This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: pthread wastes memory with mlockall(MCL_FUTURE)
- From: Rich Felker <dalias at libc dot org>
- To: Balazs Kezes <rlblaster at gmail dot com>
- Cc: libc-alpha at sourceware dot org
- Date: Mon, 21 Sep 2015 13:44:43 -0400
- Subject: Re: pthread wastes memory with mlockall(MCL_FUTURE)
- Authentication-results: sourceware.org; auth=none
- References: <20150918143824 dot GB17773 at brightrain dot aerifal dot cx> <20150918163842 dot GB27881 at eper> <20150918170853 dot GC17773 at brightrain dot aerifal dot cx> <20150918192952 dot GC27881 at eper> <20150918194521 dot GD17773 at brightrain dot aerifal dot cx> <20150918201101 dot GD27881 at eper> <20150918232246 dot GF17773 at brightrain dot aerifal dot cx> <20150920132712 dot GA7569 at eper> <20150920233221 dot GP17773 at brightrain dot aerifal dot cx> <20150921174123 dot GB7569 at eper>
On Mon, Sep 21, 2015 at 06:41:23PM +0100, Balazs Kezes wrote:
> On 2015-09-20 19:32 -0400, Rich Felker wrote:
> > You're still adding a new mprotect rather than just inverting the one
> > that's already there (somewhere else) adding the PROT_NONE for the
> > guard page. Is there a reason this is hard to do right on glibc?
>
> Even if I manage to fix it properly (hah, I wish!) I won't be able to
> test it as I lack the various hardware this function supports. I've
> opened a bug instead so that more experienced people pick this up:
>
> https://sourceware.org/bugzilla/show_bug.cgi?id=18988
>
> Thanks!
Thanks! This looks like the best approach to get some more attention
on it from people who might have better ideas for what a fix would
look like.
Rich