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.
Signed-off-by: Martin Liu <liumartin@xxxxxxxxxx>
---
include/trace/events/kmem.h | 33 +++++++++++++++++++++++++++++++++
mm/page_alloc.c | 1 +
2 files changed, 34 insertions(+)
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index b37eb0a7060f..5fd392dae503 100644
--- 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 579789600a3c..50893061db66 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5920,6 +5920,7 @@ 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);
}
--
2.48.1.711.g2feabab25a-goog
