It seems that you provided wrong information:<br><br>1. You shown only 8 CPUs. Where are the other 8 as you were talking about 16 CPUs job.<br>2. There is only one task actually running ( PID 4404, run as root)<br>3. There's absolutely no other thing running in this node.<br>
<br>My guess is that you took those information from wrong node, probably from head node. <br><br>:) <br><br><div class="gmail_quote">2009/9/11 Giovanni Cantele <span dir="ltr"><<a href="mailto:Giovanni.Cantele@na.infn.it">Giovanni.Cantele@na.infn.it</a>></span><br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div><div></div><div class="h5">wangqj1 wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Dear pwscf users<br>
I use 16 CPUs to run a job,but the usage of CPUs is very slow ,it as like:<br>
Tasks: 179 total, 1 running, 178 sleeping, 0 stopped, 0 zombie<br>
Cpu0 : 0.0%us, 4.8%sy, 0.0%ni, 90.3%id, 0.3%wa, 0.0%hi, 4.5%si, 0.0%st<br>
Cpu1 : 0.0%us, 1.0%sy, 0.0%ni, 95.8%id, 3.3%wa, 0.0%hi, 0.0%si, 0.0%st<br>
Cpu2 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st<br>
Cpu3 : 0.7%us, 0.0%sy, 0.0%ni, 99.0%id, 0.3%wa, 0.0%hi, 0.0%si, 0.0%st<br>
Cpu4 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st<br>
Cpu5 : 0.0%us, 0.3%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st<br>
Cpu6 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st<br>
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<br>
Mem: 8048812k total, 7995856k used, 52956k free, 283692k buffers<br>
Swap: 4192956k total, 124k used, 4192832k free, 7492420k cached<br>
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND<br>
4522 root 15 -5 0 0 0 S 5 0.0 17:59.16 nfsd<br>
2012 root 15 -5 0 0 0 S 1 0.0 6:29.01 kjournald<br>
4404 root 20 0 104m 17m 5044 S 0 0.2 55:07.93 X<br>
4519 root 15 -5 0 0 0 S 0 0.0 18:05.58 nfsd<br>
4521 root 15 -5 0 0 0 S 0 0.0 16:55.33 nfsd<br>
5023 gdm 20 0 235m 31m 11m S 0 0.4 13:39.99 gdm-simple-gree<br>
1 root 20 0 1064 408 348 S 0 0.0 0:02.90 init<br>
2 root 15 -5 0 0 0 S 0 0.0 0:00.02 kthreadd<br>
3 root RT -5 0 0 0 S 0 0.0 0:00.00 migration/0<br>
4 root 15 -5 0 0 0 S 0 0.0 0:00.22 ksoftirqd/0<br>
<br>
The ifort ,MKL,and mpi I used is :<br>
INTFC=/opt/intel/Compiler/11.0/081<br>
INTMKL=/opt/intel/mkl/<a href="http://10.1.1.019" target="_blank">10.1.1.019</a><br>
/opt/mpich2/bin/mpd<br>
My machine model is as following :<br>
processor : 0<br>
vendor_id : GenuineIntel<br>
cpu family : 6<br>
model : 23<br>
model name : Intel(R) Xeon(R) CPU E5410 @ 2.33GHz<br>
stepping : 10<br>
cpu MHz : 2327.489<br>
cache size : 6144 KB<br>
physical id : 0<br>
siblings : 4<br>
core id : 0<br>
cpu cores : 4<br>
apicid : 0<br>
initial apicid : 0<br>
fpu : yes<br>
fpu_exception : yes<br>
cpuid level : 13<br>
wp : yes<br>
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov<br>
pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant<br>
_tsc arch_perfmon pebs bts rep_good nopl pni monitor ds_cpl vmx est tm2 ssse3 cx<br>
16 xtpr dca sse4_1 lahf_lm<br>
bogomips : 4654.97<br>
...............<br>
The pwscf version is espresso-4.0.3 .<br>
So , I want to know why the usage is so slow ?<br>
How can I solve this problem ? Anybody who meet the same problem ?<br>
Your kind help will be appreciated !<br>
Best regards<br>
Q.J.Wang<br>
XiangTan University<br>
<br>
</blockquote></div></div>
Some possibilities are:<br>
<br>
1) <a href="http://www.quantum-espresso.org/wiki/index.php/Frequently_Asked_Questions#Why_is_my_parallel_job_running_in_such_a_lousy_way.3F" target="_blank">http://www.quantum-espresso.org/wiki/index.php/Frequently_Asked_Questions#Why_is_my_parallel_job_running_in_such_a_lousy_way.3F</a><br>
2) you are running a job over a very slow network (interconnecting the different nodes)<br>
3) you are trying to force a node to write on a disk which is local to other nodes and connected to it<br>
through a very-low performance network<br>
4) your job requests much more resources than you have, e.g. RAM memory (causing a node to swap). From<br>
your data it seems you are using all the 8Gb mem, actually the same test should be done on every node.<br>
<br>
<br>
How are distributed the 16 CPU? Over more than one node?<br>
<br>
Giovanni<br>
<br>
-- <br>
<br>
<br>
<br>
Dr. Giovanni Cantele<br>
Coherentia CNR-INFM and Dipartimento di Scienze Fisiche<br>
Universita' di Napoli "Federico II"<br>
Complesso Universitario di Monte S. Angelo - Ed. 6<br>
Via Cintia, I-80126, Napoli, Italy<br>
Phone: +39 081 676910<br>
Fax: +39 081 676346<br>
E-mail: <a href="mailto:giovanni.cantele@cnr.it" target="_blank">giovanni.cantele@cnr.it</a><br><font color="#888888">
<a href="mailto:giovanni.cantele@na.infn.it" target="_blank">giovanni.cantele@na.infn.it</a><br>
Web: <a href="http://people.na.infn.it/%7Ecantele" target="_blank">http://people.na.infn.it/~cantele</a><br>
Research Group: <a href="http://www.nanomat.unina.it" target="_blank">http://www.nanomat.unina.it</a><br>
Skype contact: giocan74<br>
<br>
</font><br>_______________________________________________<br>
Pw_forum mailing list<br>
<a href="mailto:Pw_forum@pwscf.org">Pw_forum@pwscf.org</a><br>
<a href="http://www.democritos.it/mailman/listinfo/pw_forum" target="_blank">http://www.democritos.it/mailman/listinfo/pw_forum</a><br>
<br></blockquote></div><br><br clear="all"><br>-- <br>--------------------------------------------------<br>Duy Le<br>PhD Student<br>Department of Physics<br>University of Central Florida.<br>