llc_misses.mem_read
On no-die system, die_id is 0, actually it's hashmap(socket,0), original
behavior
is not changed.
Reported-by: Huang Ying
Signed-off-by: Jin Yao
---
v9:
Rename zero_per_pkg to evsel__zero_per_pkg and move it to evsel.c. Then
evsel__zero_per_pkg can be called under
currently it uses 'int' for i in struct int_node, maybe something I don't
understand correctly. Please correct me if my understanding is wrong.
Thanks
Jin Yao
2230848 Bytes llc_misses.mem_read
On no-die system, die_id is 0, this patch keeps original behavior unchanged.
Reported-by: Huang Ying
Signed-off-by: Jin Yao
---
tools/perf/util/cpumap.h | 2 ++
tools/perf/util/stat.c | 21 +
2 files changed, 19 insertions(+), 4 deletions
On 2014/4/22 21:18, Linus Walleij wrote:
> On Mon, Apr 14, 2014 at 4:48 AM, Jin, Yao wrote:
>
>> A crash is triggered on the ASUS T100TA Baytrail-T because of a IRQ
>> descriptor conflict. There are two gpio triggered acpi events in this
>> device, GPIO 6 and 18. These
On 2014/4/23 20:23, Mika Westerberg wrote:
> On Wed, Apr 23, 2014 at 11:34:30AM +0300, Mika Westerberg wrote:
>> On Tue, Apr 22, 2014 at 10:16:50PM -0700, Adam Williamson wrote:
>>> Well, I can't actually concur. See my results in
>>> https://bugzilla.kernel.org/show_bug.cgi?id=68291#c44 .
>>>
>>
On 2014/4/25 5:33, Adam Williamson wrote:
> On Thu, 2014-04-24 at 21:30 +0800, Jin, Yao wrote:
>
>>> Jin, do you have any idea what is going on?
>>>
>>
>> Maybe neither the patch (http://dougvj.net/baytrail_gpio_quirk_v3.patch)
>> nor my patch break
On 2014/4/25 17:40, Mika Westerberg wrote:
> [+Aubrey]
>
> On Fri, Apr 25, 2014 at 03:27:42PM +0800, Jin, Yao wrote:
>>
>>
>> On 2014/4/25 5:33, Adam Williamson wrote:
>>> On Thu, 2014-04-24 at 21:30 +0800, Jin, Yao wrote:
>>>
>
On 2014/4/25 23:13, Adam Williamson wrote:
> On Fri, 2014-04-25 at 11:32 +0200, Linus Walleij wrote:
>> On Thu, Apr 24, 2014 at 11:33 PM, Adam Williamson
>> wrote:
>>
>>> Well, I just ran another test too. I built a kernel (3.15rc2) with both
>>> v3 of Doug's SDIO device enumeration patch -
>>>
On 2014/4/26 11:04, Jin, Yao wrote:
>
>
> On 2014/4/25 23:13, Adam Williamson wrote:
>> On Fri, 2014-04-25 at 11:32 +0200, Linus Walleij wrote:
>>> On Thu, Apr 24, 2014 at 11:33 PM, Adam Williamson
>>> wrote:
>>>
>>>> Well, I just ran
the IRQ conflict. It still uses the irq domain to allocate irq descriptor
but start from a predefined irq base number (256).
Signed-off-by: Jin Yao
---
drivers/pinctrl/pinctrl-baytrail.c | 37
+
1 file changed, 29 insertions(+), 8 deletions(-)
diff --gi
ict. It still uses the irq domain to allocate irq descriptor but start
from a predefined irq base number (256) to avoid the conflict.
