On Wed, Feb 14, 2024 at 9:42 AM Ian Rogers <irogers@xxxxxxxxxx> wrote:
>
> On Wed, Feb 14, 2024 at 9:24 AM Arnaldo Carvalho de Melo
> <acme@xxxxxxxxxx> wrote:
> >
> > On Tue, Feb 13, 2024 at 10:37:03PM -0800, Ian Rogers wrote:
> > > Commit 91e467bc568f ("perf machine: Use hashtable for machine
> > > threads") made the iteration of thread tids unordered. The perf report
> > > --tasks output now shows child threads in an order determined by the
> > > hashing. For example, in this snippet tid 3 appears after tid 256 even
> > > though they have the same ppid 2:
> > >
> > > ```
> > > $ perf report --tasks
> > > % pid tid ppid comm
> > > 0 0 -1 |swapper
> > > 2 2 0 | kthreadd
> > > 256 256 2 | kworker/12:1H-k
> > > 693761 693761 2 | kworker/10:1-mm
> > > 1301762 1301762 2 | kworker/1:1-mm_
> > > 1302530 1302530 2 | kworker/u32:0-k
> > > 3 3 2 | rcu_gp
> > > ...
> > > ```
> > >
> > > The output is easier to read if threads appear numerically
> > > increasing. To allow for this, read all threads into a list then sort
> > > with a comparator that orders by the child task's of the first common
> > > parent. The list creation and deletion are created as utilities on
> > > machine. The indentation is possible by counting the number of
> > > parents a child has.
> > >
> > > With this change the output for the same data file is now like:
> > > ```
> > > $ perf report --tasks
> > > % pid tid ppid comm
> > > 0 0 -1 |swapper
> > > 1 1 0 | systemd
> > > 823 823 1 | systemd-journal
> > > 853 853 1 | systemd-udevd
> > > 3230 3230 1 | systemd-timesyn
> > > 3236 3236 1 | auditd
> > > 3239 3239 3236 | audisp-syslog
> > > 3321 3321 1 | accounts-daemon
> >
> >
> > Since we're adding extra code for sorting wouldn't be more convenient to
> > have this done in an graphically hierarchical output?
> >
> > But maybe to make this honour asking for a CSV output the above is
> > enough? Or can we have both, i.e. for people just doing --tasks, the
> > hirarchical way, for CSV, then like above, with the comma separator.
> >
> > But then perf stat has -x to ask for CSV that is used by the more
> > obscure --exclude-other option :-\
> >
> > Maybe we need a --csv that is consistent accross all tools.
>
> I've no objection to a graphical/CSV output, I was in this code as I
> was restructuring it for memory savings. Fixing the output ordering
> was a side-effect, the "graphical" sorting/indentation is mentioned as
> it is carrying forward a behavior from the previous code but done in a
> somewhat different way. Let's have other output things as follow up
> work.
Agreed, maybe a good project for GSoC students..
Thanks,
Namhyung
