Re: [PATCH 0/3 v5] Introduce a bulk order-0 page allocator

[Jesper Dangaard Brouer]

On Tue, 23 Mar 2021 10:44:21 +0000
Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> wrote:

> On Mon, Mar 22, 2021 at 09:18:42AM +0000, Mel Gorman wrote:
> > This series is based on top of Matthew Wilcox's series "Rationalise
> > __alloc_pages wrapper" and does not apply to 5.12-rc2. If you want to
> > test and are not using Andrew's tree as a baseline, I suggest using the
> > following git tree
> > 
> > git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux.git mm-bulk-rebase-v5r9
> >   
> 
> Jesper and Chuck, would you mind rebasing on top of the following branch
> please? 
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux.git mm-bulk-rebase-v6r2
> 
> The interface is the same so the rebase should be trivial.
> 
> Jesper, I'm hoping you see no differences in performance but it's best
> to check.

I will rebase and check again.

The current performance tests that I'm running, I observe that the
compiler layout the code in unfortunate ways, which cause I-cache
performance issues.  I wonder if you could integrate below patch with
your patchset? (just squash it)

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer

[PATCH] mm: optimize code layout for __alloc_pages_bulk

From: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>

Looking at perf-report and ASM-code for __alloc_pages_bulk() then the code
activated is suboptimal. The compiler guess wrong and place unlikely code in
the beginning. Due to the use of WARN_ON_ONCE() macro the UD2 asm
instruction is added to the code, which confuse the I-cache prefetcher in
the CPU

Signed-off-by: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
---
 mm/page_alloc.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f60f51a97a7b..88a5c1ce5b87 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5003,10 +5003,10 @@ int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 	unsigned int alloc_flags;
 	int nr_populated = 0, prep_index = 0;
 
-	if (WARN_ON_ONCE(nr_pages <= 0))
+	if (unlikely(nr_pages <= 0))
 		return 0;
 
-	if (WARN_ON_ONCE(page_list && !list_empty(page_list)))
+	if (unlikely(page_list && !list_empty(page_list)))
 		return 0;
 
 	/* Skip populated array elements. */
@@ -5018,7 +5018,7 @@ int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 		prep_index = nr_populated;
 	}
 
-	if (nr_pages == 1)
+	if (unlikely(nr_pages == 1))
 		goto failed;
 
 	/* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
@@ -5054,7 +5054,7 @@ int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 	 * If there are no allowed local zones that meets the watermarks then
 	 * try to allocate a single page and reclaim if necessary.
 	 */
-	if (!zone)
+	if (unlikely(!zone))
 		goto failed;
 
 	/* Attempt the batch allocation */
@@ -5075,7 +5075,7 @@ int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 
 		page = __rmqueue_pcplist(zone, ac.migratetype, alloc_flags,
 								pcp, pcp_list);
-		if (!page) {
+		if (unlikely(!page)) {
 			/* Try and get at least one page */
 			if (!nr_populated)
 				goto failed_irq;