/nio/MappedByteBuffer.html#load--)
that calls MADVISE_WILLNEED at the low level. There is no way for us
to switch this behavior, but we take advantage of this behavior to
optimize large file sequential I/O with great success.
So it's looking like it'll be hard to help this reporter avoid
changes... but that's not upstream's problem!
Mike
