[Bug 236233] Python multiprocessing is 4x slower with 11.2 compared to 11.0 kernel

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236233

--- Comment #4 from Alex Richardson <arichardson at FreeBSD.org> ---
It is a virtual machine with an Intel CPU: CPU info from dmesg:

Hyper-V Version: 0.0.0 [SP0]
  Features=0x870<APIC,HYPERCALL,VPINDEX,TMFREQ>
  PM Features=0x0 [C0]
  Features3=0x0
XEN: Hypervisor version 4.7 detected.
CPU: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (2593.81-MHz K8-class CPU)
  Origin="GenuineIntel"  Id=0x206d6  Family=0x6  Model=0x2d  Stepping=6
 
Features=0x17c3fbff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,ACPI,MMX,FXSR,SSE,SSE2,HTT>
  Features2=0x80b82201<SSE3,SSSE3,CX16,SSE4.1,SSE4.2,x2APIC,POPCNT,HV>
  AMD Features=0x28100800<SYSCALL,NX,RDTSCP,LM>
  AMD Features2=0x1<LAHF>
Hypervisor: Origin = "Microsoft Hv"
real memory  = 118107406336 (112636 MB)
avail memory = 114828369920 (109508 MB)
Event timer "LAPIC" quality 100
ACPI APIC Table: <Xen HVM>
FreeBSD/SMP: Multiprocessor System Detected: 32 CPUs
FreeBSD/SMP: 2 package(s) x 16 core(s)


It is kind of difficult to see which sycalls take longer  before and after but
my guess is that it is related to semaphores since it is attempting to get data
from the subprocesses and it uses semaphores for synchronization.

I'm not sure if there is an easy way to see what is taking longer. I'll see if
I can somehow get the information using DTrace.

-- 
You are receiving this mail because:
You are the assignee for the bug.