From: Bo Zhang <zhangbo0325@gmail.com>
To: akpm@linux-foundation.org, vbabka@kernel.org, david@kernel.org
Cc: surenb@google.com, mhocko@suse.com, brendan.jackman@linux.dev,
hannes@cmpxchg.org, ziy@nvidia.com, ljs@kernel.org,
liam@infradead.org, rppt@kernel.org, qi.zheng@linux.dev,
shakeel.butt@linux.dev, kasong@tencent.com, baohua@kernel.org,
axelrasmussen@google.com, yuanchu@google.com, weixugc@google.com,
zhaonanzhe@xiaomi.com, lipengfei28@xiaomi.com,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Bo Zhang <zhangbo56@xiaomi.com>
Subject: [RFC PATCH v2 2/4] mm: compaction: target mTHP order for proactive compaction
Date: Thu, 1 Oct 2026 08:14:10 +0800 [thread overview]
Message-ID: <20261001001412.3837085-3-zhangbo56@xiaomi.com> (raw)
In-Reply-To: <20261001001412.3837085-1-zhangbo56@xiaomi.com>
Proactive compaction triggers against COMPACTION_HPAGE_ORDER (order-9),
which is too heavyweight and misdirected for mTHP systems where the
pressure is on smaller orders like order-2.
Add compact_hpage_order() to return the highest always-enabled anonymous
mTHP order, and use it as the proactive compaction target in
should_proactive_compact_node(), __compact_finished() and kcompactd().
Fragmentation scores are not comparable across orders, a small order
scores much lower for the same state, so scale the proactive watermarks
down in proportion to the target order, otherwise order-2 would rarely
reach the order-9 threshold.
Signed-off-by: Bo Zhang <zhangbo56@xiaomi.com>
---
mm/compaction.c | 40 ++++++++++++++++++++++++++++++++--------
1 file changed, 32 insertions(+), 8 deletions(-)
diff --git a/mm/compaction.c b/mm/compaction.c
index ecd3e6cf54fc..3928a5483efc 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -24,6 +24,7 @@
#include <linux/page_owner.h>
#include <linux/psi.h>
#include <linux/cpuset.h>
+#include <linux/huge_mm.h>
#include "page_alloc.h"
#include "internal.h"
@@ -81,6 +82,17 @@ static inline bool is_via_compact_memory(int order) { return false; }
#define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT)
#endif
+static inline int compact_hpage_order(void)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ unsigned long orders = READ_ONCE(huge_anon_orders_always);
+
+ if (orders)
+ return __fls(orders);
+#endif
+ return COMPACTION_HPAGE_ORDER;
+}
+
static struct page *mark_allocated_noprof(struct page *page, unsigned int order, gfp_t gfp_flags)
{
post_alloc_hook(page, order, __GFP_MOVABLE, ALLOC_DEFAULT);
@@ -2257,24 +2269,36 @@ static unsigned int fragmentation_score_node(pg_data_t *pgdat, unsigned int orde
return score;
}
-static unsigned int fragmentation_score_wmark(bool low)
+/*
+ * Fragmentation scores are not comparable across orders: a lower order
+ * scores much lower than a higher order for the same fragmentation state.
+ * Scale the watermark proportionally to the target order so a small order
+ * can still trigger proactive compaction; COMPACTION_HPAGE_ORDER keeps the
+ * original threshold.
