Re: [PATCH 0/4] (RESEND) ext3[34] barrier changes



Ric Wheeler wrote:
I will have to figure out to get this kind of test going without all
of my big EMC toys ;-)

Fwiw, you can test correctness by running a nested VM-in-VM guest
which simulates disk write cache and flush operations (which flush to
the host kernel). I believe recent QEMU/KVM has this as an option.
Data written by the innermost guest will reside in the middle kernel's
write cache.

Disk cache flush commands from the innermost kernel will cause the
middle kernel to write dirty sectors to the outer kernel. Killing the
outermost host process is roughly equivalent to pulling the plug on a
real machine, but faster and without hurting real hardware.

This might not tell you much about performance, but you should be able
to run a lot of repeatable filesystem barrier tests this way.

-- Jamie
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/



Relevant Pages

  • Re: USB mass storage and ARM cache coherency
    ... kernel alias for the page becomes dirty. ... don't handle I cache problems in the I/O or page cache code ... ... don't flush the icache for anonymous pages. ...
    (Linux-Kernel)
  • Re: USB mass storage and ARM cache coherency
    ... kernel alias for the page becomes dirty. ... OK, but the point I'm trying to make is that the page cache code, ... which look to be the result of some I flush race like this. ... user flush without a mapping. ...
    (Linux-Kernel)
  • Re: Scheduler: Process priority fed back to parent?
    ... > cache information about individual executables. ... > a daemon which stores it on disk in such a way ... > that the kernel can efficiently get at it. ... it looks at the cache for interactivity history to estimate ...
    (Linux-Kernel)
  • Re: Scheduler: Process priority fed back to parent?
    ... There would have to be some sort of cache. ... > The kernel already does disk access to load a process... ... > would be an artificial one which always exists for this, or the priority ...
    (Linux-Kernel)
  • Test program with VM or FS problems
    ... The attached program implements an external sort algorithm. ... around on disk. ... the cache is working as well as it could be. ... For example, I have a laptop with 288M of ram, running the kernel ...
    (Linux-Kernel)