Redis server crash caused by jemalloc library bug.
Severe. But only crashes one server. As long as there are HA solutions shouldn’t be a big problem.
Standard (but run on a 32-bit OS)
1. Create a large db that will be larger than 4GB (the addr space)
2. Observe the crash
Irrelevant --- jemalloc will randomly crash memory once the usage is larger than the addr space.
Yes. But noisy.
This is very hard to diagnose. The developer ended up asking all the user logs.
jemalloc (freebsd malloc library) randomly corrupt memory once the usage is greater than addr space.
Incorrect error handling (in jemalloc library)
Fix it by configuration.