Thread (71 messages) 71 messages, 13 authors, 2011-05-11

Re: [BUG] fatal hang untarring 90GB file, possibly writeback related.

From: James Bottomley <hidden>
Date: 2011-05-06 15:58:12
Also in: linux-ext4, linux-fsdevel, lkml

On Fri, 2011-05-06 at 08:42 +0100, Mel Gorman wrote:
[...]
Will try tests and post results
Out of curiousity, what's the exact machine you are testing on
because I want to see what sort of hardware combination triggers
this problem? Is the tar local or is it copied over NFS? What is the
configuration of the disk or partition you are copying to?
It's a Lenovo T420s with 2GB of memory.  It's core i5, so it has two
cores each with two threads, so it emulates a 4 cpu system.  It's
running Fedora 15 Beta, so the 2.6.38.4 kernel (although I've tried the
default 2.6.38.5 as well, since the fedora i915 updates are a bit
unstable).  I'm also booting 2.6.39-rc on it (with and without PREEMPT).
The standard Fedora config is SLUB.  Because it's FC15, it has all of
the cgroups stuff enabled for systemd.

Just in case, I've attached the FC15 config ... I modify it slightly for
2.6.39-rc but since the bug shows up in standard FC15, that should be
enough.

James

Attachments

Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help