[systemd-devel] [PATCH 0/2] RFC for avoid dynamic allocation in?journald

[Holger Hans Peter Freyther]

On Mon, Apr 08, 2013 at 07:06:44PM +0200, Lennart Poettering wrote:

> > Is it really needed to determine the cgroup of /proc/1 on every message?
> > Couldn't journald keep the variables for its identity around?

> a) use gcc's __thread support, i.e. have one static cache var per
>    thread. Since all stuff in systemd's repo is essentially single
>    threaded this should give you the desired effect and should be a
>    pretty simple way to have caches without having to think about
>    concurrency. Of course, this only really works for small fixed-size
>    data that needs no destructors (i.e. no free()).
 
> b) Only provide the caching in the main thread, and be un-cached
>    expensive in all others. This is slightly less nice, but effectively
>    gives you the same properties for systemd's own code. We have a call
>    in util.c to detect if we are running in the main thread:
>    is_main_thread().

I understand the constraints. My hardware (like most older ARM cores)
doesn't have a dedicated HW register for TLS. So I would like to avoid
any usage of threading. What is the argument against caching it inside
the application layer? E.g. is it fair to assume that journald will be
launched once systemd has created the cgroup?

I will try to get a perf report of the current journald. Cross-platform
perf report was broken the last time I tried.. maybe it has been fixed
since then. :}


holger