Messages in this thread | | | From | Roland Dreier <> | Subject | Re: [ofa-general] Re: [GIT PULL] please pull ummunotify | Date | Wed, 30 Sep 2009 10:06:32 -0700 |
| |
> Performance events filtering is being worked on and now with the proper > non-DoS limit you've added you can lose events too, dont you? So it's > all a question of how much buffering to add - and with perf events too > you can buffer arbitrary large amount of events.
No, the idea for non-DoS for ummunotify is that we would limit the number of regions the application can register; so an application might hit the limit up front but no runtime loss of events once a region was registered successfully.
> I think this could be done in a simpler, less limited, more generic, > more useful form by using some variation of perf events. > > You should be able to get all that you want by adding two TRACE_EVENT() > tracepoints and using the existing perf event syscall to get the events > to user-space.
Yes, I would like to use perf events too. Would it be plausible to create a way for userspace to create a "counter" for each address range being watched? Then events would not be lost, because those counters would become non-zero.
> Meaning that this: > 9 files changed, 1060 insertions(+), 1 deletions(-)
Note that lots/ of the files touched here are in Documentation or are one-line changes to Makefiles etc.
- R.
| |