Re: [PATCH V2 06/12] perf mem: Clean up output format

2020-12-08 Thread Jiri Olsa
On Mon, Dec 07, 2020 at 03:19:06PM -0500, Liang, Kan wrote: > > > On 12/4/2020 6:27 PM, Jiri Olsa wrote: > > On Mon, Nov 30, 2020 at 09:27:57AM -0800, kan.li...@linux.intel.com wrote: > > > > SNIP > > > > > @@ -172,7 +172,7 @@ dump_raw_samples(struct perf_tool *tool, > > > { > > > s

Re: [PATCH V2 06/12] perf mem: Clean up output format

2020-12-07 Thread Liang, Kan
On 12/4/2020 6:27 PM, Jiri Olsa wrote: On Mon, Nov 30, 2020 at 09:27:57AM -0800, kan.li...@linux.intel.com wrote: SNIP @@ -172,7 +172,7 @@ dump_raw_samples(struct perf_tool *tool, { struct perf_mem *mem = container_of(tool, struct perf_mem, tool); struct addr_location al;

Re: [PATCH V2 06/12] perf mem: Clean up output format

2020-12-04 Thread Jiri Olsa
On Mon, Nov 30, 2020 at 09:27:57AM -0800, kan.li...@linux.intel.com wrote: SNIP > @@ -172,7 +172,7 @@ dump_raw_samples(struct perf_tool *tool, > { > struct perf_mem *mem = container_of(tool, struct perf_mem, tool); > struct addr_location al; > - const char *fmt; > + const cha

[PATCH V2 06/12] perf mem: Clean up output format

2020-11-30 Thread kan . liang
From: Kan Liang Now, "--phys-data" is the only option which impacts the output format. A simple "if else" is enough to handle the option. But there will be more options added, e.g. "--data-page-size", which also impact the output format. The code will become too complex to be maintained. Divide