Some ideas, like Ron Paul's crusade to end monopolies on money, have such a stark simplicity and obvious utility that they continue to cling to the collective consciousness of anyone who has read them.  Plan 9 is one of those ideas.  As we all know (or don't as is the point in this case), Plan 9 got a few Dilbert cartoons, made its point and went off to pasture.  My opinion is that this is mostly because it wasn't open-sourced properly by Bell Labs at the start, and that at present, running the OS is not so important anyway with 9P network protocol bindings available for most languages.  However, it was sad to see IL go.  Overall, I think the trick is less about knowing when to fold, but more about knowing 1) how to market, 2) when to `part-out' an old idea, and 3) when to develop hyperopia and keep pushing on what seems like a dead-end to the unenlightened.

I wrote a little more about Plan 9 in my additions to the go9p library:

  9P is the network protocol used by the mythical Plan9 operating system.  The big idea is that all resources, networked or local, can be represented as read/write  operations on named hierarchies of objects.  Accessing those should be just as easy as  accessing a file, and it shouldn't make any difference if the file represents a local  or remote resource.  For modern re-inventions of this, see REST API design and FUSE.  Although revolutionary in its scope, the OS was not initially released open  source and required some effort in porting existing software, hindering  widespread adoption.  Its relatively small following led Eric S. Raymond, one of its more vocal  designers, to lament that "the most dangerous enemy of a better solution is an existing  codebase that is just good enough."

  After the decision to leave the personal computer and Unix networked server markets in 1996, AT&T divested the National Cash Register Corporation and spun-off Bell Labs as Lucent Technologies, Lucent gave Plan9 a back-seat and development slowly declined.  In 2002, Lucent made its last (4th edition) release of the Plan9 OS.  Interestingly, this nearly coincides with the date that Rob Pike moved from Lucent to Google.  Its major issue is the lack of support for most hardware.  It spewed some random garbage and ground to a halt when I tried to boot it on my AMD 2700-based system.

  In 2011, a fork (9front) of the slowly developing v4 was made to allow faster development, addition of new hardware support, and a re-write of the fossil filesystem to the "Cached Write Once Read Many Filesystem."  All I know is that this one did boot on my (ca. 2002) hardware.