This is the mail archive of the
glibc-bugs@sourceware.org
mailing list for the glibc project.
[Bug malloc/21273] insufficient memory with more then 10 GB free memory
- From: "carlos at redhat dot com" <sourceware-bugzilla at sourceware dot org>
- To: glibc-bugs at sourceware dot org
- Date: Fri, 05 May 2017 18:27:40 +0000
- Subject: [Bug malloc/21273] insufficient memory with more then 10 GB free memory
- Auto-submitted: auto-generated
- References: <bug-21273-131@http.sourceware.org/bugzilla/>
https://sourceware.org/bugzilla/show_bug.cgi?id=21273
Carlos O'Donell <carlos at redhat dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |carlos at redhat dot com
--- Comment #4 from Carlos O'Donell <carlos at redhat dot com> ---
(In reply to Adhemerval Zanella from comment #3)
> As for comment #2 neither comment added any useful information to indicate
> it might either be a glibc issue or any way to try reproduce or pinpoint any
> possible issue. If you indeed have any information indicating a glibc issue
> (backtrace, testcase, etc.), please open a new bug or reopen issue.
I would also note that firefox uses a jemalloc fork (mozjemalloc) and so
interfaces directly with the OS for memory requests. This allows the browser to
more carefully tailor their memory allocation needs to the allocator, with more
apriori information about the allocation patterns you can usually do better
than a generic allocator.
The Fedora 25 chromium build does appear to use the system memory allocator,
and so would be an interesting candidate for analysis if it is indeed causing
the system to run out of memory.
Java similarly doesn't use glibc's malloc, instead it has it's own garbage
collection and AFAIK uses mmap directly for most of these uses.
So it looks like none of these problems are related to userspace, but instead
might be related to kernel issues around virtual memory utilization.
We need a lot more information which is why this is currently closed
RESOLVED/INVALID.
--
You are receiving this mail because:
You are on the CC list for the bug.