Signed-off-by: Jin Yao
---
drivers/pinctrl/pinctrl-baytrail.c | 37 +
1 file changed, 29 insertions(+), 8 deletions(-)
diff --
On 2014/4/19 4:44, Benjamin Tissoires wrote:
> On Wed, Apr 16, 2014 at 8:05 AM, Jin Yao wrote:
>> A crash is triggered on the ASUS T100TA Baytrail-T because of a irq
>> descriptor conflict. There are two gpio triggered acpi events in this
>> device, GPIO 6 and 18. These gp
On 2014/4/20 18:31, Jin, Yao wrote:
>
>
> On 2014/4/19 4:44, Benjamin Tissoires wrote:
>> On Wed, Apr 16, 2014 at 8:05 AM, Jin Yao wrote:
>>> A crash is triggered on the ASUS T100TA Baytrail-T because of a irq
>>> descriptor conflict. There are two gpio trigger
On 2014/4/20 23:28, Adam Williamson wrote:
> On Sun, 2014-04-20 at 20:08 +0800, Jin, Yao wrote:
>> For the issue that touch screen doesn't work, could you check power
>> state of LPSS devices? For example:
>>
>> cd /sys/bus/acpi/devices
>> grep -H . */po
On 2014/4/21 14:27, Jin, Yao wrote:
>
>
> On 2014/4/20 23:28, Adam Williamson wrote:
>> On Sun, 2014-04-20 at 20:08 +0800, Jin, Yao wrote:
>>> For the issue that touch screen doesn't work, could you check power
>>> state of LPSS devices? For example:
>
Thanks Mika, I will fix this warning.
On 2014/4/22 19:51, Mika Westerberg wrote:
> On Wed, Apr 16, 2014 at 08:05:59PM +0800, Jin Yao wrote:
>> A crash is triggered on the ASUS T100TA Baytrail-T because of a irq
>> descriptor conflict. There are two gpio triggered acpi events in
ail directly. Is it really correct? Could you help to look
at this?
BTW, I tested with Arnaldo's perf/core branch.
Thanks
Jin Yao
On 1/10/2019 10:27 PM, Mark Rutland wrote:
The perf tool uses /proc/sys/kernel/perf_event_mlock_kb to determine how
large its ringbuffer mmap should be. Thi
On 3/15/2019 9:34 PM, Jiri Olsa wrote:
On Sat, Mar 16, 2019 at 12:04:13AM +0800, Jin Yao wrote:
The coresum event qualifier which sums up the event counts for both
hardware threads in a core. For example,
perf stat -e cpu/event=0,umask=0x3,coresum=1/,cpu/event=0,umask=0x3/
In this example
On 3/15/2019 9:34 PM, Jiri Olsa wrote:
On Sat, Mar 16, 2019 at 12:04:15AM +0800, Jin Yao wrote:
SNIP
+static void print_counter_aggrdata(struct perf_stat_config *config,
+ struct perf_evsel *counter, int s,
+ char *prefix
be escaped in metric expressions.
-Andi
Oh, yes, thanks for reminding. Will use 'percore' in next version.
Thanks
Jin Yao
o 'percore'.
2. Move the aggregate counts printing to a seperate patch.
Jin Yao (4):
perf: Add a 'percore' event qualifier
perf stat: Factor out aggregate counts printing
perf stat: Support 'percore' event qualifier
perf test: Add a simple test for term '
It's a simple test which just checks if parser works.
v2:
---
Change 'coresum' to 'percore'
Signed-off-by: Jin Yao
---
tools/perf/tests/parse-events.c | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/tools/perf/tests/parse-events.c
.
So we need to support this per-core counting on a event level.
This can be implemented in only the user tool, no kernel support needed.
v2:
---
Change the qualifier name from 'coresum' to 'percore' according to
comments from Jiri and Andi.
Signed-off-by: Jin Yao
---
Move the aggregate counts printing to a new function
print_counter_aggrdata, which will be used in following
patches.
v2:
---
Create this patch according to Jiri's comments.
Signed-off-by: Jin Yao
---
tools/perf/util/stat-display.c | 65 +-
1
From the output, we can see:
S0-C0 = CPU0 + CPU4
S0-C1 = CPU1 + CPU5
S0-C2 = CPU2 + CPU6
S0-C3 = CPU3 + CPU7
So the result is expected (tiny difference is ignored).
