Joshua M. Clulow writes:

> On 23 June 2015 at 14:11, Ryan Zezeski <[email protected]> wrote:
>> 2) I decided to try to build 4.0.2.4 but with the alternate signal stack
>>    disabled. But the build got stock. Interesting enough it got stuck in
>>    the same place before when I was writing my original report but after
>>    sitting there for a few minutes it eventually kicked itself free (or
>>    maybe me poking around caused it to unstick). Anyways, I wrote up a
>>    report of what I saw:
>>
>> https://gist.github.com/rzezeski/8a967f9cfdd3976869eb#comment-1479293
>
> When the native tools tell you the program is blocked in "SYS#0",
> that's an artefact of the way Linux system calls are handled by LX.
> If you look at the kernel stack for that LWP, you will likely see
> where it's actually blocked in the kernel.  The inflight Linux system
> call number is also stashed in "br_syscall_num" of the "lx_lwp_data_t"
> for that LWP (which is pointed to by "lwp_brand" on the "klwp_t").

This was a big help! Thank you.

I have another stuck build and it looks like the futex implementation
may be the culprit. I will run more tests to verify futex is always
invovled when stuck. Here is my latest report:

https://gist.github.com/rzezeski/8a967f9cfdd3976869eb#comment-1479375

-- 
-Z


-------------------------------------------
smartos-discuss
Archives: https://www.listbox.com/member/archive/184463/=now
RSS Feed: https://www.listbox.com/member/archive/rss/184463/25769125-55cfbc00
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=25769125&id_secret=25769125-7688e9fb
Powered by Listbox: http://www.listbox.com

Reply via email to