IMHO something close to collocation groupping can be done right now:
1. Using COPY DOMAIN create several "group" domains with same policies
2. Define several pool over same library/devclass
3. Update each "group" domain to refer its corresponding "group" pool
4. Update nodes to become part of group domain
All pools use same set of scratch libvolumes. Each "group" domain can have
different MAXSCR limits and different collocation density.
Zlatko Krastev
IT Consultant
Bill Colwell <bcolwell AT DRAPER DOT COM> on 16.11.2001 17:43:46
Please respond to "ADSM: Dist Stor Manager" <ADSM-L AT VM.MARIST DOT EDU>
To: ADSM-L AT VM.MARIST DOT EDU
cc:
Subject: Re: Collocation - on or off
Dwight, I agree with you on most of your analysis except for the math.
2500 * 3 minutes = 7500 min = 5+ days!
This problem of more nodes than tapes when running with collocation on is
one I have been asking Tivoli to fix for a long time. A fix may be coming!
See Dave Cannon's 'Scalability Enhancements' slides on the Oxford
TSM Symposium web site at http://tsm-symposium.oucs.ox.ac.uk/home.html
Check out the slides about 'groups'. I am not sure his presentation says
this enhancement will definitely be done, so if anyone really wants it
let your marketing rep know (if you can find him/her).
I run with collocation on and 1,600 nodes. At any time I have only
100 - 150 filling or empty tapes so the server has to double up the nodes
on each tape, actually more like 10-up to 20-up. To avoid the
stress of too many mounts I only migrate down to 20% at most migration
events. On weekends I migrate down to 10% and every 4th weekend after
reaching 10% I switch collocation off and migrate to 0%.
--
--------------------------
--------------------------
Bill Colwell
Bill Colwell
C. S. Draper Lab
Cambridge, Ma.
bcolwell AT draper DOT com
--------------------------
In <473D713C23E6D211BF810008C7B179D6045FF0C7 AT amtulx4.tul.am.bp DOT com>, on
In <473D713C23E6D211BF810008C7B179D6045FF0C7 AT amtulx4.tul.am.bp DOT com>, on
11/16/01
at 10:43 AM, "Cook, Dwight E (SAIC)" <cookde AT BP DOT COM> said:
>In an event like that the normal tape selection goes like
> filling tape with node's data already on it
>if not then
> scratch tape if "MAXSCR" for storage pool hasn't been hit AND
>scratch tape still exists in the ATL
>if not then
> any filling tape within the storage pool
>when you add a new node, it goes through the same routine when its data
goes
>to a tapepool...
>collocation in an environment with 2500 clients will cause a bunch of tape
>mounts unless you limit the maxscr's
>knowing that in a 3494 ATL (with 6+ frames) you are looking at an average
of
>90 seconds or so for each tape mount (until it starts writing) and I'd
>guess about the same for dismounts (from rewind to insert back into tape
>storage slot)
>so 2500 mounts/dismounts at 3 minutes each would put you at 2.08 hours for
>just mounts & dismounts for migrating data from a diskpool to a tapepool
and
>if we are realistic, that many daily mounts would be hard on the loaders
>within the tape drives...
>Sure, without using collocation, eventually (from a statistic point of
view)
>each node would have some data on each tape and that would suck for a
>restore...
>as always it all depends...
>I keep flip'n environments back & forth trying to do the best for the
>clients and unless you have lots of clients and lots of client data and
only
>a small part changes nightly and only if you end up doing LOTS of complete
>restores, using collocation seems to be a flip of a coin (or at least in
the
>environments I deal with)
>Now & again we end up doing a restore of an NT box with 30 GB and that
takes
>a long time due to mounts/dismounts of TONS of volumes... but that might
be
>only once or twice a year... other than that, all our DB's are complete
>archives each time so all their data that they restore is on a select few
>tapes and collocation wouldn't buy anything anyway.
>OK, I'm reaching the end of a page so I'll cut my reply here ;-)
>later,
> Dwight
>-----Original Message-----
>From: Luke Dahl [mailto:ldahl AT JPL.NASA DOT GOV]
>Sent: Thursday, November 15, 2001 3:19 PM
>To: ADSM-L AT VM.MARIST DOT EDU
>Subject: Collocation - on or off
>Hi,
> We're trying to determine if we should use collocation on a system
>we plan to put into production shortly. My question is whether or not
>it's possible to turn collocation on and specify the number of nodes
>assigned to a tape. The reason I ask is because we expect the addition
>of approximately 2,500 nodes, with the majority being workstations. The
>media we will be using are extended tapes holding up to 70GB
>compressed. If we collocate and a individual tape is assigned to each
>workstation we will waste all of that space (assuming each node will
>have about 10GB aggregate over the expected subscription period) right?
>Will TSM allow for shared tapes if there aren't enough tapes for each
>node? What about if there aren't any scratch tapes in the library and a
>new node is added? Thanks in advance!
>Luke
|
