node exporter cpu crash on boot on 64cpu flavor host

[demetthyl]

Bug Report

Describe the bug
When starting fluent-bit on a 64cpu ubuntu with node exporter input, fluent-bit instant crashes

To Reproduce

• Start a 64cpu ubuntu VM

• Install fluent-bit and run node exporter cpu metrics

• Steps to reproduce the problem:

1/ apt-get install fluent-bit
2/ sudo /opt/fluent-bit/bin/fluent-bit -i node_exporter_metrics -pmetrics=cpu -p path.sysfs=/sys -Z -vv -o stdout

Output:

[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing core_throttle_count: /sys/devices/system/cpu/cpu39
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing package_throttle_count: /sys/devices/system/cpu/cpu39
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing core_throttle_count: /sys/devices/system/cpu/cpu4
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing package_throttle_count: /sys/devices/system/cpu/cpu4
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing core_throttle_count: /sys/devices/system/cpu/cpu40
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing package_throttle_count: /sys/devices/system/cpu/cpu40
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing core_throttle_count: /sys/devices/system/cpu/cpu41
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing package_throttle_count: /sys/devices/system/cpu/cpu41
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing core_throttle_count: /sys/devices/system/cpu/cpu42
[2025/02/12 13:34:17] [engine] caught signal (SIGSEGV)
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing package_throttle_count: /sys/devices/system/cpu/cpu42
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing core_throttle_count: /sys/devices/system/cpu/cpu43
[2025/02/12 13:34:17] [debug] [input:node_exporter_metrics:node_exporter_metrics.0] CPU is missing package_throttle_count: /sys/devices/system/cpu/cpu43
#0 0x61dce0d07451 in ne_cpu_update() at plugins/in_node_exporter_metrics/ne_cpu_linux.c:393
#1 0x61dce0d05ef7 in activate_collector() at plugins/in_node_exporter_metrics/ne.c:160
#2 0x61dce0d05ef7 in in_ne_init() at plugins/in_node_exporter_metrics/ne.c:223
#3 0x61dce0c8be35 in input_thread() at src/flb_input_thread.c:365
#4 0x61dce0cad8a1 in step_callback() at src/flb_worker.c:43
#5 0x734b7ca9caa3 in ???() at ???:0
#6 0x734b7cb29c3b in ???() at ???:0
#7 0xffffffffffffffff in ???() at ???:0
Aborted

Notable point: if i point on an unexisting sys path (/sys2 for example), i have /proc datas in stdout and error about sys2 :

[2025/02/12 13:49:04] [error] [input:node_exporter_metrics:node_exporter_metrics.0] read error, check permissions: /sys2/devices/system/cpu/cpu[0-9]*

But fluent-bit is up and running

=> something happens in /sys with 64cpu : volumetry ?

For information, ive installed prometheus node exporter standalone on the host, to compare, and it works like a charm

=> Do i hit a buffer or something when fluent-bit tries to gather cpu infos in /sys for 64cpus ?

Your Environment

• Version used: 3.2.6
• Server type and version: Openstack VM
• Operating System and version:

uname -a
Linux r1-mongodb-f2-0 6.8.0-39-generic #39-Ubuntu SMP PREEMPT_DYNAMIC Fri Jul 5 21:49:14 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux

ubuntu@r1-mongodb-f2-0:~$ lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 40 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 64
On-line CPU(s) list: 0-63
Vendor ID: GenuineIntel
Model name: Intel Xeon Processor (Icelake)
CPU family: 6
Model: 134
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s): 64
Stepping: 0
BogoMIPS: 5200.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq
vmx ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow fl
expriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsa
ves avx_vnni avx512_bf16 wbnoinvd arat vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri mo
vdir64b fsrm md_clear serialize tsxldtrk avx512_fp16 arch_capabilities
Virtualization features:
Virtualization: VT-x
Hypervisor vendor: KVM
Virtualization type: full
Caches (sum of all):
L1d: 2 MiB (64 instances)
L1i: 2 MiB (64 instances)
L2: 256 MiB (64 instances)
L3: 1 GiB (64 instances)

• Filters and plugins:
  node-exporter embedded with 3.2.6 fluent-bit