Red Hat NETWORK WORKGROUP - USER 1.0 Instalační příručka stáhnout pdf (Strana 44)

22 007-5680-001

3: SGI Peformance Suite Products Overview

Note: Performance tuning information for single processor and multiprocessor

programs resides in Linux Application Tuning Guide.

dlook Command

Thedlook(1) commanddisplaysthememorymap andCPU useforaspeciﬁedprocess.

The following information is printed for each page in the virtual address space of the

process:

• The object that owns the page (ﬁle, SYSV shared memory, device driver, and so on)

• Type of page (RAM, FETCHOP, IOSPACE, and so on)

• If RAM memory, the following information is supplied:

– Memory attributes (SHARED, DIRTY, and so on)

– Node on which that the page is located

– Physical address of page (optional)

Optionally, the amount of elapsed CPU time that the process has executed on each

physical CPU in the system is also printed.

dplace Command

The dplace(1) command binds a related set of processes to speciﬁc CPUs or nodes to

preventprocessmigrations.Insomecases,thistoolimprovesperformancebecauseofthe

occurrence of a higher percentage of memory accesses to the local node.

taskset Command

Thetaskset(1)command isusedto setorretrievetheCPUafﬁnityofarunningprocess

given its PID or to launch a new command with a given CPU afﬁnity. CPU afﬁnity is a

scheduler property that "bonds" a process to a given set of CPUs on the system. The

Linux scheduler will honor the given CPU afﬁnity and the process will not run on any

other CPUs. Note that the Linux scheduler also supports natural CPU afﬁnity; the

scheduler attempts to keep processes on the same CPU as long as practical for

1 2 ... 39 40 41 42 43 44 45 46 47 48

Žádné komentáře

Red Hat NETWORK WORKGROUP - USER 1.0 Instalační příručka Strana 44