[FATAL /home/roc/rr/rr/src/PerfCounters.cc:203:start_counter() errno: ENOENT]

[AkeelAli]

Getting this core dump on Ubuntu in a VM:

$ rr record ./jpegtran -transverse -outfile testout.jpg testimg.jpg 
rr: Saving execution to trace directory `/home/cs6340/.local/share/rr/jpegtran-7'.
[FATAL /home/roc/rr/rr/src/PerfCounters.cc:203:start_counter() errno: ENOENT] Unable to open performance counter with 'perf_event_open'; are perf events enabled? Try 'perf record'.
Aborted (core dumped)

$ rr replay

rr: error: Version file for recorded trace `/home/cs6340/.local/share/rr/latest-trace/version' not found.  Did you record
           `/home/cs6340/.local/share/rr/latest-trace/version' with an older version of rr?  If so, you'll need to replay
           `/home/cs6340/.local/share/rr/latest-trace/version' with that older version.  Otherwise, your trace is
           likely corrupted.

$ perf --version
perf version 4.2.8-ckt3

$ uname -a
Linux cs6340ProjectVM 4.2.0-30-generic #35-Ubuntu SMP Fri Feb 19 13:52:26 UTC 2016 x86_64 x86_64 x86_64 GNU/Linux

[rocallahan]

are perf events enabled? Try 'perf record'

Did you try perf record? How about perf list?

[AkeelAli]

$ perf record

 usage: perf record [<options>] [<command>]
    or: perf record [<options>] -- <command> [<options>]

    -e, --event <event>   event selector. use 'perf list' to list available events
        --filter <filter>
                          event filter
    -p, --pid <pid>       record events on existing process id
    -t, --tid <tid>       record events on existing thread id
    -r, --realtime <n>    collect data with this RT SCHED_FIFO priority
        --no-buffering    collect data without buffering
    -R, --raw-samples     collect raw sample records from all opened counters
    -a, --all-cpus        system-wide collection from all CPUs
    -C, --cpu <cpu>       list of cpus to monitor
    -c, --count <n>       event period to sample
    -o, --output <file>   output file name
    -i, --no-inherit      child tasks do not inherit counters
    -F, --freq <n>        profile at this frequency
    -m, --mmap-pages <pages[,pages]>
                          number of mmap data pages and AUX area tracing mmap pages
        --group           put the counters into a counter group
    -g                    enables call-graph recording
        --call-graph <mode[,dump_size]>
                          setup and enables call-graph (stack chain/backtrace) recording: fp dwarf lbr
    -v, --verbose         be more verbose (show counter open errors, etc)
    -q, --quiet           don't print any message
    -s, --stat            per thread counts
    -d, --data            Record the sample addresses
    -T, --timestamp       Record the sample timestamps
    -P, --period          Record the sample period
    -n, --no-samples      don't sample
    -N, --no-buildid-cache
                          do not update the buildid cache
    -B, --no-buildid      do not collect buildids in perf.data
    -G, --cgroup <name>   monitor event in cgroup name only
    -D, --delay <n>       ms to wait before starting measurement after program start
    -u, --uid <user>      user to profile
    -b, --branch-any      sample any taken branches
    -j, --branch-filter <branch filter mask>
                          branch stack filter modes
    -W, --weight          sample by weight (on special events only)
        --transaction     sample transaction flags (special events only)
        --per-thread      use per-thread mmaps
    -I, --intr-regs       Sample machine registers on interrupt
        --running-time    Record running/enabled time of read (:S) events
    -k, --clockid <clockid>
                          clockid to use for events, see clock_gettime()
    -S, --snapshot[=<opts>]
                          AUX area tracing Snapshot Mode
        --proc-map-timeout <n>
                          per thread proc mmap processing timeout in ms


$ perf list

List of pre-defined events (to be used in -e):

  alignment-faults                                   [Software event]
  context-switches OR cs                             [Software event]
  cpu-clock                                          [Software event]
  cpu-migrations OR migrations                       [Software event]
  dummy                                              [Software event]
  emulation-faults                                   [Software event]
  major-faults                                       [Software event]
  minor-faults                                       [Software event]
  page-faults OR faults                              [Software event]
  task-clock                                         [Software event]

  rNNN                                               [Raw hardware event descriptor]
  cpu/t1=v1[,t2=v2,t3 ...]/modifier                  [Raw hardware event descriptor]
   (see 'man perf-list' on how to encode it)

  mem:<addr>[/len][:access]                          [Hardware breakpoint]

[rocallahan]

It looks like, as the error messages suggest, hardware performance counters are not enabled on your system. Try dmesg|grep PMU?

[AkeelAli]

You're right. I should mention this is a virtualbox Ubuntu VM.

$ dmesg | grep PMU
[    4.132417] Performance Events: unsupported p6 CPU model 70 no PMU driver, software events only.

[rocallahan]

Ah. As noted here, VirtualBox doesn't support PMU virtualization currently and therefore can't run rr. Sorry!

[Srinivasuluch]

I am seeing same issue on my setup too... Any idea

root@<>:~/Desktop/tmp# dmesg | grep PMU
[ 0.335342] Performance Events: Fam15h core perfctr, AMD PMU driver.
[ 0.336794] NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter.

[Srinivasuluch]

root@<>:~/Desktop/tmp# rr record /usr/bin/clinfo
rr: Saving execution to trace directory `/root/.local/share/rr/clinfo-1'.
[FATAL /home/roc/rr/rr/src/PerfCounters.cc:162:get_cpu_microarch() errno: ENOTTY] CPU 0x30f00 unknown.
Aborted (core dumped)

[khuey]

rr does not work on any AMD microarchitecture. See #2034.

[mikepurvis]

I'm also having no joy, under VMWare:

$ dmesg | grep PMU
[    0.020526] Performance Events: Haswell events, core PMU driver.
[    0.029365] core: PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off

[Hi-Angel]

@mikepurvis the #2816 should fix the problem.