Note that, the 'percore' event qualifier needs to use with option '-A'.
v2:
---
Change 'c
Change 'coresum' to 'percore'.
Signed-off-by: Jin Yao
---
tools/perf/Documentation/perf-stat.txt | 4
tools/perf/builtin-stat.c | 21 +
tools/perf/util/stat-display.c | 43 ++
tools/perf/util/stat.c
It's a simple test which just checks if parser works.
v3:
---
No change
v2:
---
Change 'coresum' to 'percore'
Signed-off-by: Jin Yao
---
tools/perf/tests/parse-events.c | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/tools/perf/tes
Move the aggregate counts printing to a new function
print_counter_aggrdata, which will be used in following
patches.
v3:
---
No change
v2:
---
Create this patch according to Jiri's comments.
Signed-off-by: Jin Yao
---
tools/perf/util/stat-display.c
->val.percore;"
v2:
---
Change the qualifier name from 'coresum' to 'percore' according to
comments from Jiri and Andi.
Signed-off-by: Jin Yao
---
tools/perf/util/evsel.c| 2 ++
tools/perf/util/evsel.h| 3 +++
tools/perf/util/parse-events.c | 2
dd a 'percore' event qualifier"
Other patches don't have changes.
v2:
---
1. Change 'coresum' to 'percore'.
2. Move the aggregate counts printing to a seperate patch.
Jin Yao (4):
perf: Add a 'percore' event qualifier
perf stat: Factor out
On 3/18/2019 5:21 PM, Jiri Olsa wrote:
On Sun, Mar 17, 2019 at 12:34:25AM +0800, Jin Yao wrote:
SNIP
static bool config_term_shrinked;
@@ -950,6 +951,7 @@ config_term_avail(int term_type, struct parse_events_error
*err)
case PARSE_EVENTS__TERM_TYPE_CONFIG2:
case
Nobody like this patch? :)
In my test, for a 72MB perf.data (with LBR data), the perf annotate
processing speed:
Before: 10.2s
After: 2.2s
Thanks
Jin Yao
On 3/16/2019 5:16 AM, Jin Yao wrote:
The hist__account_cycles is executed when the hist_iter__branch_callback
is called. But it looks
On 8/31/2019 2:22 AM, Arnaldo Carvalho de Melo wrote:
Em Wed, Aug 28, 2019 at 01:59:30PM +0800, Jin Yao escreveu:
From: Haiyan Song
Not applying, please check, will apply the other 3 patches in the
series, next time please try to collect some Acked-by in advance.
- Arnaldo
Hi
tion ‘compute_cycles_diff’:
builtin-diff.c:712:10: error: taking the absolute value of unsigned type
‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value]
712 | labs(pair->block_info->cycles_spark[i] -
| ^~~~
Because the result of u64 - u64
On 8/15/2019 9:22 PM, Jiri Olsa wrote:
On Tue, Aug 13, 2019 at 03:30:37PM +0800, Jin Yao wrote:
SNIP
static void
hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
{
@@ -1662,6 +1794,10 @@ static void data__hpp_register(struct data__file *d, int
idx
On 8/15/2019 9:23 PM, Jiri Olsa wrote:
On Tue, Aug 13, 2019 at 03:30:37PM +0800, Jin Yao wrote:
This patch prints the stddev and hist for the cycles diff of
program block. It can help us to understand if the cycles
is noisy or not.
This patch is inspired by Andi Kleen's patch
struct stats
v2:
---
Jiri got a compile error,
CC builtin-diff.o
builtin-diff.c: In function ‘compute_cycles_diff’:
builtin-diff.c:712:10: error: taking the absolute value of unsigned type
‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value]
712 |
ale and changes the function to global.
No functional change.
