On Sat, May 11, 2024 at 12:54:18AM -0400, Waiman Long wrote: > I had suggested in the past to have a sysctl parameter to set a threshold on > how many negative dentries (as a percentage of total system memory) are Yes, but that's obviously bogus. System memory is completely uncorrelated with the optimum number of negative dentries to keep around for workload performance. Some multiple of "number of positive dentries" might make sense.
