Login | Register For Free | Help
Search for: (Advanced)

Mailing List Archive: DRBD: Users

Re: monitor and graph "data transfer rate"

 

 

DRBD users RSS feed   Index | Next | Previous | View Threaded


Lars.Ellenberg at linbit

Aug 9, 2006, 12:01 PM

Post #1 of 2 (568 views)
Permalink
Re: monitor and graph "data transfer rate"

/ 2006-08-09 10:51:21 -0600
\ Monty Taylor:
> I'm thinking what is being sought after is the data transfer rate
> under normal operation ... (although with each block being transfered
> synchronously with writes, I'm not sure if that number would actually
> show useful information, now that I think about it)

we have "ns nr dw dr", which are
network send, read
disk write, read

ns may be higher than dw, since it inlcudes resync data blocks.

unit is sectors (512 Byte).
counters are only reset to zero when drbd is newly initialized,
so when you (re)configure the drbd network, the network counters are
reset, when you (re)configure the drbd disk, the disk counters are
reset.

you can easily "strategically monitor" using e.g. rrd-tools.
if you equally monitor /proc/diskstats (obviously the lower level
devices, drbd does not do any statistics there), and rrd-graph the
results, thats about as good as it gets.

or am I still missing something?

--
: Lars Ellenberg Tel +43-1-8178292-0 :
: LINBIT Information Technologies GmbH Fax +43-1-8178292-82 :
: Schoenbrunner Str. 244, A-1120 Vienna/Europe http://www.linbit.com :
__
please use the "List-Reply" function of your email client.
_______________________________________________
drbd-user mailing list
drbd-user [at] lists
http://lists.linbit.com/mailman/listinfo/drbd-user


vampired at gmail

Aug 9, 2006, 2:50 PM

Post #2 of 2 (523 views)
Permalink
Re: monitor and graph "data transfer rate" [In reply to]

I was looking for something like this, but super easy query or command.
Like Monty said, since it is block level most transactions may not "ramp" up
enough to really show real throughput, but some way of "testing" what the
devices are able to keep up would go a long way for benchmarking, scaling,
sizing, and making sure everything keeps running "up to snuff".


On 8/9/06, Lars Ellenberg <Lars.Ellenberg [at] linbit> wrote:
>
> / 2006-08-09 10:51:21 -0600
> \ Monty Taylor:
> > I'm thinking what is being sought after is the data transfer rate
> > under normal operation ... (although with each block being transfered
> > synchronously with writes, I'm not sure if that number would actually
> > show useful information, now that I think about it)
>
> we have "ns nr dw dr", which are
> network send, read
> disk write, read
>
> ns may be higher than dw, since it inlcudes resync data blocks.
>
> unit is sectors (512 Byte).
> counters are only reset to zero when drbd is newly initialized,
> so when you (re)configure the drbd network, the network counters are
> reset, when you (re)configure the drbd disk, the disk counters are
> reset.
>
> you can easily "strategically monitor" using e.g. rrd-tools.
> if you equally monitor /proc/diskstats (obviously the lower level
> devices, drbd does not do any statistics there), and rrd-graph the
> results, thats about as good as it gets.
>
> or am I still missing something?
>
> --
> : Lars Ellenberg Tel +43-1-8178292-0 :
> : LINBIT Information Technologies GmbH Fax +43-1-8178292-82 :
> : Schoenbrunner Str. 244, A-1120 Vienna/Europe http://www.linbit.com :
> __
> please use the "List-Reply" function of your email client.
> _______________________________________________
> drbd-user mailing list
> drbd-user [at] lists
> http://lists.linbit.com/mailman/listinfo/drbd-user
>



--
"Do the actors on Unsolved Mysteries ever get arrested because they look
just like the criminal they are playing?"

Christopher

DRBD users RSS feed   Index | Next | Previous | View Threaded
 
 


Interested in having your list archived? Contact Gossamer Threads
 
  Web Applications & Managed Hosting Powered by Gossamer Threads Inc.