kernel-ark/include/trace/events/kmem.h

309 lines
7.0 KiB
C
Raw Normal View History

#undef TRACE_SYSTEM
#define TRACE_SYSTEM kmem
#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_KMEM_H
#include <linux/types.h>
#include <linux/tracepoint.h>
#include <trace/events/gfpflags.h>
DECLARE_EVENT_CLASS(kmem_alloc,
TP_PROTO(unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
gfp_t gfp_flags),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
TP_STRUCT__entry(
__field( unsigned long, call_site )
__field( const void *, ptr )
__field( size_t, bytes_req )
__field( size_t, bytes_alloc )
__field( gfp_t, gfp_flags )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
__entry->bytes_req = bytes_req;
__entry->bytes_alloc = bytes_alloc;
__entry->gfp_flags = gfp_flags;
),
TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
__entry->call_site,
__entry->ptr,
__entry->bytes_req,
__entry->bytes_alloc,
show_gfp_flags(__entry->gfp_flags))
);
DEFINE_EVENT(kmem_alloc, kmalloc,
TP_PROTO(unsigned long call_site, const void *ptr,
size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
);
DEFINE_EVENT(kmem_alloc, kmem_cache_alloc,
TP_PROTO(unsigned long call_site, const void *ptr,
size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
);
DECLARE_EVENT_CLASS(kmem_alloc_node,
TP_PROTO(unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
gfp_t gfp_flags,
int node),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
TP_STRUCT__entry(
__field( unsigned long, call_site )
__field( const void *, ptr )
__field( size_t, bytes_req )
__field( size_t, bytes_alloc )
__field( gfp_t, gfp_flags )
__field( int, node )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
__entry->bytes_req = bytes_req;
__entry->bytes_alloc = bytes_alloc;
__entry->gfp_flags = gfp_flags;
__entry->node = node;
),
TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
__entry->call_site,
__entry->ptr,
__entry->bytes_req,
__entry->bytes_alloc,
show_gfp_flags(__entry->gfp_flags),
__entry->node)
);
DEFINE_EVENT(kmem_alloc_node, kmalloc_node,
TP_PROTO(unsigned long call_site, const void *ptr,
size_t bytes_req, size_t bytes_alloc,
gfp_t gfp_flags, int node),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
);
DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node,
TP_PROTO(unsigned long call_site, const void *ptr,
size_t bytes_req, size_t bytes_alloc,
gfp_t gfp_flags, int node),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
);
DECLARE_EVENT_CLASS(kmem_free,
TP_PROTO(unsigned long call_site, const void *ptr),
TP_ARGS(call_site, ptr),
TP_STRUCT__entry(
__field( unsigned long, call_site )
__field( const void *, ptr )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
),
TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
);
DEFINE_EVENT(kmem_free, kfree,
TP_PROTO(unsigned long call_site, const void *ptr),
TP_ARGS(call_site, ptr)
);
DEFINE_EVENT(kmem_free, kmem_cache_free,
TP_PROTO(unsigned long call_site, const void *ptr),
TP_ARGS(call_site, ptr)
);
TRACE_EVENT(mm_page_free,
TP_PROTO(struct page *page, unsigned int order),
TP_ARGS(page, order),
TP_STRUCT__entry(
__field( struct page *, page )
__field( unsigned int, order )
),
TP_fast_assign(
__entry->page = page;
__entry->order = order;
),
TP_printk("page=%p pfn=%lu order=%d",
__entry->page,
page_to_pfn(__entry->page),
__entry->order)
);
TRACE_EVENT(mm_page_free_batched,
TP_PROTO(struct page *page, int cold),
TP_ARGS(page, cold),
TP_STRUCT__entry(
__field( struct page *, page )
__field( int, cold )
),
TP_fast_assign(
__entry->page = page;
__entry->cold = cold;
),
TP_printk("page=%p pfn=%lu order=0 cold=%d",
__entry->page,
page_to_pfn(__entry->page),
__entry->cold)
);
TRACE_EVENT(mm_page_alloc,
TP_PROTO(struct page *page, unsigned int order,
gfp_t gfp_flags, int migratetype),
TP_ARGS(page, order, gfp_flags, migratetype),
TP_STRUCT__entry(
__field( struct page *, page )
__field( unsigned int, order )
__field( gfp_t, gfp_flags )
__field( int, migratetype )
),
TP_fast_assign(
__entry->page = page;
__entry->order = order;
__entry->gfp_flags = gfp_flags;
__entry->migratetype = migratetype;
),
TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s",
__entry->page,
__entry->page ? page_to_pfn(__entry->page) : 0,
__entry->order,
__entry->migratetype,
show_gfp_flags(__entry->gfp_flags))
);
DECLARE_EVENT_CLASS(mm_page,
