On Thu, 4 Aug 2016 11:30:33 -0400 Steven Rostedt <rostedt@xxxxxxxxxxx> wrote: > Note, I'm currently working on adding code to detect NMIs to this as > well. And perhaps even tracing SMI counters. Just to show what caused > the latency, as latency isn't measured by the counters (that I know of). > I like the trace report, but for one small thing; I think it's worth either adding units to the reported latency values (us suffix) or putting in a header line that hwlatdetect values are reported in microseconds. > <...>-2644 [001] d... 202.735708: [99] inner:13 outer:16 ts:1470352534.886878855 > <...>-2644 [001] d... 206.767274: [100] inner:14 outer:18747 ts:1470352538.917966818 smi-total:2 > <...>-2644 [002] d... 207.775164: [101] inner:0 outer:19162 ts:1470352539.920988709 smi-total:6 > <...>-2644 [003] d... 208.783067: [102] inner:19376 outer:19276 ts:1470352540.923010578 smi-total:6 > <...>-2644 [000] d... 209.827416: [103] inner:19650 outer:20665 ts:1470352541.926032469 smi-total:6 > <...>-2644 [001] d... 210.831062: [104] inner:20526 outer:20680 ts:1470352542.973055312 smi-total:6 Clark -- The United States Coast Guard: Ruining natural selection since 1790
Attachment:
pgpXkkNnCEmU5.pgp
Description: OpenPGP digital signature
