Re: [PATCH v2]: perf/core: addressing 4x slowdown during per-process, profiling of STREAM benchmark on Intel Xeon Phi

[Alexey Budankov <alexey.budankov@linux.intel.com>]

On 29.05.2017 10:46, Peter Zijlstra wrote:
> On Sat, May 27, 2017 at 02:19:51PM +0300, Alexey Budankov wrote:
>> @@ -571,6 +587,27 @@ struct perf_event {
>>   	 * either sufficies for read.
>>   	 */
>>   	struct list_head		group_entry;
>> +	/*
>> +	 * Node on the pinned or flexible tree located at the event context;
>> +	 * the node may be empty in case its event is not directly attached
>> +	 * to the tree but to group_list list of the event directly
>> +	 * attached to the tree;
>> +	 */
>> +	struct rb_node			group_node;
>> +	/*
>> +	 * List keeps groups allocated for the same cpu;
>> +	 * the list may be empty in case its event is not directly
>> +	 * attached to the tree but to group_list list of the event directly
>> +	 * attached to the tree;
>> +	 */
>> +	struct list_head		group_list;
>> +	/*
>> +	 * Entry into the group_list list above;
>> +	 * the entry may be attached to the self group_list list above
>> +	 * in case the event is directly attached to the pinned or
>> +	 * flexible tree;
>> +	 */
>> +	struct list_head		group_list_entry;
>>   	struct list_head		sibling_list;
>>
>>   	/*
> 
>> @@ -742,7 +772,17 @@ struct perf_event_context {
>>
>>   	struct list_head		active_ctx_list;
>>   	struct list_head		pinned_groups;
>> +	/*
>> +	 * Cpu tree for pinned groups; keeps event's group_node nodes
>> +	 * of attached flexible groups;
>> +	 */
>> +	struct rb_root			pinned_tree;
>>   	struct list_head		flexible_groups;
>> +	/*
>> +	 * Cpu tree for flexible groups; keeps event's group_node nodes
>> +	 * of attached flexible groups;
>> +	 */
>> +	struct rb_root			flexible_tree;
>>   	struct list_head		event_list;
>>   	int				nr_events;
>>   	int				nr_active;
>> @@ -758,6 +798,7 @@ struct perf_event_context {
>>   	 */
>>   	u64				time;
>>   	u64				timestamp;
>> +	struct perf_event_tstamp	tstamp_data;
>>
>>   	/*
>>   	 * These fields let us detect when two contexts have both
> 
> 
> So why do we now have a list _and_ a tree for the same entries?
We need groups list to iterate through all groups configured for 
collection and we need the tree to quickly iterate through the groups 
allocated for a particular CPU only.
> 
> 

-Alexey