tracing, page-allocator: add trace event for page traffic related to the buddy lists The page allocation trace event reports that a page was successfully allocated but it does not specify where it came from. When analysing performance, it can be important to distinguish between pages coming from the per-cpu allocator and pages coming from the buddy lists as the latter requires the zone lock to the taken and more data structures to be examined. This patch adds a trace event for __rmqueue reporting when a page is being allocated from the buddy lists. It distinguishes between being called to refill the per-cpu lists or whether it is a high-order allocation. Similarly, this patch adds an event to catch when the PCP lists are being drained a little and pages are going back to the buddy lists. This is trickier to draw conclusions from but high activity on those events could explain why there were a large number of cache misses on a page-allocator-intensive workload. The coalescing and splitting of buddies involves a lot of writing of page metadata and cache line bounces not to mention the acquisition of an interrupt-safe lock necessary to enter this path. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Li Ming Chun <macli@brc.ubc.ca> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:02:44 +00:00
TP_PROTO(struct page *page, unsigned int order, int migratetype),
TP_ARGS(page, order, migratetype),
TP_STRUCT__entry(
__field( struct page *, page )
__field( unsigned int, order )
__field( int, migratetype )
),
TP_fast_assign(
__entry->page = page;
__entry->order = order;
__entry->migratetype = migratetype;
),
TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d",
__entry->page,
__entry->page ? page_to_pfn(__entry->page) : 0,
tracing, page-allocator: add trace event for page traffic related to the buddy lists The page allocation trace event reports that a page was successfully allocated but it does not specify where it came from. When analysing performance, it can be important to distinguish between pages coming from the per-cpu allocator and pages coming from the buddy lists as the latter requires the zone lock to the taken and more data structures to be examined. This patch adds a trace event for __rmqueue reporting when a page is being allocated from the buddy lists. It distinguishes between being called to refill the per-cpu lists or whether it is a high-order allocation. Similarly, this patch adds an event to catch when the PCP lists are being drained a little and pages are going back to the buddy lists. This is trickier to draw conclusions from but high activity on those events could explain why there were a large number of cache misses on a page-allocator-intensive workload. The coalescing and splitting of buddies involves a lot of writing of page metadata and cache line bounces not to mention the acquisition of an interrupt-safe lock necessary to enter this path. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Li Ming Chun <macli@brc.ubc.ca> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:02:44 +00:00
__entry->order,
__entry->migratetype,
__entry->order == 0)
);
DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked,
tracing, page-allocator: add trace event for page traffic related to the buddy lists The page allocation trace event reports that a page was successfully allocated but it does not specify where it came from. When analysing performance, it can be important to distinguish between pages coming from the per-cpu allocator and pages coming from the buddy lists as the latter requires the zone lock to the taken and more data structures to be examined. This patch adds a trace event for __rmqueue reporting when a page is being allocated from the buddy lists. It distinguishes between being called to refill the per-cpu lists or whether it is a high-order allocation. Similarly, this patch adds an event to catch when the PCP lists are being drained a little and pages are going back to the buddy lists. This is trickier to draw conclusions from but high activity on those events could explain why there were a large number of cache misses on a page-allocator-intensive workload. The coalescing and splitting of buddies involves a lot of writing of page metadata and cache line bounces not to mention the acquisition of an interrupt-safe lock necessary to enter this path. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Li Ming Chun <macli@brc.ubc.ca> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:02:44 +00:00
TP_PROTO(struct page *page, unsigned int order, int migratetype),
tracing, page-allocator: add trace event for page traffic related to the buddy lists The page allocation trace event reports that a page was successfully allocated but it does not specify where it came from. When analysing performance, it can be important to distinguish between pages coming from the per-cpu allocator and pages coming from the buddy lists as the latter requires the zone lock to the taken and more data structures to be examined. This patch adds a trace event for __rmqueue reporting when a page is being allocated from the buddy lists. It distinguishes between being called to refill the per-cpu lists or whether it is a high-order allocation. Similarly, this patch adds an event to catch when the PCP lists are being drained a little and pages are going back to the buddy lists. This is trickier to draw conclusions from but high activity on those events could explain why there were a large number of cache misses on a page-allocator-intensive workload. The coalescing and splitting of buddies involves a lot of writing of page metadata and cache line bounces not to mention the acquisition of an interrupt-safe lock necessary to enter this path. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Li Ming Chun <macli@brc.ubc.ca> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:02:44 +00:00
