climateprediction.net (CPDN) home page
Thread 'What is the name of a checkpoint file (especially hadam4h)?'

Thread 'What is the name of a checkpoint file (especially hadam4h)?'

Questions and Answers : Unix/Linux : What is the name of a checkpoint file (especially hadam4h)?
Message board moderation

To post messages, you must log in.

AuthorMessage
Jean-David Beyer

Send message
Joined: 5 Aug 04
Posts: 1120
Credit: 17,202,915
RAC: 2,154
Message 61435 - Posted: 31 Oct 2019, 12:40:01 UTC

I would like to look at checkpoint files. Actually, I do not wish to look at the content, but just size, time and date written, etc. What ls -l could tell me.

If I knew the name of it, the locate command could probably find it for me.
ID: 61435 · Report as offensive     Reply Quote
ProfileDave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 4540
Credit: 19,018,099
RAC: 20,856
Message 61436 - Posted: 31 Oct 2019, 13:58:26 UTC - in response to Message 61435.  

I would like to look at checkpoint files. Actually, I do not wish to look at the content, but just size, time and date written, etc. What ls -l could tell me.

If I knew the name of it, the locate command could probably find it for me.


Just been digging around, clicking on the task and then properties for the time of the last checkpoint is a clue but looking at one of mine, I am not sure that whichever one it is is the only file modified at that time as a number of files seem to be modified about the time of last checkpoint based on cpu time since it occurred. There are files modified both in the slots directory for the task and in the task directory.
ID: 61436 · Report as offensive     Reply Quote
Les Bayliss
Volunteer moderator

Send message
Joined: 5 Sep 04
Posts: 7629
Credit: 24,240,330
RAC: 0
Message 61437 - Posted: 31 Oct 2019, 14:49:47 UTC

Yes, there are lots of files in use for each model, which is why they need to be given time to be saved before shutting down.
ID: 61437 · Report as offensive     Reply Quote
Profilegeophi
Volunteer moderator

Send message
Joined: 7 Aug 04
Posts: 2187
Credit: 64,822,615
RAC: 5,275
Message 61438 - Posted: 31 Oct 2019, 16:51:35 UTC - in response to Message 61435.  

In the "boincdata"/projects/climateprediction.net directory, a file is written with the filename trickle_up_"rest of the filename". It is usually immediately uploaded, unless the communications with the project site has "backed off" because of a communication less than 60 minutes prior. When you know a trickle-up is not too far off, you can "Suspend Network Activity" from boinc manager so you can look at the file before it is uploaded.
ID: 61438 · Report as offensive     Reply Quote
Jean-David Beyer

Send message
Joined: 5 Aug 04
Posts: 1120
Credit: 17,202,915
RAC: 2,154
Message 61439 - Posted: 31 Oct 2019, 19:09:28 UTC - in response to Message 61438.  

In the "boincdata"/projects/climateprediction.net directory, a file is written with the filename trickle_up_"rest of the filename".


Trouble is, I do not wish to see the trickle_up files; I want to see the checkpoint files.
ID: 61439 · Report as offensive     Reply Quote
Profilegeophi
Volunteer moderator

Send message
Joined: 7 Aug 04
Posts: 2187
Credit: 64,822,615
RAC: 5,275
Message 61440 - Posted: 31 Oct 2019, 19:30:40 UTC - in response to Message 61439.  

Ahh, I didn't read that very well. Restart files are in the

boincDataDirectory/projects/climateprediction.net/"hadam4ModelName"/dataout

directory. Filename should be like atmos_restart.day
ID: 61440 · Report as offensive     Reply Quote
Jean-David Beyer

Send message
Joined: 5 Aug 04
Posts: 1120
Credit: 17,202,915
RAC: 2,154
Message 61441 - Posted: 31 Oct 2019, 21:56:26 UTC - in response to Message 61440.  

OK. Thank-you.

boinc[~/projects/climateprediction.net/hadam4h_a18g_201111_4_842_011906056/dataout]$ ls -l
total 475276
[snip]
-rw-r--r--. 1 boinc boinc 423837696 Oct 31 15:51 atmos_restart.day
-rw-r--r--. 1 boinc boinc     14173 Oct 31 15:51 shmem_restart.day
-rw-r--r--. 1 boinc boinc         0 Oct 30 16:27 xnnuj.err
-rw-r--r--. 1 boinc boinc    279754 Oct 31 17:53 xnnuj.out
-rw-r--r--. 1 boinc boinc     14100 Oct 31 15:51 xnnuj.phist
-rw-r--r--. 1 boinc boinc     14100 Oct 31 15:51 xnnuj.thist

ID: 61441 · Report as offensive     Reply Quote
Jean-David Beyer

Send message
Joined: 5 Aug 04
Posts: 1120
Credit: 17,202,915
RAC: 2,154
Message 61442 - Posted: 1 Nov 2019, 12:09:11 UTC - in response to Message 61441.  

$ locate atmos_restart.day
/home/boinc/projects/climateprediction.net/hadam4h_a0pg_200811_4_842_011905372/dataout/atmos_restart.day
/home/boinc/projects/climateprediction.net/hadam4h_a18g_201111_4_842_011906056/dataout/atmos_restart.day
/home/boinc/projects/climateprediction.net/hadcm3s_qg42_190012_240_837_011899288/dataout/atmos_restart.day
/home/boinc/projects/climateprediction.net/hadcm3s_qy57_190012_240_837_011900203/dataout/atmos_restart.day

On my machine, /home/boinc is a separate file system all its own.
$ df
Filesystem      1K-blocks      Used  Available Use% Mounted on
/dev/sdb5        48249720  15625144   30166976  35% /
/dev/sdb2          499656    115328     358116  25% /boot
/dev/sdb6        48249720   9864708   35927412  22% /home
/dev/sdd3       122908728   9562664  107095976   9% /home/boinc <---<<<
/dev/sdb8         3966144     19108    3742236   1% /tmp
/dev/sdb7        15995848   4110856   11065792  28% /var
...

ID: 61442 · Report as offensive     Reply Quote

Questions and Answers : Unix/Linux : What is the name of a checkpoint file (especially hadam4h)?

©2024 cpdn.org