Messages in this thread | | | Date | Wed, 30 Jan 2013 21:58:47 +0100 | From | Andi Kleen <> | Subject | Re: [PATCH 07/12] perf, x86: Avoid checkpointed counters causing excessive TSX aborts v3 |
| |
> That's a very low sampling rate, yet I think it would be rejected by your code.
You mean allowed?
> But if I come in with frequency 0x7fffffff+1, then that's a very high > frequency, thus > small period, I would pass the test. So I think you need to reinforce the test > for freq=1.
I'm aware that there are some configs that can slip through, but there's no other choice if we still allow guest perf stat. The cutoff is somewhat arbitary.
It's not a correctness problem, just things can be unexpectedly slower and you may see unexpected NMI messages.
-Andi -- ak@linux.intel.com -- Speaking for myself only.
| |