Re: [iovisor-dev] kprobe/kretprobe on cls_bpf_classify

2016-10-31 Thread William Tu via iovisor-dev
Hi Brenden, thanks, I will double check my kernel settings. On Sat, Oct 29, 2016 at 3:16 PM, Brenden Blanco wrote: > > > On Sat, Oct 29, 2016 at 1:27 AM, William Tu via iovisor-dev > wrote: >> >> Hi, >> >> I'm trying to measure the performance of my BPF programs, which attach >> to clsact. As a

Re: [iovisor-dev] kprobe/kretprobe on cls_bpf_classify

2016-10-29 Thread Brenden Blanco via iovisor-dev
On Sat, Oct 29, 2016 at 1:27 AM, William Tu via iovisor-dev < iovisor-dev@lists.iovisor.org> wrote: > Hi, > > I'm trying to measure the performance of my BPF programs, which attach > to clsact. As a start, I thought I could simply measure the cycles > spent on cls_bpf_classify(), because it's the

[iovisor-dev] kprobe/kretprobe on cls_bpf_classify

2016-10-28 Thread William Tu via iovisor-dev
Hi, I'm trying to measure the performance of my BPF programs, which attach to clsact. As a start, I thought I could simply measure the cycles spent on cls_bpf_classify(), because it's the wrapper calling into my BPF programs. However, it seems that kprobe can not probe cls_bpf_classify(), even th