<html><body><p><font size="2">Along with what Fred wrote, you can look at the mmbackup doc and also peek into the script and find some options to look at the mmapplypolicy RULEs used, and also capture the mmapplypolicy output which will better show you which files and directories are being examined and so forth.<br></font><br><font size="2">--marc</font><br><br><img width="16" height="16" src="cid:1__=0ABB0E05DFDDB9B98f9e8a93df938690918c0AB@" border="0" alt="Inactive hide details for "Frederick Stock" ---10/17/2019 08:43:02 AM---Jonathan the "objects inspected" refers to the number o"><font size="2" color="#424282">"Frederick Stock" ---10/17/2019 08:43:02 AM---Jonathan the "objects inspected" refers to the number of file system objects that matched the policy</font><br><br><font size="2" color="#5F5F5F">From: </font><font size="2">"Frederick Stock" <stockf@us.ibm.com></font><br><font size="2" color="#5F5F5F">To: </font><font size="2">gpfsug-discuss@spectrumscale.org</font><br><font size="2" color="#5F5F5F">Cc: </font><font size="2">gpfsug-discuss@spectrumscale.org</font><br><font size="2" color="#5F5F5F">Date: </font><font size="2">10/17/2019 08:43 AM</font><br><font size="2" color="#5F5F5F">Subject: </font><font size="2">[EXTERNAL] Re: [gpfsug-discuss] mmbackup questions</font><br><font size="2" color="#5F5F5F">Sent by: </font><font size="2">gpfsug-discuss-bounces@spectrumscale.org</font><br><hr width="100%" size="2" align="left" noshade style="color:#8091A5; "><br><br><br><font face="Arial">Jonathan the "objects inspected" refers to the number of file system objects that matched the policy rules used for the backup. These rules are influenced by TSM server and client settings, e.g. the dsm.sys file. So not all objects in the file system are actually inspected.</font><br><font face="Arial"> </font><br><font face="Arial">As for tuning I think the mmbackup man page is the place to start, and I think it is thorough in its description of the tuning options. You may also want to look at the mmapplypolicy man page since mmbackup invokes it to scan the file system for files that need to be backed up.</font><br><font face="Arial"> </font><br><font face="Arial">To my knowledge there are no options to place the shadow database file in another location than the GPFS file system. If the file system has fast storage I see no reason why you could not use a placement policy rule to place the shadow database on that fast storage. However, I think using more than one node for your backups, and adjusting the various threads used by mmbackup will provide you with sufficient performance improvements.</font><br><br>Fred<br>__________________________________________________<br>Fred Stock | IBM Pittsburgh Lab | 720-430-8821<br>stockf@us.ibm.com<br><font face="Arial"> </font><br><font face="Arial"> </font><br><font face="Arial">----- Original message -----<br>From: Jonathan Buzzard <jonathan.buzzard@strath.ac.uk><br>Sent by: gpfsug-discuss-bounces@spectrumscale.org<br>To: "gpfsug-discuss@spectrumscale.org" <gpfsug-discuss@spectrumscale.org><br>Cc:<br>Subject: [EXTERNAL] [gpfsug-discuss] mmbackup questions<br>Date: Thu, Oct 17, 2019 8:00 AM<br> </font><br><tt><font size="2">I have been looking to give mmbackup another go (a very long history<br>with it being a pile of steaming dinosaur droppings last time I tried,<br>but that was seven years ago).<br><br>Anyway having done a backup last night I am curious about something<br>that does not appear to be explained in the documentation.<br><br>Basically the output has a line like the following<br><br> Total number of objects inspected: 474630<br><br>What is this number? Is it the number of files that have changed since<br>the last backup or something else as it is not the number of files on<br>the file system by any stretch of the imagination. One would hope that<br>it inspected everything on the file system...<br><br>Also it appears that the shadow database is held on the GPFS file<br>system that is being backed up. Is there any way to change the location<br>of that? I am only using one node for backup (because I am cheap and<br>don't like paying for more PVU's than I need to) and would like to hold<br>it on the node doing the backup where I can put it on SSD. Which does<br>to things firstly hopefully goes a lot faster, and secondly reduces the<br>impact on the file system of the backup.<br><br>Anyway a significant speed up (assuming it worked) was achieved but I<br>note even the ancient Xeon E3113 (dual core 3GHz) was never taxed (load<br>average never went above one) and we didn't touch the swap despite only<br>have 24GB of RAM. Though the 10GbE networking did get busy during the<br>transfer of data to the TSM server bit of the backup but during the<br>"assembly stage" it was all a bit quiet, and the DSS-G server nodes<br>where not busy either. What options are there for tuning things because<br>I feel it should be able to go a lot faster.<br><br><br>JAB.<br><br>--<br>Jonathan A. Buzzard Tel: +44141-5483420<br>HPC System Administrator, ARCHIE-WeSt.<br>University of Strathclyde, John Anderson Building, Glasgow. G4 0NG<br><br><br>_______________________________________________<br>gpfsug-discuss mailing list<br>gpfsug-discuss at spectrumscale.org</font></tt><tt><u><font size="2" color="#0000FF"><br></font></u></tt><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss" target="_blank"><tt><u><font size="2" color="#0000FF">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</font></u></tt></a><tt><font size="2"> </font></tt><font face="Arial"><br> </font><br><font face="Arial"> </font><br><tt><font size="2">_______________________________________________<br>gpfsug-discuss mailing list<br>gpfsug-discuss at spectrumscale.org<br></font></tt><tt><font size="2"><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a></font></tt><tt><font size="2"> <br></font></tt><br><br><BR>
</body></html>