Re: [PATCH] Name shared memory segments in a more portable way

On Tue, Oct 25, 2011 at 5:12 PM, Alex Rousskov
<rousskov_at_measurement-factory.com> wrote:
> On 10/25/2011 01:50 AM, Kinkie wrote:
>> On Tue, Oct 25, 2011 at 8:05 AM, Kinkie <gkinkie_at_gmail.com> wrote:
>>> On Tue, Oct 25, 2011 at 7:33 AM, Alex Rousskov
>>> <rousskov_at_measurement-factory.com> wrote:
>>>> Hello,
>>>>
>>>>    This patch should make shm_open() work on FreeBSD and some other
>>>> OSes. It is untested beyond test-builds.sh on Linux, but is based on
>>>> working boost::interprocess code. The preamble has the details.
>>>>
>>>
>>> I'm giving it a spin in the build farm on freebsd and openbsd.
>
> Thank you.
>
>> It's building but failing unit tests:
>> FreeBSD:
>> http://build.squid-cache.org/job/3.ALPHA-PATCH-amd64-FreeBSD-7.2/20/consoleText
>
> There are two problems here:
>
> 1) I guessed the return value of shm_portable_segment_name_is_path wrong
> for FreeBSD v7+ jails (at least).
>
> 2) Fixing #1 exposes a more serious problem:
>
>> Fatal: Ipc::Mem::Segment::create failed to shm_open(/usr/local/squid/var/run/squidtestRock__testRockSearch): (2) No such file or directory
>
> Here, our "use PREFIX for FreeBSD segment names" logic kicks in as it
> should, but the test fails because there is no /usr/local/squid/var/run/
> when/where the test runs. PREFIX-based names do not work for tests. I
> see two possible solutions:
>
> A) Create a special "we are in a test mode", "use current dir", or a
> similar flag so that shm_open can use current dir for shared segments
> during testing. Special flags are ugly, but this will allow general code
> to continue to use path-agnostic names for shared segments.
>
> B) Switch to path-based names for shared segments in the general code.
> When general code needs to name a segment, it will call a
> Segment::GenerateName()-like functions explicitly. The shm_open() code
> itself will no longer try to add a path when needed. This will make the
> general code a little more complex, but the test cases can then use
> names that do not start with a slash. This is what Store test cases
> already do for cache_dir names.
>
> I favor (B) because it is cleaner and more flexible, even though it is
> more work.

Same here. You can rely on the 3.ALPHA-PATCH framework that Amos has
prepared to test on platforms you don't have in-house.

> Any better ideas?

Maybe not better, but alternate: accept to depend on boost.

>> OpenBSD:
>> http://build.squid-cache.org/view/c-experimental/job/3.ALPHA-PATCH-i386-OpenBSD/7/consoleText
>
> "Duplicate fake segment creation" is a different bug that this patch is
> not trying to fix.

-- 
    /kinkie