easy-tier « WordPress.com Tag Feed

DS8000 Series Easy Tier Volume Extent Allocation - Chargeback Tool

rogerluethy — Thu, 08 Nov 2012 08:23:04 +0000

DRAFT: 02.November 2012

DS8000 Series Easy Tier Volume Extent Allocation – Chargeback Tool

Easy Tier is an optional, no-charge, feature of the IBM System Storage DS8700, DS8800 and DS8870.

Easy Tier can move logical volume extents between disk ranks within an extent pool to provide automated hot spot management. Extents of a logical volume which are considered “hot” can be promoted to a higher tier of disk. Extents that are considered “cold” and have no or little I/O activity can be demoted to a lower tier of disk. What disk tier, such as Solid State, Enterprise or Nearline, a volume currently has extents on may be of interest for various reasons, including possible charge back or cost recovery for high performance disk tier use.
This Redpaper™ contains a sample script, providing a sample of the coding technique

DRAM vs Flash who wins?

richswain — Sat, 06 Oct 2012 10:46:47 +0000

I have spent most of the day looking over the products from TMS (Texas Memory Systems) that IBM just acquired. One of the questions I have always wondered is how to map performance back to a certain technology. When dealing with DRAM and Flash devices there seems to trade offs on each. The first that comes to mind is DRAM requires some sort of battery backup as it will loose the data contents when power is lost. Most DRAM cards and appliances have this under control with some sort of destaging to SSD or they have some sort of battery attached to the IO card that allows the DRAM time to hold information until power is restored.
DRAM is typically faster than its flash cousin as well as reliable and more durable. Typically there is less controller latency due to the lack of complexity of wear leveling and garbage collection. DRAM is still more expensive that Flash and has the problem of needing power all the time.
When looking at systems to find out how to decide which solution fits your environment it comes down to price and IO. The DRAM solutions are usually smaller in size but can push more IO. For Example the TMS 420 is 256GB of storage in a 4U frame that can push 600,000 IOPs. Not bad if you need 256GB of really fast space. This could be used for very high transaction volumes. This can be deployed with traditional storage and used for the frequently used database tables and indexes while lower IO tables can be thrown over to the spinning hard disk side.
In comparison the TMS 820 Flash array delivers a whopping 24TB in a 1U space and can push a meek 450,000 IOPS. This is somewhat incredible as the footprint is small and dense but still gives you the punch needed to beef up parts of your infrastructure. I stared running the numbers to compare this with say a V7000 with all SSD drives and we can’t come close. You could virtualize the system under the SVC code (included in the V7000) and use the Easy Tier function to move hot data to and from the TMS array which gives you the performance needed. I see why IBM decided to acquire TMS now.
So who wins in a DRAM and Flash discussion? The vendors of course, they are the ones who are going after this market aggressively. I think most consumers are trying to figure out if its needed to spend money on moving a database from 1500 disks at sub 20 ms response to using 200 larger disk and adding the DRAM or Flash device to keep the same latency. As an architect I want to keep in mind how much space and environmentals all of those disk eat up and having an alternative even if it costs more up front, is appealing.

EMC VMAX 40K AIMS at IBM DS8000

dancingdinosaur — Wed, 23 May 2012 14:45:22 +0000

EMC introduced the latest addition to its top mainframe Symmetrix storage, the VMAX 40K, which can scale to 4PB and is intended for extreme scalable environments. EMC claims the new device will deliver up to 3X more performance and more than 2X more usable capacity than any other offering in the industry. By configuring it with 2.5″ SAS drives and MLC (eMLC) Flash drives the device can also deliver the most densely packed storage.

The VMAX 40K, according to EMC, can store 60% more data than the Hitachi Virtual Storage Platform and 74% more than the IBM System Storage DS8000. The DS8000 today has a maximum capacity of 2.3PB. The Hitachi VSP tops out at 2.5PB.

If sheer capacity is the only issue, last summer word got out that IBM’s Almaden Lab delivered a 120PB array consisting of 200,000 SAS disk drives (rather than SATA) to ensure better performance for an unnamed client. Reports at that time also suggested the giant array was using IBM’s new General Parallel File System (GPFS), capable of indexing 10 billion files in just 43 minutes. The client and the use case have not been identified but the specs clearly suggest an extreme Big Data analytics situation.

For general enterprise computing as done by mainframe shops there is more to storage than just sheer capacity. For zEnterprise shops, the issue is how well optimized the EMC storage is for other parts of the System z. The zEnterprise already is highly optimized across its memory, processors, firmware, and networks as well as DS8000 storage.

As of the first quarter of this year IBM reports that the DS8000 supported the following capabilities that the EMC Symmetrix does not:

Dynamic Volume Expansion
Basic Hyper Swap
zHPF—QSAM, BSAM, BPAM, format writes, DB2 list prefetch cache optimization
Sub-volume tiering for CKD volumes
zDAC performance optimization
IMS WADS enhanced performance
Workload Manager I/O performance support
Metro Mirror suspension –message aggregation

If these capabilities are used in your data center, then the new EMC storage won’t work without extra effort on your part no matter how much capacity it delivers.

The VMAX 40K, however, does offer some nifty features, such as new Federated Tiered Storage (FTS) for VMAX through which external arrays can be used either as capacity pools for FAST VP (Fully Automated Storage Tiering for Virtual Pools) or managed as pass-through devices. FAST VP also now supports the System z and IBM i servers. Of course, IBM already delivers such storage tiering through EasyTier.

