My initial reaction to reading that Linux 7.0 had halved PostgreSQL performance was that the kernel team had broken userspace and would revert it. Then I read this:
“The fix here is to make PostgreSQL make use of rseq slice extension: lkml.kernel.org/r/2025121… That should limit the exposure to lock holder preemption (unless PostgreSQL is doing seriously egregious things)."
So if that stands and shifting the blame to PostgreSQL, Linux 7.0 stable could lead to a significant drop for PostgreSQL performance in some scenarios until that popular database server is updated.
There’s always tension between long-term architectural decisions and the needs of users. But this isn’t shifting the blame, it’s assigning the responsibility. Linux 7.0 is a new major version. PostgreSQL gets to decide what that means for their project.
