[dm-devel] Thoughts on removing the remap cache

[FUJITA Tomonori]

From: Dan Smith <danms at us.ibm.com>
Subject: [dm-devel] Thoughts on removing the remap cache
Date: Fri, 29 Sep 2006 14:36:58 -0700

> However, all of my tests up until now have been with dbench.  I think
> that dbench works well in cases where latency is high, which is of
> course the case since we're sending all requests to userspace.  When I
> try to boot a Xen domU with root on dm-userspace (without the
> caching), it is *painfully* slow.  I assume this is because the domU
> boot is doing a lot of synchronous, sequential operations.
> 
> Since domU performance was good when I was caching mappings in the
> kernel, I would assume that the difference in performance is related
> to the caching.

I guess that dbench generates relatively large size I/Os than common
workloads, which is more sensitive to latency.

Seems that Xen camp is pretty happy with blktap. So dm-userspace
should be ok with domU. Maybe it's time to try ring buffer stuff
again. :)

Ok, I'll salvage and update the old patch, post a new patch compatible
with the current code.