Mago Study Notes-computer and operating system principles

Cache method:

Direct ing

N-link Association

Cache Policy:

Write Through: Write-through

Write back: Write back

Process type:

Interactive Process (IO-intensive)

Batch Processing (CPU-intensive)

Real-time process)

CPU: time segment, low priority
IO: short time slice, high priority

Linux priority: Priority

Real-time Priority: 1-99. The smaller the number, the lower the priority.

Static Priority: 100-139. The smaller the data size, the higher the priority.

Real-time priority is higher than static priority

Nice value: Adjust static priority-100,139:

PS-EO: displays the process with parentheses as the kernel thread.

Scheduling type:
Real-time process:
Sched_fifo: first in first out
Shced_rr: Round Robin
Sched_other: Used to schedule processes -.

Dynamic Priority:
Dynamic Priority = max (100, min (static priority-bonus + 5,139 ))
Bonus: 0-10

Manually adjust the priority:

100-139: Nice

Nice n command

Renice-N # PID

CHRT-P [PRIO] PID

1-99:

CHRT-F-P [PRIO] PID

CHRT-r-p [PRIO] PID

CHRT-F-P [PRIO] command

PS-e-o class, rtprio, PRI, nice, cmd

CFS (complete fair sched): completely fair scheduling

SMP: symmetric multiplexing

NUMA: Non-consistent Memory Access

CPU affinity: CPU affinity

Numastat
Numactl
Numad

Taskset: bind a process to a CPU

Mask: 0x0000 0001 (converted to binary, 1 indicates a CPU, starting from scratch)

Taskset-P mask PID

Taskset-p-C 0-2, 7 101

The interrupt should be bound to those non-isolated CPUs to avoid those isolated CPU processing interrupt programs:

Echo cpu_mask>/proc/IRQ/<IRQ Number>/smp_affinity