[Pw_forum] How to handle with the I/O wait

[vega lew]

Dear all,

First thank you all again to spend a lot time reading my mail, dealing with my questions, and giving me so much help. It's meanful for my resarch work.

Paolo said "if a process is not running close to 100%, it is either swapping, or waiting for I/O, or for memory access, or for the CPU. This remind me the case of CASTEP. CASTEP is so good a software, but it more suitable for commercial use. So I gived it up. According to many high quality scientific paper such as nature materials Journal of the American Society, Q-E is the best choice for academic using.

According to my CASTEP experiences, I think swapping is due to either lacking of memory or settings of the job. CASTEP can run in speed option or momory option. In speed mode, calculation will cost relative high memory but faster, while memory mode, the calculation will cost additional I/O to the hard-disk with much slower run. Does Q-E has the same function? I wonder whether the disk_io and verboity command in &CONTROL section has the similar function as CASTEP does? Where could I find the detail explaination of all the command in Q-E? I can't find the document with all the command illustrated. Where is it?

Also ccording to my CASTEP experiences, if the temporary file is stored in a NFS space, it will suffer a lot from I/O data and result in a long time of CPU waiting. The best CASTEP I/O wait percentage showed by 'sar' command is about 0.01. But the Q-E is about 0.20 and 0.30 occasionally, I think this probably the reason for less efficiency. 

Another thing I want to ask is how to place the temporary file correctly. There are two types of temporary file,outdir and wfcdir. Which one should be placed at NFS space for all the node can read and write? Which one should be placed at local disk to avoid additional unnecessary communication I/O data via network. Some temporary data is very important for further analysis such as DOS, pDOS, Charge et al. Whether I set the wf_collect=yes in &CONTROL the information for DOS,pDOS, Charge won't be lost? All the information for DoS analysis et al. is in the folder of ~/outdir/prefix.save/?

best wishes,

Vega Lew
PH.D Candidate in Chemical Engineering
State Key Laboratory of Materials-oriented Chemical Engineering
College of Chemistry and Chemical Engineering
Nanjing University of Technology, 210009, Nanjing, Jiangsu, China
_________________________________________________________________
Discover the new Windows Vista
http://search.msn.com/results.aspx?q=windows+vista&mkt=en-US&form=QBRE
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.quantum-espresso.org/pipermail/users/attachments/20080627/69cf49d6/attachment.html>