mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-11 23:03:55 +08:00
perf/ring_buffer: Use high order allocations for AUX buffers optimistically
Currently, the AUX buffer allocator will use high-order allocations for PMUs that don't support hardware scatter-gather chaining to ensure large contiguous blocks of pages, and always use an array of single pages otherwise. There is, however, a tangible performance benefit in using larger chunks of contiguous memory even in the latter case, that comes from not having to fetch the next page's address at every page boundary. In particular, a task running under Intel PT on an Atom CPU shows 1.5%-2% less runtime penalty with a single multi-page output region in snapshot mode (no PMI) than with multiple single-page output regions, from ~6% down to ~4%. For the snapshot mode it does make a difference as it is intended to run over long periods of time. For this reason, change the allocation policy to always optimistically start with the highest possible order when allocating pages for the AUX buffer, desceding until the allocation succeeds or order zero allocation fails. Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Link: https://lkml.kernel.org/r/20190215114727.62648-2-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
6ea98b4baa
commit
5768402fd9
@ -598,29 +598,27 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
|
||||
{
|
||||
bool overwrite = !(flags & RING_BUFFER_WRITABLE);
|
||||
int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
|
||||
int ret = -ENOMEM, max_order = 0;
|
||||
int ret = -ENOMEM, max_order;
|
||||
|
||||
if (!has_aux(event))
|
||||
return -EOPNOTSUPP;
|
||||
|
||||
if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) {
|
||||
/*
|
||||
* We need to start with the max_order that fits in nr_pages,
|
||||
* not the other way around, hence ilog2() and not get_order.
|
||||
*/
|
||||
max_order = ilog2(nr_pages);
|
||||
/*
|
||||
* We need to start with the max_order that fits in nr_pages,
|
||||
* not the other way around, hence ilog2() and not get_order.
|
||||
*/
|
||||
max_order = ilog2(nr_pages);
|
||||
|
||||
/*
|
||||
* PMU requests more than one contiguous chunks of memory
|
||||
* for SW double buffering
|
||||
*/
|
||||
if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
|
||||
!overwrite) {
|
||||
if (!max_order)
|
||||
return -EINVAL;
|
||||
/*
|
||||
* PMU requests more than one contiguous chunks of memory
|
||||
* for SW double buffering
|
||||
*/
|
||||
if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
|
||||
!overwrite) {
|
||||
if (!max_order)
|
||||
return -EINVAL;
|
||||
|
||||
max_order--;
|
||||
}
|
||||
max_order--;
|
||||
}
|
||||
|
||||
rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,
|
||||
|
Loading…
Reference in New Issue
Block a user