On Fri, May 05, 2017 at 09:57:54AM +0200, Jiri Olsa wrote: > On Thu, May 04, 2017 at 03:26:20PM -0700, Andi Kleen wrote: > > On Tue, May 02, 2017 at 08:41:47AM +0200, Jiri Olsa wrote: > > > On Mon, May 01, 2017 at 12:47:46PM -0700, Andi Kleen wrote: > > > > From: Andi Kleen <a...@linux.intel.com> > > > > > > > > With perf script it is common that we just want to add or remove a > > > > field. > > > > Currently this requires figuring out the long list of default fields and > > > > specifying them first, and then adding/removing the new field. > > > > > > > > This patch adds a new + - syntax to merely add or remove fields, > > > > that allows more succint and clearer command lines > > > > > > > > For example to remove the comm field from PMU samples: > > > > > > > > Previously > > > > > > > > perf script -F pid,cpu,time,event,sym,ip,dso,period > > > > 0 [000] 504345.383126: 1 cycles: ffffffff90060c66 > > > > native_write_msr ([kernel.kallsyms]) > > > > > > > > with the new syntax > > > > > > > > perf script -F -comm > > > > 0 [000] 504345.383126: 1 cycles: ffffffff90060c66 > > > > native_write_msr ([kernel.kallsyms]) > > > > > > > > > I haven't checked deeply yet, but I'm getting different pids > > > with the new syntax, perhaps some mixing with tids column? > > > > Cannot reproduce. Do you have an exact command line? > > > > The patch shouldn't really change any columns. > > > > [jolsa@krava perf]$ ./perf record -a
I looked at this, and I don't think it's different with my patch. Any time you set fields you get different output versus default: % perf script -F pid,cpu,time,event,sym,ip,dso,period,comm vs % perf script First gives PID second TID. It would be good to fix, but I don't think it should block my patch. -Andi
