1 |
Hi, |
2 |
|
3 |
I have done many tests on my ~x86 system to confirm that it is nptl based: |
4 |
|
5 |
- I have the nptl and nptlonly use flags in my make.conf and my system |
6 |
is up to date. |
7 |
|
8 |
- Running /lib/libc.so.6 shows: |
9 |
|
10 |
ta@bonsai ~ $ /lib/libc.so.6 |
11 |
GNU C Library stable release version 2.15, by Roland McGrath et al. |
12 |
Copyright (C) 2012 Free Software Foundation, Inc. |
13 |
This is free software; see the source for copying conditions. |
14 |
There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A |
15 |
PARTICULAR PURPOSE. |
16 |
Compiled by GNU CC version 4.5.3. |
17 |
Compiled on a Linux 3.5.0 system on 2012-09-10. |
18 |
Available extensions: |
19 |
C stubs add-on version 2.1.2 |
20 |
crypt add-on version 2.1 by Michael Glad and others |
21 |
Gentoo patchset 21 |
22 |
GNU Libidn by Simon Josefsson |
23 |
Native POSIX Threads Library by Ulrich Drepper et al |
24 |
Support for some architectures added on, not maintained in glibc |
25 |
core. |
26 |
BIND-8.2.3-T5B |
27 |
libc ABIs: UNIQUE IFUNC |
28 |
For bug reporting instructions, please see: |
29 |
<http://www.gnu.org/software/libc/bugs.html>. |
30 |
|
31 |
- getconf also indicates nptl: |
32 |
|
33 |
ta@bonsai ~ $ getconf GNU_LIBPTHREAD_VERSION |
34 |
NPTL 2.15 |
35 |
|
36 |
|
37 |
Yet, when I look at the process list, I am seeing all programs that use |
38 |
threads having uniquey pid's for each thread. I even compiled a simple |
39 |
program that just creates 5 threads, each sleeping forever. Again, each |
40 |
thread had a unique pid. |
41 |
|
42 |
I have also checked the kernel config. FUTEX support was enabled, but |
43 |
the top level selector (EXPERT options) was not selected. I guess the |
44 |
top level selector just exposes the FUTEX selector and doesn't really |
45 |
affect whether it is enabled or not. |
46 |
|
47 |
So, what I am wondering now, is my system configured for NPTL or not? |
48 |
|
49 |
-- |
50 |
Timur |