ADSM-L

Re: TSM Server 4.1.3 Performance

2001-12-18 19:44:57
Subject: Re: TSM Server 4.1.3 Performance
From: Zlatko Krastev/ACIT <acit AT ATTGLOBAL DOT NET>
Date: Wed, 19 Dec 2001 02:45:00 +0200
They DO NOT provide same type and level of performance as ESS does!
The reason is very simple - if they do IBM would not put this massive
ammount of memory in ESS. ESS Internally consists of two "clusters", in
other words RS/6000 H50 or H70 with specific AIX&HACMP version. Those nodes
connect to SSA disks using 4 (four) SSA adapters per "cluster" and because
cache on the adapters cannot help too much (is too small for data ESS can
hold) each "cluster" has 4/8 GB of memory for caching the writes.
So do the math by yourself - is 128 MB adapter memory + 32 MB fast-write
cache equal to 8 GB RAM + 4 times (128 MB adapter memory + 32 MB cache) ?

Zlatko Krastev
IT Consultant





Paul Zarnowski <vkm AT CORNELLC.CIT.CORNELL DOT EDU> on 05.11.2001 21:17:55
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: TSM Server 4.1.3 Performance

You can get write cache on the SSA RAID adapters as well.  Wouldn't they
provide the same type of performance benefit that ESS write cache does?  In
any event, the question that Mike originally asked was about Read
performance, not Write performance.

At 10:00 AM 11/5/2001 -0800, Joshua S. Bassi wrote:
>The ESS is a whole different beast.  Because of the amount of cache
>involved and the fact that the ESS provides write responses as soon as
>data goes into the cache (and not actually written on disk) makes the
>RAID-5 array on the ESS a superb storage pool for TSM backup data.
>
>
>--
>Joshua S. Bassi
>Independent IT Consultant
>IBM Certified - AIX/HACMP, SAN, Shark
>Tivoli Certified Consultant- ADSM/TSM
>Cell (408)&(831) 332-4006
>jbassi AT ihwy DOT com
>
>-----Original Message-----
>From: ADSM: Dist Stor Manager [mailto:ADSM-L AT VM.MARIST DOT EDU] On Behalf Of
>Bill Mansfield
>Sent: Monday, November 05, 2001 9:56 AM
>To: ADSM-L AT VM.MARIST DOT EDU
>Subject: Re: TSM Server 4.1.3 Performance
>
>Unless your storage device is heavily cached, like IBM ESS or the other
>big
>storage boxes.
>There is no way to avoid Raid 5 on ESS, and there is no way to avoid
>Raid 1
>on EMC Symmetrix.
>
>
>_____________________________
>William Mansfield
>Senior Consultant
>Solution Technology, Inc
>
>
>
>
>                     "Joshua S.
>                     Bassi"               To:     ADSM-L AT VM.MARIST DOT EDU
>                     <jbassi@IHWY.        cc:
>                     COM>                 Subject:     Re: TSM Server
>4.1.3 Performance
>                     Sent by:
>                     "ADSM: Dist
>                     Stor Manager"
>                     <ADSM-L AT VM DOT MA
>                     RIST.EDU>
>
>
>                     11/05/2001
>                     11:42 AM
>                     Please
>                     respond to
>                     "ADSM: Dist
>                     Stor Manager"
>
>
>
>
>
>
>I would not recommend using RAID-5 for your disk storage pool unless it
>is the only copy of the data and you cannot afford to use plain
>mirroring.  TSM uses it's own striping technique for one and for two
>RAID-5 has a sever write penalty associated with it.
>
>
>--
>Joshua S. Bassi
>Independent IT Consultant
>IBM Certified - AIX/HACMP, SAN, Shark
>Tivoli Certified Consultant- ADSM/TSM
>Cell (408)&(831) 332-4006
>jbassi AT ihwy DOT com
>
>-----Original Message-----
>From: ADSM: Dist Stor Manager [mailto:ADSM-L AT VM.MARIST DOT EDU] On Behalf Of
>Mike Wiggan
>Sent: Sunday, November 04, 2001 11:20 PM
>To: ADSM-L AT VM.MARIST DOT EDU
>Subject: TSM Server 4.1.3 Performance
>
>Hi Guru's
>
>I have recently installed a new TSM 4.1.3 server on a P600 and AIX
>4.1.3. I
>have 2*75Gybyte RAID5 Disk Cache attached through SSA. The performance
>for
>reading from disk to tape is fine for small files, but I only get
>2.5MB/Sec
>when files are larger than say 1Gbyte. I have set "SELFTUNETXNsize
>Yes",
>and it brought it up tothis speed when using two drives.
>
>I have 18 *4Gbyte files on each RAID5 and can see that the data is
>evenly
>distributed in each file. I can see that the file say 7Gbytes is spread
>throughout many of the Disk Storage Volumes. I don't want to go straight
>to
>tape as this causes a huge headache in scheduling.
>
>Is this a known bottleneck or is there a way around to get at least
>20MB/Sec?
>
>Kind Regards
>Mike Wiggan, TCS/31
>Infrastructure Integration Specialist
>Petroleum Devlopment Oman LLC
>(michael.ma.wiggan AT pdo.co DOT om)


--
Paul Zarnowski                         Ph: 607-255-4757
Paul Zarnowski                         Ph: 607-255-4757
747 Rhodes Hall, Cornell University    Fx: 607-255-8521
Ithaca, NY 14853-3801                  Em: psz1 AT cornell DOT edu
<Prev in Thread] Current Thread [Next in Thread>
  • Re: TSM Server 4.1.3 Performance, Zlatko Krastev/ACIT <=