It is hard to assess how the VMAX 40K will work in the mainframe environment based on the spec sheet. And without pricing and workload benchmark data it is not possible to make an accurate assessment.

Still EMC rivals are decidedly cool. To HP, for instance, the VMAX 40K looks like a typical EMC midlife kicker; nothing surprising here, said an HP manager. He added that this does not change the fact that the EMC architecture is aging, and it doesn’t fundamentally change the economics of VMAX. HP, he notes, is beating VMAX head to head more and more with 3PAR based on its architectural advantage and newer technology. The HP mainframe storage is a Hitachi box, the P9500 XP Disk Array.

An IBMer, similarly, described the VMAX 40K as a business-as-usual, next-generation disk system announcement with new hardware and a few new functions. It still doesn’t appear to address the unsupported z capabilities noted above. The new EMC storage doesn’t do enough to offset advantages DS8000 offers mainframe shops today.

The introduction of the VMAX 40K, however, raises a larger question. In an increasingly scale-out world (as opposed to scale-up), do enterprises really need to load multi-petabytes of storage into a single frame? IBM recently boosted its SmartCloud offerings for enterprise computing. Will IBM put the zEnterprise and DS8000 storage up there too?

CMUA00007E error while running the IBM STAT tool

Anthony Vandewerdt — Tue, 23 Aug 2011 02:18:43 +0000

The IBM Storage Tier Adviser Tool (known as STAT for short) is a clever piece of software that lets you predict how much business value you would get from adding SSDs to your Storwize V7000, SVC, DS8700 or DS8800. This is because you can add SSDs to all of these products and then have hot spots dynamically and automatically migrated to SSD using IBM’s Easy Tier technology (which is offered as a no charge feature).

For clients who have not yet purchased SSDs, or who are unsure which Storage Pools to deploy them into, the STAT tool will help with decision-making.

I recently struck a rather simple problem with the STAT tool after installing it: I kept getting a CMUA00007E error. I downloaded the tool from here and installed it successfully onto my Windows 2008 64-bit lab machine (running on a IBM x3850). The install went fine so I then proceeded to download the heatmap from my Storwize V7000. The heatmap file is automatically generated by Easy Tier and is used as an input file for the STAT tool. You can see an example of where to find the heatmap file in the screen capture below:

I then placed the heatmap into the same folder as the STAT tool and tried to generate a report. It failed with this rather annoying message:

C:\Program Files (x86)\IBM\STAT>stat dpa_heat.78G01A6-2.110823.072309.data

CMUA00007E  The STAT.exe command failed to produce the heat distribution output.

I initially thought I had a bad heatmap, but since it is a binary file, opening it in a text editor did not tell me anything.

Actually the issue was simple: I did not have write authority to that folder. To get around this I instead started the command prompt as Administrator:

I then re-ran the command:

C:\Program Files (x86)\IBM\STAT>stat dpa_heat.78G01A6-2.110823.072309.data

CMUA00019I The STAT.exe command has completed.

Having run the tool I was now able to open the index.html in the STAT folder and see much hot data I have in my lab. Turns out that I don’t actually have any hot data right now! Don’t tell my manager though, he might try to take my SSDs away. #;-)

Having run the tool once, I did not need to use this trick again. It now runs without starting the command prompt as Administrator.

IBM bolsters System z storage

dancingdinosaur — Sun, 18 Apr 2010 17:17:53 +0000

Years ago the mainframe offered the first storage that would later become known as a storage area network (SAN). Few noticed. Even now mainframe storage hardly draws any attention. The ongoing improvements tend to be steady and incremental. An occasional first, like built-in tape drive encryption, but in general nothing revolutionary occurs in z storage.

The last year, however, has seen a resurgence of IBM interest in System z storage. It bought Diligent and turned it into the ProtecTIER product and IBM XIV, another acquisition and interesting grid storage product. Both now can connect with the System z, XIV through Linux on z as the gateway. It also introduced Easy Tier, an SSD product that uses built-in intelligence to automatically detect and move data that will specifically benefit from SSD performance.

Storage enhancements for the z are coming just in time. IBM is targeting HP customers for its System z and POWER7 servers. HP introduced 400 GB SSD for use with the System z through its HP XP storage system. While HP doesn’t have a storage grid product like XIV, it does allow the XP to act as a storage controller for various large arrays behind the XP, in effect creating grid-like storage using various HP storage arrays. It also has data deduplication products. The HP mainframe storage story is here.

ProtecTIER for the z is a deduplication product. It reduces the amount of data you have to backup (after the initial full backup), thereby speeding backup and reducing IT resource consumption.

XIV, however, is the more interesting of the new System z storage options. It allows an organization to put large amounts of varied storage (different disk, capacity, performance characteristics) behind the System z. Don’t expect it to replace conventional mainframe storage as delivered by, say, the DS8700. Rather, it offers a way for an organization to consolidate all its storage behind the z and gain the benefits of storage consolidation for varied workloads and z reliability and availability. XIV, as a storage grid, automatically spread copies of data across the available capacity. This speeds rebuild time, especially now that XIV is incorporating 2TB disks.

The emergence of Linux on System z along with Java has rejuvenated the System z in many ways. It has enabled new and different workloads, makes SOA practical, and enables the z to play in the web 2.0 and mobile computing worlds. The arrival of XIV and ProtecTIER do the same for System z storage, which had been effective but uninspired, with maybe an occasional tape innovation, until now.