OpenSearch/server
Jason Tedor a36543531b
Fix race in clear scroll (#31259)
Here is the problem: if two threads are racing and one hits a failure
freeing a context and the other succeeded, we can expose the value of
the has failure marker to the succeeding thread before the failing
thread has had a chance to set the failure marker. This is a problem if
the failing thread counted down the expected number of operations, then
be put to sleep by a gentle lullaby from the OS, and then the other
thread could count down to zero. Since the failing thread did not get to
set the failure marker, the succeeding thread would respond that the
clear scroll succeeded and that makes that thread a liar. This commit
addresses by first setting the failure marker before we potentially
expose its value to another thread.
2018-06-12 10:17:41 -04:00
..
licenses Upgrade to Lucene-7.4.0-snapshot-0a7c3f462f (#31073) 2018-06-04 14:18:46 -04:00
src Fix race in clear scroll (#31259) 2018-06-12 10:17:41 -04:00
build.gradle Build: Split distributions into oss and default 2018-04-20 15:33:57 -07:00