TP_ARGS(page, order, migratetype)
);
tracing, page-allocator: add trace event for page traffic related to the buddy lists The page allocation trace event reports that a page was successfully allocated but it does not specify where it came from. When analysing performance, it can be important to distinguish between pages coming from the per-cpu allocator and pages coming from the buddy lists as the latter requires the zone lock to the taken and more data structures to be examined. This patch adds a trace event for __rmqueue reporting when a page is being allocated from the buddy lists. It distinguishes between being called to refill the per-cpu lists or whether it is a high-order allocation. Similarly, this patch adds an event to catch when the PCP lists are being drained a little and pages are going back to the buddy lists. This is trickier to draw conclusions from but high activity on those events could explain why there were a large number of cache misses on a page-allocator-intensive workload. The coalescing and splitting of buddies involves a lot of writing of page metadata and cache line bounces not to mention the acquisition of an interrupt-safe lock necessary to enter this path. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Li Ming Chun <macli@brc.ubc.ca> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:02:44 +00:00
DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
tracing, page-allocator: add trace event for page traffic related to the buddy lists The page allocation trace event reports that a page was successfully allocated but it does not specify where it came from. When analysing performance, it can be important to distinguish between pages coming from the per-cpu allocator and pages coming from the buddy lists as the latter requires the zone lock to the taken and more data structures to be examined. This patch adds a trace event for __rmqueue reporting when a page is being allocated from the buddy lists. It distinguishes between being called to refill the per-cpu lists or whether it is a high-order allocation. Similarly, this patch adds an event to catch when the PCP lists are being drained a little and pages are going back to the buddy lists. This is trickier to draw conclusions from but high activity on those events could explain why there were a large number of cache misses on a page-allocator-intensive workload. The coalescing and splitting of buddies involves a lot of writing of page metadata and cache line bounces not to mention the acquisition of an interrupt-safe lock necessary to enter this path. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Li Ming Chun <macli@brc.ubc.ca> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:02:44 +00:00
TP_PROTO(struct page *page, unsigned int order, int migratetype),
TP_ARGS(page, order, migratetype),
tracing, page-allocator: add trace event for page traffic related to the buddy lists The page allocation trace event reports that a page was successfully allocated but it does not specify where it came from. When analysing performance, it can be important to distinguish between pages coming from the per-cpu allocator and pages coming from the buddy lists as the latter requires the zone lock to the taken and more data structures to be examined. This patch adds a trace event for __rmqueue reporting when a page is being allocated from the buddy lists. It distinguishes between being called to refill the per-cpu lists or whether it is a high-order allocation. Similarly, this patch adds an event to catch when the PCP lists are being drained a little and pages are going back to the buddy lists. This is trickier to draw conclusions from but high activity on those events could explain why there were a large number of cache misses on a page-allocator-intensive workload. The coalescing and splitting of buddies involves a lot of writing of page metadata and cache line bounces not to mention the acquisition of an interrupt-safe lock necessary to enter this path. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Li Ming Chun <macli@brc.ubc.ca> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:02:44 +00:00
TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
