4.3.3. Determining Time Spent in Kernel and User Space
Ce contenu n'est pas disponible dans la langue sélectionnée.
4.3.3. Determining Time Spent in Kernel and User Space
This section illustrates how to determine the amount of time any given thread is spending in either kernel or user-space.
thread-times.stp
#! /usr/bin/env stap
probe perf.sw.cpu_clock!, timer.profile {
// NB: To avoid contention on SMP machines, no global scalars/arrays used,
// only contention-free statistics aggregates.
tid=tid(); e=execname()
if (!user_mode())
kticks[e,tid] <<< 1
else
uticks[e,tid] <<< 1
ticks <<< 1
tids[e,tid] <<< 1
}
global uticks, kticks, ticks
global tids
probe timer.s(5), end {
allticks = @count(ticks)
printf ("%16s %5s %7s %7s (of %d ticks)\n",
"comm", "tid", "%user", "%kernel", allticks)
foreach ([e,tid] in tids- limit 20) {
uscaled = @count(uticks[e,tid])*10000/allticks
kscaled = @count(kticks[e,tid])*10000/allticks
printf ("%16s %5d %3d.%02d%% %3d.%02d%%\n",
e, tid, uscaled/100, uscaled%100, kscaled/100, kscaled%100)
}
printf("\n")
delete uticks
delete kticks
delete ticks
delete tids
}
#! /usr/bin/env stap
probe perf.sw.cpu_clock!, timer.profile {
// NB: To avoid contention on SMP machines, no global scalars/arrays used,
// only contention-free statistics aggregates.
tid=tid(); e=execname()
if (!user_mode())
kticks[e,tid] <<< 1
else
uticks[e,tid] <<< 1
ticks <<< 1
tids[e,tid] <<< 1
}
global uticks, kticks, ticks
global tids
probe timer.s(5), end {
allticks = @count(ticks)
printf ("%16s %5s %7s %7s (of %d ticks)\n",
"comm", "tid", "%user", "%kernel", allticks)
foreach ([e,tid] in tids- limit 20) {
uscaled = @count(uticks[e,tid])*10000/allticks
kscaled = @count(kticks[e,tid])*10000/allticks
printf ("%16s %5d %3d.%02d%% %3d.%02d%%\n",
e, tid, uscaled/100, uscaled%100, kscaled/100, kscaled%100)
}
printf("\n")
delete uticks
delete kticks
delete ticks
delete tids
}
Copy to ClipboardCopied!Toggle word wrapToggle overflow
thread-times.stp lists the top 20 processes currently taking up CPU time within a 5-second sample, along with the total number of CPU ticks made during the sample. The output of this script also notes the percentage of CPU time each process used, as well as whether that time was spent in kernel space or user space.
Nous aidons les utilisateurs de Red Hat à innover et à atteindre leurs objectifs grâce à nos produits et services avec un contenu auquel ils peuvent faire confiance. Découvrez nos récentes mises à jour.
Rendre l’open source plus inclusif
Red Hat s'engage à remplacer le langage problématique dans notre code, notre documentation et nos propriétés Web. Pour plus de détails, consultez le Blog Red Hat.
À propos de Red Hat
Nous proposons des solutions renforcées qui facilitent le travail des entreprises sur plusieurs plates-formes et environnements, du centre de données central à la périphérie du réseau.