On Sun, Mar 10, 2019 at 07:17:08PM +0300, Alexey Budankov wrote:
SNIP
> > so to be on the same page.. normal processing without compression is:
> >
> > perf_mmap__push does:
> > push(mmap buf)
> > record__pushfn
> > record__write
> > write(buf)
> >
> >
On 08.03.2019 13:46, Jiri Olsa wrote:
> On Thu, Mar 07, 2019 at 06:26:47PM +0300, Alexey Budankov wrote:
>>
>> On 07.03.2019 15:14, Jiri Olsa wrote:
>>> On Thu, Mar 07, 2019 at 11:39:46AM +0300, Alexey Budankov wrote:
On 05.03.2019 15:25, Jiri Olsa wrote:
> On Fri, Mar 01, 2019 at
On 08.03.2019 13:46, Jiri Olsa wrote:
> On Thu, Mar 07, 2019 at 06:26:47PM +0300, Alexey Budankov wrote:
>>
>> On 07.03.2019 15:14, Jiri Olsa wrote:
>>> On Thu, Mar 07, 2019 at 11:39:46AM +0300, Alexey Budankov wrote:
On 05.03.2019 15:25, Jiri Olsa wrote:
> On Fri, Mar 01, 2019 at
On Thu, Mar 07, 2019 at 06:26:47PM +0300, Alexey Budankov wrote:
>
> On 07.03.2019 15:14, Jiri Olsa wrote:
> > On Thu, Mar 07, 2019 at 11:39:46AM +0300, Alexey Budankov wrote:
> >>
> >> On 05.03.2019 15:25, Jiri Olsa wrote:
> >>> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>
On 07.03.2019 18:26, Alexey Budankov wrote:
>
> On 07.03.2019 15:14, Jiri Olsa wrote:
>> On Thu, Mar 07, 2019 at 11:39:46AM +0300, Alexey Budankov wrote:
>>>
>>> On 05.03.2019 15:25, Jiri Olsa wrote:
On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
SNIP
>
On 07.03.2019 15:14, Jiri Olsa wrote:
> On Thu, Mar 07, 2019 at 11:39:46AM +0300, Alexey Budankov wrote:
>>
>> On 05.03.2019 15:25, Jiri Olsa wrote:
>>> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>>>
>>> SNIP
>>>
/*
* Increment md->refcount to guard
On 07.03.2019 14:59, Jiri Olsa wrote:
> On Thu, Mar 07, 2019 at 11:26:16AM +0300, Alexey Budankov wrote:
>>
>> On 05.03.2019 15:26, Jiri Olsa wrote:
>>> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>>>
>>> SNIP
>>>
+static size_t record__process_comp_header(void *record,
On Thu, Mar 07, 2019 at 11:39:46AM +0300, Alexey Budankov wrote:
>
> On 05.03.2019 15:25, Jiri Olsa wrote:
> > On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
> >
> > SNIP
> >
> >>
> >>/*
> >> * Increment md->refcount to guard md->data[idx] buffer
> >> @@ -350,7
On Thu, Mar 07, 2019 at 11:26:16AM +0300, Alexey Budankov wrote:
>
> On 05.03.2019 15:26, Jiri Olsa wrote:
> > On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
> >
> > SNIP
> >
> >> +static size_t record__process_comp_header(void *record, size_t increment)
> >> +{
> >> + struct
On 05.03.2019 15:25, Jiri Olsa wrote:
> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>
> SNIP
>
>>
>> /*
>> * Increment md->refcount to guard md->data[idx] buffer
>> @@ -350,7 +357,7 @@ int perf_mmap__aio_push(struct perf_mmap *md, void *to,
>> int idx,
>>
On 05.03.2019 15:26, Jiri Olsa wrote:
> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>
> SNIP
>
>> +static int record__aio_enabled(struct record *rec);
>> +
>> static void record__aio_mmap_read_sync(struct record *rec)
>> {
>> int i;
>> struct perf_evlist
On 05.03.2019 15:26, Jiri Olsa wrote:
> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>
> SNIP
>
>> +static size_t record__process_comp_header(void *record, size_t increment)
>> +{
>> +struct compressed_event *event = record;
>> +size_t size = sizeof(struct
On 05.03.2019 15:26, Jiri Olsa wrote:
> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>
> SNIP
>
>>
>> +static size_t record__process_comp_header(void *record, size_t increment)
>> +{
>> +struct compressed_event *event = record;
>> +size_t size = sizeof(struct
On 05.03.2019 15:25, Jiri Olsa wrote:
> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>
> SNIP
>
>> +static size_t record__zstd_compress(void *data, void *dst, size_t dst_size,
>> +void *src, size_t src_size)
>> +{
>> +size_t compressed;
>> +struct
On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
SNIP
> +static size_t record__process_comp_header(void *record, size_t increment)
> +{
> + struct compressed_event *event = record;
> + size_t size = sizeof(struct compressed_event);
> +
> + if (increment) {
> +
On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
SNIP
> +static int record__aio_enabled(struct record *rec);
> +
> static void record__aio_mmap_read_sync(struct record *rec)
> {
> int i;
> struct perf_evlist *evlist = rec->evlist;
> struct perf_mmap *maps =
On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
SNIP
>
> +static size_t record__process_comp_header(void *record, size_t increment)
> +{
> + struct compressed_event *event = record;
> + size_t size = sizeof(struct compressed_event);
> +
> + if (increment) {
> +
On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
SNIP
> +static size_t record__zstd_compress(void *data, void *dst, size_t dst_size,
> + void *src, size_t src_size)
> +{
> + size_t compressed;
> + struct perf_session *session = data;
> + /* maximum size of
On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
SNIP
>
> /*
>* Increment md->refcount to guard md->data[idx] buffer
> @@ -350,7 +357,7 @@ int perf_mmap__aio_push(struct perf_mmap *md, void *to,
> int idx,
> md->prev = head;
> perf_mmap__consume(md);
On 05.03.2019 3:01, Andi Kleen wrote:
> On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
>
> Could do this as a follow up patch, but at some point the new
> records need to be documented in Documentation/perf.data-file-format.txt
Well, let's have it as a part of v6 04/10.
On Fri, Mar 01, 2019 at 06:58:32PM +0300, Alexey Budankov wrote:
Could do this as a follow up patch, but at some point the new
records need to be documented in Documentation/perf.data-file-format.txt
-Andi
Implemented -z,--compression_level=n option that enables compression
of mmaped kernel data buffers content in runtime during perf record
sampling collection.
Compression is implemented using the functions from zstd.c. As the
memory to operate on the compression employs mmap->data buffer in case
22 matches
Mail list logo
