mm/page_alloc: add trace event for per-zone watermark setup

Patch series "Add tracepoints for lowmem reserves, watermarks and
totalreserve_pages", v2.

This patchset introduces tracepoints to track changes in the lowmem
reserves, watermarks and totalreserve_pages. This helps to track
the exact timing of such changes and understand their relation to
reclaim activities.

The tracepoints added are:

mm_setup_per_zone_lowmem_reserve
mm_setup_per_zone_wmarks
mm_calculate_totalreserve_pagesi

This patch (of 3):

This commit introduces the `mm_setup_per_zone_wmarks` trace event,
which provides detailed insights into the kernel's per-zone watermark
configuration, offering precise timing and the ability to correlate
watermark changes with specific kernel events.

While `/proc/zoneinfo` provides some information about zone watermarks,
this trace event offers:

1. The ability to link watermark changes to specific kernel events and
   logic.

2. The ability to capture rapid or short-lived changes in watermarks
   that may be missed by user-space polling

3. Diagnosing unexpected kswapd activity or excessive direct reclaim
   triggered by rapidly changing watermarks.

Link: https://lkml.kernel.org/r/20250308034606.2036033-1-liumartin@google.com
Link: https://lkml.kernel.org/r/20250308034606.2036033-2-liumartin@google.com
Signed-off-by: Martin Liu <liumartin@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Martin Liu <liumartin@google.com>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index b37eb0a7060ffac01f482d66602fc16b98e0849f..5fd392dae503e240c3ddc80bf409338e9c719b11 100644 (file)
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -342,6 +342,39 @@ TRACE_EVENT(mm_alloc_contig_migrate_range_info,
                  __entry->nr_mapped)
 );
 
+TRACE_EVENT(mm_setup_per_zone_wmarks,
+
+       TP_PROTO(struct zone *zone),
+
+       TP_ARGS(zone),
+
+       TP_STRUCT__entry(
+               __field(int, node_id)
+               __string(name, zone->name)
+               __field(unsigned long, watermark_min)
+               __field(unsigned long, watermark_low)
+               __field(unsigned long, watermark_high)
+               __field(unsigned long, watermark_promo)
+       ),
+
+       TP_fast_assign(
+               __entry->node_id = zone->zone_pgdat->node_id;
+               __assign_str(name);
+               __entry->watermark_min = zone->_watermark[WMARK_MIN];
+               __entry->watermark_low = zone->_watermark[WMARK_LOW];
+               __entry->watermark_high = zone->_watermark[WMARK_HIGH];
+               __entry->watermark_promo = zone->_watermark[WMARK_PROMO];
+       ),
+
+       TP_printk("node_id=%d zone name=%s watermark min=%lu low=%lu high=%lu promo=%lu",
+                 __entry->node_id,
+                 __get_str(name),
+                 __entry->watermark_min,
+                 __entry->watermark_low,
+                 __entry->watermark_high,
+                 __entry->watermark_promo)
+);
+
 /*
  * Required for uniquely and securely identifying mm in rss_stat tracepoint.
  */

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2c6ae7e5aaad937c3c7bd3833bf73c0523c6ece7..b739367434ce87cbaf980b76a5484c780c8f0817 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6006,6 +6006,7 @@ static void __setup_per_zone_wmarks(void)
                zone->_watermark[WMARK_LOW]  = min_wmark_pages(zone) + tmp;
                zone->_watermark[WMARK_HIGH] = low_wmark_pages(zone) + tmp;
                zone->_watermark[WMARK_PROMO] = high_wmark_pages(zone) + tmp;
+               trace_mm_setup_per_zone_wmarks(zone);
 
                spin_unlock_irqrestore(&zone->lock, flags);
        }