Signed-off-by: Jin Yao
---
tools/perf/util/pmu.c | 6 +++---
tools/perf/util/pmu.h | 2 ++
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9807be6f09bb..8e35e97ecf90
;,
"ScaleUnit": "60ns",
"UMask": "0x1",
"Unit": "iMC"
},
For above example, the ratio should be,
ratio = (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS /
UNC_M_CLOCKTICKS) * 60
But in current cod
From: Haiyan Song
Signed-off-by: Haiyan Song
---
.../arch/x86/cascadelakex/uncore-memory.json | 191 ++
.../arch/x86/cascadelakex/uncore-other.json | 1809 -
2 files changed, 1971 insertions(+), 29 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore
UNC_M_PMM_READ_LATENCY'.
Haiyan Song (1):
perf vendor events intel: Update cascadelakex uncore events to v1.04
Jin Yao (3):
perf util: Change convert_scale from static to global
perf util: Scale the metric result
perf util: Support multiple events for metricgroup
.../arch/x86/c
6356 unc_m_clockticks
1.001749103 seconds time elapsed
Now we can see the correct metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' and
'UNC_M_PMM_READ_LATENCY'.
Signed-off-by: Jin Yao
---
tools/perf/util/evsel.h | 1 +
tools/perf/util/metricgroup.c | 84 +
Hi Jiri, Hi Arnaldo,
Can this patch be accepted?
Thanks
Jin Yao
On 9/25/2019 9:14 AM, Jin Yao wrote:
This patch prints the stddev and hist for the cycles diff of
program block. It can help us to understand if the cycles
is noisy or not.
This patch is inspired by Andi Kleen's patch
1
[perf_event_nmi_handler+57 -> perf_event_nmi_handler+63] [kernel.kallsyms]
0.00% 10.02% 1
[perf_event_nmi_handler+68 -> perf_event_nmi_handler+74] [kernel.kallsyms]
Signed-off-by: Jin Yao
---
tools/perf/Documentation/perf-re
We have already implemented some block related functions. Now it's
time to do some cleanup, and move the functions and structures to
the new block.h/block.c.
Signed-off-by: Jin Yao
---
tools/perf/builtin-diff.c | 38 ++-
tools/perf/util/Build | 1 +
tools/perf
[random_r.c:388 -> random_r.c:388] libc-2.27.so
1.57% 123.3K0.02% 1
[div.c:42 -> div.c:44] div
1.44% 116.0K0.42% 19
[r
116.0K0.42% 19
[random_r.c:357 -> random_r.c:394] libc-2.27.so
It only shows the entries which 'Sampled Cycles%' > 1%.
Signed-off-by: Jin Yao
---
tools/perf/builtin-report.c | 2 +-
tools/perf/ui/stdio/hist.c | 7 ++-
0.02% 1
[div.c:42 -> div.c:44] div
1.44% 116.0K0.42% 19
[random_r.c:357 -> random_r.c:394] libc-2.27.so
..
This patch series support
a new argument 'total_cycles' in hist__account_cycles(),
which will be added with the cycles of each sample.
Signed-off-by: Jin Yao
---
tools/perf/builtin-annotate.c | 2 +-
tools/perf/builtin-diff.c | 3 ++-
tools/perf/builtin-report.c | 2 +-
tools/perf/builtin-top.c | 3 ++-
atch which just follows the perf-record behavior.
Thanks
Jin Yao
On 10/10/2019 4:00 PM, Jiri Olsa wrote:
On Thu, Oct 10, 2019 at 02:46:36PM +0800, Jin, Yao wrote:
On 10/1/2019 10:17 AM, Andi Kleen wrote:
I think it's useful. Makes it easy to do kernel/user break downs.
perf record should support the same.
Don't we have this already with:
[
Hi,
Can this patch be accepted?
Thanks
Jin Yao
On 9/3/2019 10:03 AM, Jin Yao wrote:
This patch prints the stddev and hist for the cycles diff of
program block. It can help us to understand if the cycles
is noisy or not.
