Hi,
habe noch was interessantes rausgefunden:
top - 14:02:47 up 185 days, 20:36, 4 users, load average: 13.07, 16.20, 16.99
Tasks: 212 total, 1 running, 210 sleeping, 0 stopped, 1 zombie
Cpu0 : 1.9%us, 1.9%sy, 0.0%ni, 96.1%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu1 : 0.0%us, 0.0%sy, 0.0%ni, 0.0%id,100.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu2 : 0.0%us, 0.0%sy, 0.0%ni, 0.0%id,100.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu3 : 0.0%us, 0.0%sy, 0.0%ni, 0.0%id,100.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu4 : 0.0%us, 0.0%sy, 0.3%ni, 0.0%id, 99.7%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu5 : 0.0%us, 0.0%sy, 0.0%ni, 0.0%id,100.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu6 : 0.0%us, 0.3%sy, 0.0%ni, 0.0%id, 99.7%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu7 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 72498M total, 32726M used, 39772M free, 249M buffers
Swap: 2046M total, 4M used, 2042M free, 28916M cached
6 Kerne scheinen durch Warten auf IO total ausgebremst zu sein. Nur zwei Kerne sind haben nix zu tun.
Wenn ich aber nun CPU-intensive Prozesse starte (cat /dev/urandom > /dev/null), dann verschwindet die (scheinbare) IO-Last:
top - 14:07:50 up 185 days, 20:41, 4 users, load average: 14.63, 14.13, 15.75
Tasks: 224 total, 9 running, 214 sleeping, 0 stopped, 1 zombie
Cpu0 : 3.0%us, 0.3%sy, 0.0%ni, 96.7%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu1 : 0.0%us, 99.7%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.3%si, 0.0%st
Cpu2 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu3 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu4 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu5 : 2.6%us, 1.3%sy, 0.0%ni, 0.0%id, 96.1%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu6 : 0.3%us, 0.3%sy, 0.0%ni, 0.0%id, 99.3%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu7 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 72498M total, 32727M used, 39770M free, 249M buffers
Swap: 2046M total, 4M used, 2042M free, 28916M cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
4515 root 20 0 4304 556 468 R 100 0.0 2:27.30 cat
4973 root 20 0 4304 556 468 R 100 0.0 2:10.26 cat
4978 root 20 0 4304 556 468 R 100 0.0 2:08.83 cat
4979 root 20 0 4304 556 468 R 100 0.0 2:07.63 cat
5783 root 20 0 4304 556 468 R 100 0.0 1:17.52 cat
Es laufen 5 cat-Prozesse, jeder nutzt einen Kern zu 100%. Es scheinen aber nur noch zwei Kerne auf IO zu warten (CPU 5 und 6). Vorher waren es 6 Kerne. Wäre da wirklich IO, müsste sich das doch zu dem cat-Befehl addieren, oder ? Es scheint aber zu verschwinden !
Starte ich noch mehr cat-Prozesse (insg. 7), "verschwindet" immer mehr IO-Last:
top - 14:12:47 up 185 days, 20:46, 4 users, load average: 16.14, 15.10, 15.71
Tasks: 224 total, 9 running, 214 sleeping, 0 stopped, 1 zombie
Cpu0 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu1 : 3.3%us, 1.3%sy, 0.0%ni, 0.0%id, 95.4%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu2 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu3 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu4 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu5 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu6 : 0.3%us, 99.7%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu7 : 0.0%us,100.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 72498M total, 32728M used, 39770M free, 249M buffers
Swap: 2046M total, 4M used, 2042M free, 28916M cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
4978 root 20 0 4304 556 468 R 100 0.0 7:05.05 cat
4515 root 20 0 4304 556 468 R 100 0.0 7:23.26 cat
4973 root 20 0 4304 556 468 R 100 0.0 7:06.54 cat
4979 root 20 0 4304 556 468 R 100 0.0 7:03.89 cat
5783 root 20 0 4304 556 468 R 100 0.0 6:13.65 cat
11380 root 20 0 4304 556 468 R 100 0.0 0:36.48 cat
11379 root 20 0 4304 556 468 R 100 0.0 0:38.37 cat
Nur noch ein Kern (CPU 1) scheint mit Warten auf IO beschäftigt zu sein.
!?!
Bernd
Helmholtz Zentrum München
Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH)
Ingolstädter Landstr. 1
85764 Neuherberg
www.helmholtz-muenchen.de
Aufsichtsratsvorsitzende: MinDir´in Bärbel Brumme-Bothe
Geschäftsführer: Prof. Dr. Günther Wess, Dr. Nikolaus Blum, Dr. Alfons Enhsen
Registergericht: Amtsgericht München HRB 6466
USt-IdNr: DE 129521671
Rgbx�������ץ���r���҉碝��V������uﮞ˛���m�)z{.��+�I�zr��ק٢�+-��h�;����r���brG