Kernel fix stops /proc maps from skipping live VMAs under load
A race in the per-VMA-locked maps walk could omit address ranges that stayed mapped for the entire read.
By oopsA race in the per-VMA-locked maps walk could omit address ranges that stayed mapped for the entire read.
By oopsHuang Shijie reports a 50% Hadoop speedup on a 384-CPU Hygon system after the global procfs inode lock fell from a 90% hotspot to about 1%.
By kexec