This patch is inspired by Andi Kleen's patch
https://lwn.net/Art
-diff.o
builtin-diff.c: In function ‘compute_cycles_diff’:
builtin-diff.c:712:10: error: taking the absolute value of unsigned type
‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value]
712 | labs(pair->block_info->cycles_spark[i] -
|
2. In perf-record, it has already supported the --all-kernel and
--all-user, but they can't be combined. We should keep the behavior
consistent among all perf subtools. So if this patch can be accepted,
will post follow-up patches for supporting other subtools for the
same beha
1.5% 83.9%
1.000773028 seconds time elapsed
Signed-off-by: Jin Yao
---
tools/perf/builtin-stat.c | 37 +++-
tools/perf/util/stat-shadow.c | 167 +-
tools/perf/util/stat.h| 12 +++
3 files changed, 171 insertions(+), 45 delet
771709 seconds time elapsed
More detail information are in the patch descriptions.
Jin Yao (2):
perf stat: Support --all-kernel and --all-user options
perf stat: Support topdown with --all-kernel/--all-user
tools/perf/Documentation/perf-record.txt | 3 +-
tools/perf/Documentation/perf-stat.
On 8/20/2019 4:34 PM, Jiri Olsa wrote:
On Fri, Aug 16, 2019 at 10:13:43AM +0800, Jin Yao wrote:
SNIP
static void
hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
{
@@ -1662,6 +1794,10 @@ static void data__hpp_register(struct data__file *d, int
idx
of unsigned type
‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value]
712 | labs(pair->block_info->cycles_spark[i] -
| ^~~~
Because the result of u64 - u64 is still u64. Now we change the type of
cycles_spark[] to s64.
Signed-off-by: Jin Yao
-
On 7/16/2019 4:51 PM, Jiri Olsa wrote:
On Fri, Jul 12, 2019 at 03:53:55PM +0800, Jin Yao wrote:
This patch prints the stddev and hist for the cycles diff of
program block. It can help us to understand if the cycles diff
is noisy or not.
I'm getting compile error:
CC bu
# 0.5 IPC
6,227,603 cpu_clk_unhalted.thread
2.003403078 seconds time elapsed
v2:
---
Rebase to perf/core branch
Jin Yao (2):
perf evsel: Create counts for collecting summary data
perf stat: Report summary for interval mode
tools/perf/builtin-stat.c | 14
7;:
2,856,395 inst_retired.any # 2.2 CPI
6,214,690 cycles
2,865,539 inst_retired.any # 0.5 IPC
6,227,603 cpu_clk_unhalted.thread
2.003403078 seconds time elapsed
v2:
---
Rebase to perf/core b
sn't bring much complexity.
The idea is to create new 'evsel->summary_counts' which sums up the
counts delta per interval. Before reporting the summary, we copy the
data from evsel->summary_counts to evsel->counts, and next we just
follow current code.
v2:
---
Rebase to pe
On 5/1/2020 7:36 PM, Jiri Olsa wrote:
On Thu, Apr 30, 2020 at 11:07:38AM +0800, Jin Yao wrote:
Currently perf-stat supports to print counts at regular interval (-I),
but it's not very easy for user to get the overall statistics.
With this patchset, it supports to report the summary a
Hi Jiri,
On 5/1/2020 6:23 PM, Jiri Olsa wrote:
On Thu, Apr 30, 2020 at 09:34:51AM +0800, Jin Yao wrote:
A metric may consist of system wide event and non system-wide event.
The event group leader may be the system wide event.
