Tested-by: Jiri Wiesner <jwiesner@xxxxxxx> Reviewed-by: Jiri Wiesner <jwiesner@xxxxxxx> Not an rlimit anymore. To avoid the magic number - 4, a symbolic constant could be used. The 4 is related to th
Yes, a cache factor of 4 happens to be a good compromise on this particular Zen 1 machine. I am not sure if I copied the right messages from the log. Probably not. Absolutely. -- Jiri Wiesner SUSE La
Hello, So, 12 tests and 3 20ms gaps eliminate any cpufreq issues in most of the cases and we do not see small chain_max value. Looks like cache_factor of 4 is good both to ondemand which prefers cach
I was testing the stability of chain_max: Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz 64 CPUs, 2 NUMA nodes Chain_max was often 30-something. Chain_max was never below 30, which was observed earlier whe
Estimating all entries in single list in timer context causes large latency with multiple rules. Spread the estimator structures in multiple chains and use kthread(s) for the estimation. Every chain