Christian von Elm
Christian von Elm
From what I've read, we would ideally extend our existing `--call-graph` option so that `--call-graph=lbr` gives us LBR and `--call-graph=fp` (mirroring perfs nomenclature) would give us traditional call stack recording....
Branch issue-242-lbr-support contains a draft of support for last branch records. Initial results look promising, with the samples providing perfect backtraces almost all of the time. However, the distribution of...
This is all the information the kernel gives us about events ```cpp static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) { int i = 0; int tc = t->action >>...
This issue is from now on only concerned with the how and why of topdown metrics in lo2s (with a focus on alder lake), alder lake support i.,g. has been...
I have looked at the example code for alder lake and the documentation at `tools/perf/Documentation/topdown.txt` and it is practically identical to how you can read topdown events Ice Lake. There...
As discovered in the PR for Alder Lake support. The individual topdown metrics are not available as simple perf events on Alder Lake.
One question is how lo2s should list those events Currently I have implemented it like this: ``` [...] amd64_fam17h_zen2::RETIRED_CPUID_INSTRUCTIONS amd64_fam17h_zen2::SMI_RECEIVED amd64_fam17h_zen2::INTERRUPT_TAKEN amd64_fam17h_zen2::MAB_ALLOCATION_BY_PIPE - TLB_PIPE_EARLY - HW_PF - TLB_PIPE_LATE - ST_PIPE...
Implemented in 92f68a89f2aa8bb40f6725ee7e1f13001b11d6df
# block level I/O Blocklevel IO can be traced using those 2 tracepoints: - block:block_rq_insert: event triggered by the insertion of a request into the queue - block:block_rq_complete: Event triggered...
# file level I/O File Level I/O should be traceable by using: - syscalls:sys_enter_open - syscalls:sys_(enter|exit)_read - syscalls:sys_(enter|exit)_write - syscalls:sys_exit_close at least it would be nice if it works like...