For example, the metric "C2_Pkg_Residency" consists of
&
formance counter stats for 'system wide':
1000850802 cstate_pkg/c2-residency/ # 0.5 C2_Pkg_Residency
201446161592 msr/tsc/
1.010637051 seconds time elapsed
Fixes: 6a4bb04caacc ("perf tools: Enable grouping logic for parsed events")
Signed-off-by: Jin Ya
7;:
2,856,395 inst_retired.any # 2.2 CPI
6,214,690 cycles
2,865,539 inst_retired.any # 0.5 IPC
6,227,603 cpu_clk_unhalted.thread
2.003403078 seconds time elapsed
Signed-off-by: Jin Yao
---
tools/p
# 0.5 IPC
6,227,603 cpu_clk_unhalted.thread
2.003403078 seconds time elapsed
Jin Yao (2):
perf evsel: Create counts for collecting summary data
perf stat: Report summary for interval mode
tools/perf/builtin-stat.c | 14 ++-
tools/perf/util/evsel.c | 10 ++
sn't bring much complexity.
The idea is to create new 'evsel->summary_counts' which sums up the
counts delta per interval. Before reporting the summary, we copy the
data from evsel->summary_counts to evsel->counts, and next we just
follow current code.
Signed-off-by: Jin Yao
Hi John, Jiri,
On 4/30/2020 7:48 PM, John Garry wrote:
On 30/04/2020 12:15, Jiri Olsa wrote:
+
On Thu, Apr 30, 2020 at 09:54:18AM +0100, John Garry wrote:
On 30/04/2020 09:45, Jiri Olsa wrote:
On Thu, Apr 30, 2020 at 08:36:18AM +0800, Jin Yao wrote:
A big uncore event group is split into
Hi Jiri,
On 4/30/2020 4:45 PM, Jiri Olsa wrote:
On Thu, Apr 30, 2020 at 08:36:18AM +0800, Jin Yao wrote:
A big uncore event group is split into multiple small groups which
only include the uncore events from the same PMU. This has been
supported in the commit 3cdc5c2cb924a ("perf parse-e
On 10/23/2019 7:37 PM, Jiri Olsa wrote:
On Tue, Oct 22, 2019 at 04:07:06PM +0800, Jin Yao wrote:
SNIP
-static int filter_cb(struct hist_entry *he, void *arg __maybe_unused)
-{
- /* Skip the calculation of column length in output_resort */
- he->filtered = t
On 10/23/2019 7:36 PM, Jiri Olsa wrote:
On Tue, Oct 22, 2019 at 04:07:10PM +0800, Jin Yao wrote:
Previous patch has implemented a new sort option "total_cycles".
But there was only stdio mode supported.
This patch supports the tui mode and support '--percent-limit'.
On 10/23/2019 7:36 PM, Jiri Olsa wrote:
On Tue, Oct 22, 2019 at 04:07:08PM +0800, Jin Yao wrote:
SNIP
+static void get_block_hists(struct hists *hists, struct block_hist *bh,
+ struct report *rep)
+{
+ struct rb_node *next = rb_first_cached(&hists->
On 10/23/2019 7:36 PM, Jiri Olsa wrote:
On Tue, Oct 22, 2019 at 04:07:08PM +0800, Jin Yao wrote:
SNIP
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 43d1d410854a..eb286700a8a9 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -492,6 +492,10 @@ struct
On 10/23/2019 7:36 PM, Jiri Olsa wrote:
On Tue, Oct 22, 2019 at 04:07:08PM +0800, Jin Yao wrote:
SNIP
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cdb436d6e11f..44aed40e9071 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -51,6
On 10/23/2019 10:27 PM, Jiri Olsa wrote:
On Wed, Oct 23, 2019 at 09:09:34PM +0800, Jin, Yao wrote:
On 10/23/2019 7:36 PM, Jiri Olsa wrote:
On Tue, Oct 22, 2019 at 04:07:08PM +0800, Jin Yao wrote:
SNIP
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index
Hi Jiri,
On 4/27/2020 6:10 PM, Jiri Olsa wrote:
On Mon, Apr 20, 2020 at 09:04:44AM +0800, Jin Yao wrote:
SNIP
compute_flag div.c:25 compute_flag div.c:25
compute_flag div.c:22 compute_flag div.c:22
main
Hi Jiri,
On 4/27/2020 6:10 PM, Jiri Olsa wrote:
On Mon, Apr 20, 2020 at 09:04:46AM +0800, Jin Yao wrote:
We think the stream is a callchain which is aggregated by the LBR
records from samples. By browsing the stream, we can understand
the code flow.
