[Bug 220971] Freebsd 11.0p11 - system freeze on intensive I/O

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=220971

            Bug ID: 220971
           Summary: Freebsd 11.0p11 - system freeze on intensive I/O
           Product: Base System
           Version: 11.0-RELEASE
          Hardware: amd64
                OS: Any
            Status: New
          Severity: Affects Some People
          Priority: ---
         Component: kern
          Assignee: freebsd-bugs at FreeBSD.org
          Reporter: execve at gmail.com

Hi,

I am duplicating my text from email to freebsd-questions and also indicating
clues from my investigation so far.

I came back to using FreeBSD after many years on my laptop. The machine is
currently in a dual-boot configuration and I basically replaced FreeBSD to
replace the earlier Ubuntu installation. Machine is at 11.0-RELEASE updated to
p11 via freebsd-update.

I encountered a similar outcome of total system freeze in two kinds of usage.
State of the system:
1) X is not usable - I use xfce - no login manager
2) I cannot ssh into the box - I do not get the username or password prompt -
connection just times out
3) the network interface is ping-able. 
4) I am not able to switch to the system consoles using Ctrl-Alt-F1..8
5) No mouse movement nor screen update
6) I suspected an issue with soft-update and then turned that off. Filesystem
is ufs. fsck is clean. 

Recovery: hard-boot, system comes up, fsck happens, some errors fixed and
resumes working normally.

The problem became visible in two kind of usage scenarios:
1) Running the backup port duplicity to create a backup of the / filesystem. It
would start but at some point but then get stuck. Running it in verbose mode
would sometimes indicate that this would happen when the write to the volume
(default setting of 200M) happens. This was tried 4-5 times. 
2) running split on a 6.4G file (filesystem dump of disk using dump) --
something like 
split -d -b 200M -a 4 - part 
This would then freeze at one point - making the system unusable. I tried this
2-3 times. 

I finally got it to work using idprio 31 before the split command. Tried this
only once - havent tried it with the duplicity command. 

The machine has 8GB RAM and is clearly not reaching the out of memory kind of
situation - basically only about 1.1 or so GB is used. 

I also ran this from the system console without X and faced the same issue - no
panic message - nothing in the logs as well.

I got a clue from my further searching on the freebsd mailing lists and forums.

It has to do with the swap file. ​I dont have a swap partition since I just put
the freebsd root over the ubuntu partition. And I had created a 
swap file based on the  instructions in 11.12.2 Creating a swap file.

https://www.freebsd.org/doc/handbook/adding-swap-space.html

I got a clue from the freebsd-forums:

https://forums.freebsd.org/threads/58266/

If the link is down (for some reason, I see the server is down quite often
these days), use the below cached link:

https://webcache.googleusercontent.com/search?q=cache:y1bJLmSEjWUJ:https://forums.freebsd.org/threads/58266/+&cd=2&hl=en&ct=clnk&gl=in

So, I just did a swapoff -La and then ran the split command again - no issues
whatsover! 

Some idea about the configuration can be had by looking at the information
below; please let me know if any further logs / debugging information needed.


$ freebsd-version 
11.0-RELEASE-p11

$ uname -a
FreeBSD mellon 11.0-RELEASE-p9 FreeBSD 11.0-RELEASE-p9 #0: Tue Apr 11 08:48:40
UTC 2017     root at amd64-builder.daemonology.net:/usr/obj/usr/src/sys/GENERIC 
amd64

CPU: Intel(R) Core(TM) i3-2330M CPU @ 2.20GHz (2195.06-MHz K8-class CPU)
  Origin="GenuineIntel"  Id=0x206a7  Family=0x6  Model=0x2a  Stepping=7
 
Features=0xbfebfbff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,PBE>
 
Features2=0x1dbae3bf<SSE3,PCLMULQDQ,DTES64,MON,DS_CPL,VMX,EST,TM2,SSSE3,CX16,xTPR,PDCM,PCID,SSE4.1,SSE4.2,x2APIC,POPCNT,TSCDLT,XSAVE,OSXSAVE,AVX>
  AMD Features=0x28100800<SYSCALL,NX,RDTSCP,LM>
  AMD Features2=0x1<LAHF>
  XSAVE Features=0x1<XSAVEOPT>
  VT-x: PAT,HLT,MTF,PAUSE,EPT,UG,VPID
  TSC: P-state invariant, performance statistics
real memory  = 8589934592 (8192 MB)
avail memory = 8172896256 (7794 MB)

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