发自我的 iPhone
> 在 2015年12月11日，下午8:03，Arnaldo Carvalho de Melo <a...@kernel.org> 写道： > > Em Tue, Dec 08, 2015 at 02:25:34AM +0000, Wang Nan escreveu: >> From: He Kuang <heku...@huawei.com> >> >> This patch adds new bison rules for specifying an alias name to a perf >> event, which allows cmdline refer to previous defined perf event through >> its name. With this patch user can give alias name to a perf event using >> following cmdline: > > Please add Jiri Olsa to any changes that touches the parser changes. > > Can you reword the above phrase? Does it mean something like: > > ---- > This patches adds new bison rules for specifying an alias to a perf > event, which allows referring to this previously defined perf event > through this alias." > ---- > > But then, why would I want this aliasing? The provided examples shows a > way to obfuscate 'cycles', a perfectly good name, why would one want to > call it "mypmu"? > Sorry. I should put this patch after 7/16 so you won't get confused. Without event aliasing it is hard to select an event and insert it into a BPF map. Patch 7/16 would use alias like: # perf record -e evt=cycles/no-inherit/ -e BPF.c/maps.pmu.event=evt/ ... So it put cycles/no-inherit/ into that map. Thank you. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