The struct callchain_node represents one
Hi Jiri,
On 4/27/2020 6:11 PM, Jiri Olsa wrote:
On Mon, Apr 20, 2020 at 09:04:45AM +0800, Jin Yao wrote:
Sometimes, a small change in a hot function reducing the cycles of
this function, but the overall workload doesn't get faster. It is
interesting where the cycles are moved to.
Wh
Hi Jiri,
On 4/27/2020 6:29 PM, Jiri Olsa wrote:
On Mon, Apr 20, 2020 at 09:04:44AM +0800, Jin Yao wrote:
Sometimes, a small change in a hot function reducing the cycles of
this function, but the overall workload doesn't get faster. It is
interesting where the cycles are moved to.
Wh
o user directly (especially valuable for perf newbie).
The warning is,
Warning:
Please install libunwind development packages during the perf build.
Both tui and stdio are supported.
Signed-off-by: Jin Yao
---
tools/perf/builtin-report.c | 7 +++
1 file changed, 7 insertions(+)
diff --g
On 10/10/2019 8:33 PM, Arnaldo Carvalho de Melo wrote:
Em Thu, Oct 10, 2019 at 04:33:57PM +0800, Jin, Yao escreveu:
On 10/10/2019 4:00 PM, Jiri Olsa wrote:
On Thu, Oct 10, 2019 at 02:46:36PM +0800, Jin, Yao wrote:
On 10/1/2019 10:17 AM, Andi Kleen wrote:
I think it's useful. Mak
perf record has supported --all-kernel / --all-user to configure all
used events to run in kernel space or run in user space. But perf
stat doesn't support these options.
It would be useful to support these options in perf-stat too to keep
the same semantics.
Signed-off-by: Jin Yao
---
On 10/11/2019 3:21 PM, Jiri Olsa wrote:
On Fri, Oct 11, 2019 at 10:50:35AM +0800, Jin, Yao wrote:
On 10/10/2019 8:33 PM, Arnaldo Carvalho de Melo wrote:
Em Thu, Oct 10, 2019 at 04:33:57PM +0800, Jin, Yao escreveu:
On 10/10/2019 4:00 PM, Jiri Olsa wrote:
On Thu, Oct 10, 2019 at 02:46
1.002109793 seconds time elapsed
Thanks
Jin Yao
---
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 9207b6c45475..2518204cffd1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1853,6 +1853,8 @@ static void setup_system_wide(int forks)
] as a new
PMU leader.
So this patch uses strcmp to compare the PMU name between events.
Fixes: 3cdc5c2cb924a ("perf parse-events: Handle uncore event aliases in small
groups properly")
Signed-off-by: Jin Yao
---
tools/perf/util/parse-events.c | 5 ++---
1 file changed, 2 insertions(+),
On 10/15/2019 12:23 AM, Arnaldo Carvalho de Melo wrote:
Em Mon, Oct 14, 2019 at 04:42:08PM +0200, Jiri Olsa escreveu:
On Fri, Oct 11, 2019 at 01:05:45PM +0800, Jin Yao wrote:
perf record has supported --all-kernel / --all-user to configure all
used events to run in kernel space or run in
On 10/14/2019 11:32 PM, Jiri Olsa wrote:
On Tue, Oct 08, 2019 at 03:04:57PM +0800, Jin Yao wrote:
It would be useful to support sorting for all blocks by the
sampled cycles percent per block. This is useful to concentrate
on the globally busiest/slowest blocks.
This patch series implements
uot;--deprecated" is enabled.
