Paper: Mind the Gap: Reconnecting Architecture and OS Research

Mind the Gap: Reconnecting Architecture and OS Research is a paper presented at HotOS XIII, the place where researchers talk about making potential futures happen. For a great overview of the conference take a look at this article by Matt Welsh: Conference report: HotOS 2011 in Napa.

In the VM/cloud age I question the need of having an OS at all, programs can compile directly against "raw" hardware, but the paper does a good job of trying to figure out the new roll operating systems can play in the future. We've been in a long OS holding pattern, so long that we've seen the rise of PaaS vendors skipping the OS level abstraction completely, but there's room for a middle ground between legacy time sharing systems of the past and service level APIs that are but one possible future.


For too long, operating systems researchers and developers have pretty much taken whatever computer architects have dished out. With occasional exceptions (e.g., virtualization support), architecture researchers do not appear to have sought or encouraged innovations that would improve the execution environment for an OS. Even worse, many do not bother to simulate and report on OS behavior when evaluating their proposals.
Times have changed: architects are running out of new ideas that lead to significant application-level performance improvements; we must now rely on improved parallelism. But parallelism stresses the very issues that operating systems research has focused on: distribution, resource management, I/O, etc. Also, many modern applications spend significant execution time in OS functions; it really does matter whether a CPU works well on OS code. We believe that closer collaboration between OS and architecture researchers could yield real benefits.
Alas, the disconnect between OS and architectural research seems to be growing, at a time when we should be trying to shrink it. In this paper, we discuss some problems arising from this gap, try to identify its causes, and consider ways to bridge it. We illustrate our discussions with examples drawn from recent OS research.