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
11/16/01
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
|