__entry->page, page_to_pfn(__entry->page),
__entry->order, __entry->migratetype)
tracing, page-allocator: add trace event for page traffic related to the buddy lists The page allocation trace event reports that a page was successfully allocated but it does not specify where it came from. When analysing performance, it can be important to distinguish between pages coming from the per-cpu allocator and pages coming from the buddy lists as the latter requires the zone lock to the taken and more data structures to be examined. This patch adds a trace event for __rmqueue reporting when a page is being allocated from the buddy lists. It distinguishes between being called to refill the per-cpu lists or whether it is a high-order allocation. Similarly, this patch adds an event to catch when the PCP lists are being drained a little and pages are going back to the buddy lists. This is trickier to draw conclusions from but high activity on those events could explain why there were a large number of cache misses on a page-allocator-intensive workload. The coalescing and splitting of buddies involves a lot of writing of page metadata and cache line bounces not to mention the acquisition of an interrupt-safe lock necessary to enter this path. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Li Ming Chun <macli@brc.ubc.ca> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:02:44 +00:00
);
TRACE_EVENT(mm_page_alloc_extfrag,
TP_PROTO(struct page *page,
int alloc_order, int fallback_order,
int alloc_migratetype, int fallback_migratetype),
TP_ARGS(page,
alloc_order, fallback_order,
alloc_migratetype, fallback_migratetype),
TP_STRUCT__entry(
__field( struct page *, page )
__field( int, alloc_order )
__field( int, fallback_order )
__field( int, alloc_migratetype )
__field( int, fallback_migratetype )
),
TP_fast_assign(
__entry->page = page;
__entry->alloc_order = alloc_order;
__entry->fallback_order = fallback_order;
__entry->alloc_migratetype = alloc_migratetype;
__entry->fallback_migratetype = fallback_migratetype;
),
TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
__entry->page,
page_to_pfn(__entry->page),
__entry->alloc_order,
__entry->fallback_order,
pageblock_order,
__entry->alloc_migratetype,
__entry->fallback_migratetype,
__entry->fallback_order < pageblock_order,
__entry->alloc_migratetype == __entry->fallback_migratetype)
);
tracing: create automated trace defines This patch lowers the number of places a developer must modify to add new tracepoints. The current method to add a new tracepoint into an existing system is to write the trace point macro in the trace header with one of the macros TRACE_EVENT, TRACE_FORMAT or DECLARE_TRACE, then they must add the same named item into the C file with the macro DEFINE_TRACE(name) and then add the trace point. This change cuts out the needing to add the DEFINE_TRACE(name). Every file that uses the tracepoint must still include the trace/<type>.h file, but the one C file must also add a define before the including of that file. #define CREATE_TRACE_POINTS #include <trace/mytrace.h> This will cause the trace/mytrace.h file to also produce the C code necessary to implement the trace point. Note, if more than one trace/<type>.h is used to create the C code it is best to list them all together. #define CREATE_TRACE_POINTS #include <trace/foo.h> #include <trace/bar.h> #include <trace/fido.h> Thanks to Mathieu Desnoyers and Christoph Hellwig for coming up with the cleaner solution of the define above the includes over my first design to have the C code include a "special" header. This patch converts sched, irq and lockdep and skb to use this new method. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Zhao Lei <zhaolei@cn.fujitsu.com> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-04-10 13:36:00 +00:00
#endif /* _TRACE_KMEM_H */
tracing: create automated trace defines This patch lowers the number of places a developer must modify to add new tracepoints. The current method to add a new tracepoint into an existing system is to write the trace point macro in the trace header with one of the macros TRACE_EVENT, TRACE_FORMAT or DECLARE_TRACE, then they must add the same named item into the C file with the macro DEFINE_TRACE(name) and then add the trace point. This change cuts out the needing to add the DEFINE_TRACE(name). Every file that uses the tracepoint must still include the trace/<type>.h file, but the one C file must also add a define before the including of that file. #define CREATE_TRACE_POINTS #include <trace/mytrace.h> This will cause the trace/mytrace.h file to also produce the C code necessary to implement the trace point. Note, if more than one trace/<type>.h is used to create the C code it is best to list them all together. #define CREATE_TRACE_POINTS #include <trace/foo.h> #include <trace/bar.h> #include <trace/fido.h> Thanks to Mathieu Desnoyers and Christoph Hellwig for coming up with the cleaner solution of the define above the includes over my first design to have the C code include a "special" header. This patch converts sched, irq and lockdep and skb to use this new method. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Zhao Lei <zhaolei@cn.fujitsu.com> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-04-10 13:36:00 +00:00
/* This part must be outside protection */
#include <trace/define_trace.h>