2025-05-07 11:18 UTC-0700 ~ Andrii Nakryiko <andrii.nakryiko@xxxxxxxxx> > On Wed, May 7, 2025 at 2:40 AM Quentin Monnet <qmo@xxxxxxxxxx> wrote: >> >> 2025-05-07 10:56 UTC+0200 ~ Jiri Olsa <olsajiri@xxxxxxxxx> >>> On Tue, May 06, 2025 at 03:33:33PM -0700, Andrii Nakryiko wrote: >>>> On Tue, May 6, 2025 at 6:58 AM Jiri Olsa <jolsa@xxxxxxxxxx> wrote: >>>>> >>>>> Adding support to display ref_ctr_offset in link output, like: >>>>> >>>>> # bpftool link >>>>> ... >>>>> 42: perf_event prog 174 >>>>> uprobe /proc/self/exe+0x102f13 cookie 3735928559 ref_ctr_offset 50500538 >>>> >>>> let's use hex for ref_ctr_offset? >>> >>> I had that, then I saw cookie was dec ;-) either way is fine for me >> >> I'm fine either way, but let's use the same base for the two values >> please. If you want to change the cookie to hexa (in the plain output) >> for better readability, that's OK as well (JSON output needs to remain a >> decimal in both cases, of course). > > Why should cookie and offset use the same base? Offset is always > address-like, so hex makes most sense there, 100%. But a cookie is > most probably going to be some small value (index into array, or small > number representing attachment point number, etc), so decimal is most > natural. Importantly, BPF cookie can't really be a pointer (what will > you do with it on BPF side?), so it's something a bit more > human-driven, and thus decimal seems like a better default. OK my bad, I take it back, then :) Quentin
