| Message ID | 20250303073537.2264323-3-liumartin@google.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Add tracepoints for lowmem reserves, watermarks and totalreserve_pages | expand |
On Sun, Mar 2, 2025 at 11:36 PM Martin Liu <liumartin@google.com> wrote: > > This commit introduces the `mm_setup_per_zone_lowmem_reserve` trace > event,which provides detailed insights into the kernel's per-zone lowmem > reserve configuration. > > The trace event provides precise timestamps, allowing developers to > > 1. Correlate lowmem reserve changes with specific kernel events and > able to diagnose unexpected kswapd or direct reclaim behavior > triggered by dynamic changes in lowmem reserve. > > 2. know memory allocation failures that occur due to insufficient lowmem > reserve, by precisely correlating allocation attempts with reserve > adjustments. > > Signed-off-by: Martin Liu <liumartin@google.com> > --- > include/trace/events/kmem.h | 27 +++++++++++++++++++++++++++ > mm/page_alloc.c | 2 ++ > 2 files changed, 29 insertions(+) > > diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h > index 5fd392dae503..9623e68d4d26 100644 > --- a/include/trace/events/kmem.h > +++ b/include/trace/events/kmem.h > @@ -375,6 +375,33 @@ TRACE_EVENT(mm_setup_per_zone_wmarks, > __entry->watermark_promo) > ); > > +TRACE_EVENT(mm_setup_per_zone_lowmem_reserve, > + > + TP_PROTO(struct zone *zone, struct zone *upper_zone, long lowmem_reserve), > + > + TP_ARGS(zone, upper_zone, lowmem_reserve), > + > + TP_STRUCT__entry( > + __field(int, node_id) > + __string(name, zone->name) > + __string(upper_name, upper_zone->name) > + __field(long, lowmem_reserve) > + ), > + > + TP_fast_assign( > + __entry->node_id = zone->zone_pgdat->node_id; > + __assign_str(name); > + __assign_str(upper_name); > + __entry->lowmem_reserve = lowmem_reserve; > + ), > + > + TP_printk("node_id=%d zone name=%s upper_zone name=%s lowmem_reserve_pages=%ld", > + __entry->node_id, > + __get_str(name), > + __get_str(upper_name), > + __entry->lowmem_reserve) > +); > + > /* > * Required for uniquely and securely identifying mm in rss_stat tracepoint. > */ > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > index 50893061db66..48623a2bf1ac 100644 > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -5857,6 +5857,8 @@ static void setup_per_zone_lowmem_reserve(void) > zone->lowmem_reserve[j] = 0; > else > zone->lowmem_reserve[j] = managed_pages / ratio; > + trace_mm_setup_per_zone_lowmem_reserve(zone, upper_zone, > + zone->lowmem_reserve[j]); Hi Martin, Please use 8-character width tabs for indentation. -- Kalesh > } > } > } > -- > 2.48.1.711.g2feabab25a-goog > >
On Mon, Mar 03, 2025 at 12:18:46AM -0800, Kalesh Singh wrote: > On Sun, Mar 2, 2025 at 11:36 PM Martin Liu <liumartin@google.com> wrote: > > > > This commit introduces the `mm_setup_per_zone_lowmem_reserve` trace > > event,which provides detailed insights into the kernel's per-zone lowmem > > reserve configuration. > > > > The trace event provides precise timestamps, allowing developers to > > > > 1. Correlate lowmem reserve changes with specific kernel events and > > able to diagnose unexpected kswapd or direct reclaim behavior > > triggered by dynamic changes in lowmem reserve. > > > > 2. know memory allocation failures that occur due to insufficient lowmem > > reserve, by precisely correlating allocation attempts with reserve > > adjustments. > > > > Signed-off-by: Martin Liu <liumartin@google.com> > > --- > > include/trace/events/kmem.h | 27 +++++++++++++++++++++++++++ > > mm/page_alloc.c | 2 ++ > > 2 files changed, 29 insertions(+) > > > > diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h > > index 5fd392dae503..9623e68d4d26 100644 > > --- a/include/trace/events/kmem.h > > +++ b/include/trace/events/kmem.h > > @@ -375,6 +375,33 @@ TRACE_EVENT(mm_setup_per_zone_wmarks, > > __entry->watermark_promo) > > ); > > > > +TRACE_EVENT(mm_setup_per_zone_lowmem_reserve, > > + > > + TP_PROTO(struct zone *zone, struct zone *upper_zone, long lowmem_reserve), > > + > > + TP_ARGS(zone, upper_zone, lowmem_reserve), > > + > > + TP_STRUCT__entry( > > + __field(int, node_id) > > + __string(name, zone->name) > > + __string(upper_name, upper_zone->name) > > + __field(long, lowmem_reserve) > > + ), > > + > > + TP_fast_assign( > > + __entry->node_id = zone->zone_pgdat->node_id; > > + __assign_str(name); > > + __assign_str(upper_name); > > + __entry->lowmem_reserve = lowmem_reserve; > > + ), > > + > > + TP_printk("node_id=%d zone name=%s upper_zone name=%s lowmem_reserve_pages=%ld", > > + __entry->node_id, > > + __get_str(name), > > + __get_str(upper_name), > > + __entry->lowmem_reserve) > > +); > > + > > /* > > * Required for uniquely and securely identifying mm in rss_stat tracepoint. > > */ > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > > index 50893061db66..48623a2bf1ac 100644 > > --- a/mm/page_alloc.c > > +++ b/mm/page_alloc.c > > @@ -5857,6 +5857,8 @@ static void setup_per_zone_lowmem_reserve(void) > > zone->lowmem_reserve[j] = 0; > > else > > zone->lowmem_reserve[j] = managed_pages / ratio; > > + trace_mm_setup_per_zone_lowmem_reserve(zone, upper_zone, > > + zone->lowmem_reserve[j]); > > Hi Martin, > > Please use 8-character width tabs for indentation. Hi Kalesh, Yes, thank you for the reminders. I will address these once receiving feedback :) > > -- Kalesh > > } > > } > > } > > -- > > 2.48.1.711.g2feabab25a-goog > > > >
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 5fd392dae503..9623e68d4d26 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -375,6 +375,33 @@ TRACE_EVENT(mm_setup_per_zone_wmarks, __entry->watermark_promo) ); +TRACE_EVENT(mm_setup_per_zone_lowmem_reserve, + + TP_PROTO(struct zone *zone, struct zone *upper_zone, long lowmem_reserve), + + TP_ARGS(zone, upper_zone, lowmem_reserve), + + TP_STRUCT__entry( + __field(int, node_id) + __string(name, zone->name) + __string(upper_name, upper_zone->name) + __field(long, lowmem_reserve) + ), + + TP_fast_assign( + __entry->node_id = zone->zone_pgdat->node_id; + __assign_str(name); + __assign_str(upper_name); + __entry->lowmem_reserve = lowmem_reserve; + ), + + TP_printk("node_id=%d zone name=%s upper_zone name=%s lowmem_reserve_pages=%ld", + __entry->node_id, + __get_str(name), + __get_str(upper_name), + __entry->lowmem_reserve) +); + /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 50893061db66..48623a2bf1ac 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5857,6 +5857,8 @@ static void setup_per_zone_lowmem_reserve(void) zone->lowmem_reserve[j] = 0; else zone->lowmem_reserve[j] = managed_pages / ratio; + trace_mm_setup_per_zone_lowmem_reserve(zone, upper_zone, + zone->lowmem_reserve[j]); } } }
This commit introduces the `mm_setup_per_zone_lowmem_reserve` trace event,which provides detailed insights into the kernel's per-zone lowmem reserve configuration. The trace event provides precise timestamps, allowing developers to 1. Correlate lowmem reserve changes with specific kernel events and able to diagnose unexpected kswapd or direct reclaim behavior triggered by dynamic changes in lowmem reserve. 2. know memory allocation failures that occur due to insufficient lowmem reserve, by precisely correlating allocation attempts with reserve adjustments. Signed-off-by: Martin Liu <liumartin@google.com> --- include/trace/events/kmem.h | 27 +++++++++++++++++++++++++++ mm/page_alloc.c | 2 ++ 2 files changed, 29 insertions(+)