On Thu, May 26, 2022 at 10:12:10AM +0100, Mel Gorman wrote:
> Peter Pavlisko reported the following problem on kernel bugzilla 216007.
>
> When I try to extract an uncompressed tar archive (2.6 milion
> files, 760.3 GiB in size) on newly created (empty) XFS file system,
> after first low tens of gigabytes extracted the process hangs in
> iowait indefinitely. One CPU core is 100% occupied with iowait,
> the other CPU core is idle (on 2-core Intel Celeron G1610T).
>
> It was bisected to c9fa563072e1 ("xfs: use alloc_pages_bulk_array() for
> buffers") but XFS is only the messenger. The problem is that nothing
> is waking kswapd to reclaim some pages at a time the PCP lists cannot
> be refilled until some reclaim happens. The bulk allocator checks that
> there are some pages in the array and the original intent was that a bulk
> allocator did not necessarily need all the requested pages and it was
> best to return as quickly as possible. This was fine for the first user
> of the API but both NFS and XFS require the requested number of pages
> be available before making progress. Both could be adjusted to call the
> page allocator directly if a bulk allocation fails but it puts a burden on
> users of the API. Adjust the semantics to attempt at least one allocation
> via __alloc_pages() before returning so kswapd is woken if necessary.
>
> It was reported via bugzilla that the patch addressed the problem and
> that the tar extraction completed successfully. This may also address
> bug 215975 but has yet to be confirmed.
>
> BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=216007
> BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=215975
> Fixes: 387ba26fb1cb ("mm/page_alloc: add a bulk page allocator")
> Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
> Cc: <stable@xxxxxxxxxxxxxxx> # v5.13+
> ---
> mm/page_alloc.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 0e42038382c1..5ced6cb260ed 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5324,8 +5324,8 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
> page = __rmqueue_pcplist(zone, 0, ac.migratetype, alloc_flags,
> pcp, pcp_list);
> if (unlikely(!page)) {
> - /* Try and get at least one page */
> - if (!nr_populated)
> + /* Try and allocate at least one page */
> + if (!nr_account)
> goto failed_irq;
> break;
> }
Looks like a sane fix to me.
Acked-by: Dave Chinner <dchinner@xxxxxxxxxx>
--
Dave Chinner
david@xxxxxxxxxxxxx
