Tony Hutter

So I just tried `zpool offline -f` again, and it did activate the spare. Then I rebooted my VM, tried it again, and it didn't activate the spare. I'll need...

I suspect what we really need is a "test spare activation after a drive has disappeared" test case. The current test cases just test faults via injecting IO/checksum errors. @AeonJJohnson...

I'm interested in this. I'm currently blocking on writing a test case for buildbot because my test calls `describe_spot_price_history`: https://github.com/buildbot/buildbot/pull/5401#issuecomment-675762309

I'm working on implementing this - once it's usable I'll put together a PR.

I'm dusting this off again. Ultimately what I'd like to do is change `describe_spot_instance_requests()'s` status to first report `pending-evaluation` the first time you call `describe_spot_instance_requests()`, and then have it report...

@spulec please re-open this issue

So I've finally had some time to fully review the API doc and the comments in this issue. I'll first go over the comments and then I'll go over what...

> Currently, the primary use case for this client API is embedding in other libraries, like HDF5. We have had several conversations with the HDF5 team about different non-POSIX behaviors...

Good points. Ok, so then let's explicitly require fsync(), even for the single writer case, so that people know it has to be done (and to simplify the code).

Random thought while reading this thread: In addition to the things already discussed, should we also consider optimistically syncing seg_tree extents in the background? That way, when they do call...