+ */
+static unsigned int fragmentation_score_wmark(bool low, unsigned int order)
{
- unsigned int wmark_low, leeway;
+ unsigned int wmark_low, leeway, wmark;
wmark_low = 100U - sysctl_compaction_proactiveness;
leeway = min(10U, wmark_low / 2);
- return low ? wmark_low : min(wmark_low + leeway, 100U);
+ wmark = low ? wmark_low : min(wmark_low + leeway, 100U);
+
+ if (order < COMPACTION_HPAGE_ORDER)
+ wmark = wmark * order / COMPACTION_HPAGE_ORDER;
+
+ return wmark;
}
static bool should_proactive_compact_node(pg_data_t *pgdat)
{
int wmark_high;
- unsigned int order = COMPACTION_HPAGE_ORDER;
+ unsigned int order = compact_hpage_order();
if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat))
return false;
- wmark_high = fragmentation_score_wmark(false);
+ wmark_high = fragmentation_score_wmark(false, order);
return fragmentation_score_node(pgdat, order) > wmark_high;
}
@@ -2306,7 +2330,7 @@ static enum compact_result __compact_finished(struct compact_control *cc)
if (cc->proactive_compaction) {
int score, wmark_low;
- unsigned int order = COMPACTION_HPAGE_ORDER;
+ unsigned int order = compact_hpage_order();
pg_data_t *pgdat;
pgdat = cc->zone->zone_pgdat;
@@ -2314,7 +2338,7 @@ static enum compact_result __compact_finished(struct compact_control *cc)
return COMPACT_PARTIAL_SKIPPED;
score = fragmentation_score_zone(cc->zone, order);
- wmark_low = fragmentation_score_wmark(true);
+ wmark_low = fragmentation_score_wmark(true, order);
if (score > wmark_low)
ret = COMPACT_CONTINUE;
@@ -3239,7 +3263,7 @@ static int kcompactd(void *p)
timeout = default_timeout;
if (should_proactive_compact_node(pgdat)) {
unsigned int prev_score, score;
- unsigned int order = COMPACTION_HPAGE_ORDER;
+ unsigned int order = compact_hpage_order();
prev_score = fragmentation_score_node(pgdat, order);
compact_node(pgdat, true);
--
2.34.1
next prev parent reply other threads:[~2026-10-01 0:14 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-01 0:14 [RFC PATCH v2 0/4] mm: compaction: mTHP-friendly memory compaction Bo Zhang
2026-10-01 0:14 ` [RFC PATCH v2 1/4] mm: compaction: parameterize fragmentation score by order Bo Zhang
2026-10-01 0:14 ` Bo Zhang [this message]
2026-10-19 8:12 ` [RFC PATCH v2 2/4] mm: compaction: target mTHP order for proactive compaction Dev Jain
2026-10-19 14:50 ` Xueyuan Chen
2026-10-19 15:03 ` Bo Zhang
2026-10-20 6:48 ` Dev Jain
2026-10-21 6:18 ` Bo Zhang
2026-10-19 15:47 ` Bo Zhang
2026-10-01 0:14 ` [RFC PATCH v2 3/4] mm: compaction: skip isolating large folios that already satisfy mTHP Bo Zhang
2026-10-01 0:14 ` [RFC PATCH v2 4/4] mm: compaction: skip unmovable blocks for non-costly proactive mTHP compaction Bo Zhang
2026-10-19 9:43 ` Dev Jain
2026-10-19 15:50 ` [RFC PATCH v2 0/4] mm: compaction: mTHP-friendly memory compaction Xueyuan Chen
2026-10-20 14:52 ` Vlastimil Babka (SUSE)
2026-10-21 6:00 ` Bo Zhang
2026-10-21 9:31 ` Vlastimil Babka (SUSE)
2026-10-21 12:31 ` Bo Zhang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261001001412.3837085-3-zhangbo56@xiaomi.com \
--to=zhangbo0325@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=baohua@kernel.org \
--cc=brendan.jackman@linux.dev \
--cc=david@kernel.org \
--cc=hannes@cmpxchg.org \
--cc=kasong@tencent.com \
--cc=liam@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lipengfei28@xiaomi.com \
--cc=ljs@kernel.org \
--cc=mhocko@suse.com \
--cc=qi.zheng@linux.dev \
--cc=rppt@kernel.org \
--cc=shakeel.butt@linux.dev \
--cc=surenb@google.com \
--cc=vbabka@kernel.org \
--cc=weixugc@google.com \
--cc=yuanchu@google.com \
--cc=zhangbo56@xiaomi.com \
--cc=zhaonanzhe@xiaomi.com \
--cc=ziy@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®