USB-related problem

[Eugene Grosbein]

On 11.11.2015 19:05, Konstantin Belousov wrote:

> On Tue, Nov 10, 2015 at 02:25:09AM +0700, Eugene Grosbein wrote:
>> On 09.11.2015 22:53, Adrian Chadd wrote:
>>> ok, let's get it to hang, then break into ddb and do 'show
>>> allthreads', 'show alllocks', 'bufvars' with my vfs_bio.c patch, etc.
>>
>> I've re-read https://www.freebsd.org/doc/en/books/developers-handbook/kerneldebug-deadlocks.html
>> and rebuilt kernel with additional debugging and reproduced the problem again to supply
>> more vfs lock info:
> 
> You have syncer running with the buffer arena mutex locked.  This probably
> means that you have DIAGNOSTIC option turned on, do you ?

I do, I've just added it before latest series of my tests because of Handbook instuctions.
The problem reproduces without DIAGNOSTICS too.

> If yes, set debug.vmem_check to zero, otherwise it just eats your anemic CPU.
> 
> Also, I am curious what is the value of vfs.unmapped_buf_allowed on
> your platform.

vfs.unmapped_buf_allowed: 0

I've set sysctl debug.vmem_check=0 and repeated the test.
The problem reproduced without any changes in my trace.