[illumos-Developer] Important - time sensitive: Drive failures and infinite waits

[Dan McDonald]

On Fri, May 27, 2011 at 11:14:20PM +0400, Garrett D'Amore wrote:

> It does.  One type of problem is a drive that does not hard fail but
> manages to limp along doing a request or two per second.  We dont have a
> good defense for this at present.  (Internal retry logic in the drives make
> this harder too.)

This sounds like a variant on the pitfalls of running TCP over IP over TCP
(e.g. SSL tunnelling).  One feedback handler compromises the higher-layer
feedback handler.

ObBlogEntry:

	http://blogs.oracle.com/sommerfeld/entry/the_end_to_end_argument

(I'm sure Bill will be pleased his old Sun blog now lives in Oracle-space.)

Dan