Signed-off-by: Jin Yao
---
tools/perf/Documentation/perf-list.txt | 3 +++
tools/perf/builtin-list.c | 14 ++
tools/perf/pmu-events/jevents.c| 26 --
tools/perf/pmu-events/jevents.h| 3 ++-
116.0K0.42% 19
[random_r.c:357 -> random_r.c:394] libc-2.27.so
It only shows the entries which 'Sampled Cycles%' > 1%.
Signed-off-by: Jin Yao
---
tools/perf/builtin-report.c | 2 +-
tools/perf/ui/stdio/hist.c | 7 ++-
We have already implemented some block related functions. Now it's
time to do some cleanup, and move the functions and structures to
the new block.h/block.c.
Signed-off-by: Jin Yao
---
tools/perf/builtin-diff.c | 38 ++-
tools/perf/util/Build | 1 +
tools/perf
o and tui. And also with the supporting
of --percent-limit.
v2:
---
Rebase to perf/core branch
Jin Yao (5):
perf util: Create new block.h/block.c for block related functions
perf util: Count the total cycles of all samples
perf report: Sort by sampled cycles percent per block for stdio
a new argument 'total_cycles' in hist__account_cycles(),
which will be added with the cycles of each sample.
Signed-off-by: Jin Yao
---
tools/perf/builtin-annotate.c | 2 +-
tools/perf/builtin-diff.c | 3 ++-
tools/perf/builtin-report.c | 2 +-
tools/perf/builtin-top.c | 3 ++-
1
[perf_event_nmi_handler+57 -> perf_event_nmi_handler+63] [kernel.kallsyms]
0.00% 10.02% 1
[perf_event_nmi_handler+68 -> perf_event_nmi_handler+74] [kernel.kallsyms]
Signed-off-by: Jin Yao
---
tools/perf/Doc
> random_r.c:388] libc-2.27.so
1.57% 123.3K0.02% 1
[div.c:42 -> div.c:44] div
1.44% 116.0K0.42% 19
[random_r.c:357 -&g
On 10/14/2019 11:32 PM, Jiri Olsa wrote:
On Tue, Oct 08, 2019 at 03:04:57PM +0800, Jin Yao wrote:
It would be useful to support sorting for all blocks by the
sampled cycles percent per block. This is useful to concentrate
on the globally busiest/slowest blocks.
This patch series implements
On 10/15/2019 4:41 PM, Jiri Olsa wrote:
On Tue, Oct 15, 2019 at 01:33:48PM +0800, Jin Yao wrote:
SNIP
+enum {
+ PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_COV,
+ PERF_HPP_REPORT__BLOCK_LBR_CYCLES,
+ PERF_HPP_REPORT__BLOCK_CYCLES_PCT,
+ PERF_HPP_REPORT__BLOCK_AVG_CYCLES
On 10/15/2019 11:11 PM, Arnaldo Carvalho de Melo wrote:
Em Tue, Oct 15, 2019 at 09:57:33AM +0800, Jin, Yao escreveu:
On 10/15/2019 12:23 AM, Arnaldo Carvalho de Melo wrote:
Em Mon, Oct 14, 2019 at 04:42:08PM +0200, Jiri Olsa escreveu:
On Fri, Oct 11, 2019 at 01:05:45PM +0800, Jin Yao
On 10/15/2019 5:14 PM, Jiri Olsa wrote:
On Tue, Oct 15, 2019 at 10:53:57AM +0800, Jin Yao wrote:
There are some deprecated events listed by perf list. But we can't remove
them from perf list with ease because some old scripts may use them.
Deprecated events are old names of renamed e
On 10/16/2019 3:27 PM, Jiri Olsa wrote:
On Wed, Oct 16, 2019 at 08:59:13AM +0800, Jin, Yao wrote:
On 10/15/2019 5:14 PM, Jiri Olsa wrote:
On Tue, Oct 15, 2019 at 10:53:57AM +0800, Jin Yao wrote:
There are some deprecated events listed by perf list. But we can't remove
them from perf
401 - 500 of 1316 matches
Mail list logo
