Messages in this thread | | | From | Chris Mason <> | Subject | Re: hunt for 2.6.37 dm-crypt+ext4 corruption? (was: Re: dm-crypt barrier support is effective) | Date | Thu, 16 Dec 2010 07:29:58 -0500 |
| |
Excerpts from Dave Chinner's message of 2010-12-15 22:37:18 -0500: > On Wed, Dec 08, 2010 at 07:20:24AM -0500, Chris Mason wrote: > > > > Usually the trick to reproducing filesystem corruptions is adding memory > > pressure. The corruption is probably a bad interaction between reads > > and writes, and we need to make sure the reads actually happen. > > > > http://oss.oracle.com/~mason/pin_ram.c > > > > gcc -Wall -o pin_ram pin_ram.c > > > > pin_ram -m 80%-of-your-ram-in-mb > > Implemented in xfstests about 10 years ago: > > http://git.kernel.org/?p=fs/xfs/xfstests-dev.git;a=blob;f=src/usemem.c;h=b8794a6b209cebf8dbf312a8ef131e2e54b18d29;hb=HEAD
But mine can use shm! I don't remember adding it, so it must have grown there while it sat on the oracle servers. Our own special Christmas magic.
-chris
| |