Crash when replaying a trace of Mixxx (part 3)

[napaalm]

Replaying a trace of Mixxx recorded with rr built from master (at cfafbfd) causes a crash. To work around #3672 I stopped the pipewire daemon before recording the execution.

I noticed that I can avoid the crash by passing the flag -n to rr record

So, here are some logs for @khuey:

• rr record and rr replay -a output: mixxx_replay_crash_part_3.txt
  • gdb backtrace: mixxx_replay_crash_part_3_gdb_backtrace.txt
  • rr dump -p -m -b: mixxx_replay_crash_part_3_dump.txt.gz
• rr record -n and rr dump -p -m -b output: mixxx_replay_crash_part_3_no_syscall_buffer_dump.txt.gz

[khuey]

Which exact CPU are you using?

[napaalm]

Here's my /proc/cpuinfo

processor	: 0
vendor_id	: AuthenticAMD
cpu family	: 25
model		: 68
model name	: AMD Ryzen 9 PRO 6950H with Radeon Graphics
stepping	: 1
microcode	: 0xa404102
cpu MHz		: 4166.297
cache size	: 512 KB
physical id	: 0
siblings	: 16
core id		: 0
cpu cores	: 8
apicid		: 0
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 16
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca debug_swap
bugs		: sysret_ss_attrs spectre_v1 spectre_v2 spec_store_bypass srso
bogomips	: 6590.39
TLB size	: 2560 4K pages
clflush size	: 64
cache_alignment	: 64
address sizes	: 48 bits physical, 48 bits virtual
power management: ts ttp tm hwpstate cpb eff_freq_ro [13] [14]

I executed zen_workaround.py as root and echo 1 | sudo tee /proc/sys/kernel/perf_event_paranoid before running rr.

[rocallahan]

This is a PMU issue; we've requested a PMU interrupt at a certain ticks value and we're not getting it:

[FATAL src/PerfCounters.cc:976:read_ticks()]
 (task 10958 (rec:10901) at time 142727)
 -> Assertion `!counting_period || interrupt_val <= adjusted_counting_period' failed to hold. Detected 272655 tic
ks, expected no more than 269042

If you replay multiple times does it fail the same way at the same point every time?

Do you have access to an Intel box you can try recording and replaying on?