possible for sysctl variables calculated dynamically?

[enihcam]

is it possible for sysctl variables to be calculated dynamically based on current context (e.g. cpu load, num of running threads, priority distribution, etc accounting)? For

• squeeze the max perf out
• user (non-geek) friendly

[ptr1337]

Benchmark them after applying.

These are settings which i use right now:

 ## Cacule-Settings - these are default values ##
kernel.sched_interactivity_factor=65536

##Network-Settings
net.core.netdev_max_backlog = 16384
net.core.somaxconn = 8192
net.core.rmem_default = 1048576
net.core.rmem_max = 16777216
net.core.wmem_default = 1048576
net.core.wmem_max = 16777216
net.core.optmem_max = 65536
net.ipv4.tcp_rmem = 4096 1048576 2097152
net.ipv4.tcp_wmem = 4096 65536 16777216
net.ipv4.udp_rmem_min = 8192
net.ipv4.udp_wmem_min = 8192
net.ipv4.tcp_fastopen = 3
net.ipv4.tcp_keepalive_time = 60
net.ipv4.tcp_keepalive_intvl = 10
net.ipv4.tcp_keepalive_probes = 6
net.ipv4.conf.default.log_martians = 1
net.ipv4.conf.all.log_martians = 1
net.ipv4.tcp_mtu_probing = 1
net.ipv4.tcp_syncookies = 1
net.core.default_qdisc = cake
net.ipv4.tcp_congestion_control = bbr2
vm.swappiness=1
kernel.nmi_watchdog = 0

[hamadmarri]

is it possible for sysctl variables to be calculated dynamically based on current context (e.g. cpu load, num of running threads, priority distribution, etc accounting)? For

* squeeze the max perf out

* user (non-geek) friendly

Hi @enihcam

Yes, sysctl is just a through gate to pass a user space values to kernel variables (both direction r/w). So yes, we can adjust those variables in the kernel. Do you have any formula to dynamically adjust some sysctl variables?

By the way, the linux kernel/scheduler has already many dynamically changed variables based on many factors.

Thanks