[Gluster-devel] Multiplexing status, January 24
jdarcy at redhat.com
Wed Jan 25 03:46:39 UTC 2017
Coming down to the wire here. Here's the latest.
With the latest patchset (61!) I've addressed most of people's review comments. I've also put a dent in the last functional area, which is full support for snapshots. Previously, snapshot bricks were exempt from multiplexing even if it was otherwise enabled. Now, basic snapshot operations seem to work, but clones and USS still need some work. The biggest obstacle is actually *shutting down* snapshot bricks. Some as-yet-unidentified translator is keeping the brick mountpoint alive, even when we try to unmount it. This causes failures near the end of some snapshot tests if multiplexing is enabled. I'll investigate that, along with two other lesser issues:
* A better way to enable/disable multiplexing (Vijay and Samikshan both have patches)
* Some way to set multiplexing levels/policies for performance testing.
IMO this code is very close to being finished, except for one thing: our regression tests. Dozens upon dozens of times, regression tests have failed in our test infrastructure even though they have worked and continue to work reliably on a regular test machine. I've addressed a lot of these - the patch fixes or disables 33 tests - but more pop up all the time. The simple fact is that many of our tests make timing or other assumptions that were never really valid, but those assumptions were violated rarely enough that the tests would pass anyway most of the time. With multiplexing, many of those assumptions are even less often true, so tests fail on a more regular basis. Going forward, it's going to be more important than ever that people flag spurious regression-test failures as such. I'll certainly be doing so, and "encouraging" test owners to participate in fixing their tests.
More information about the Gluster-devel