Around the Storage Block Blog

Converged Infrastructure: Block based storage virtualization podcast

CalvinZ — Fri, 06 Nov 2009 17:55:00 GMT

This is the third in a series of three podcasts focusing on our HP Converged Infrastructure announcement. In part 1, I spoke with Sr. VP and GM of HP StorageWorks Dave Roberson. In part 2, I talked to the former CEO of IBRIX Milan Shetti and Marketing Director Lee Johns about the new X9000.

In today's podcast, we talk about block-based storage virtualization. Storage virtualization is often a confusing topic because there are different types of storage virtualization. Today's podcast discusses two types of block-based storage virtualization: within an controller array (like our HP StorageWorks EVA) and network or SAN based (our StorageWorks SAN Virtualization Services Platform or SVSP). Each of these products had enhancements that were announced with the November 4th Converged Infrastructure announcement.

With the SVSP (link goes to the hp.com product page), we announced a "new" management tool - Command View SVSP. This will be very familiar tool to EVA customers as Command View SVSP is very consistent with Command View EVA. But it also simplifies and automates the task of provisioning a LUN. For the details, listen to the podcast.

The advancement with the StorageWorks EVA (link goes to EVA family page) is with our Cluster Extension EVA. This software manages the failover and failback between EVAs in a cluster. What's new with the software is support for Microsoft Hyper-V Live Migration. We are the first array to support the new capabilities and again, there's more about this in the podcast. I also have a guest blog from one of our engineers below that goes into more details.

So with that, here's the podcast:

By Matthias Popp, HP StorageWorks Architect, Storage Systems Integration

Migrating a running server across data centers, servers and storage?

Are you tired of planning weekend downtime for storage system upgrades, server patches or network changes in your data center? Are you getting the same "Not this weekend ..." response from your business managers and users?

HP worked with Microsoft to enable Live Migration of virtual machines (VMs) in Hyper-V R2 - not just between servers but also between your storage systems and hence between your data centers!

The latest release of HP StorageWorks Cluster Extension EVA orchestrates the interaction between Microsoft's System Center Virtual Machine Manager, Windows Failover Clustering and Hyper-V Live Migration to move running Server VMs between servers and storage in one single step.

The newest version of Cluster Extension checks the disk array replication process and prepares for a Live Migration and swaps the replication direction when the VM's target server is connected to the remote disk array. All automatic with no further administrator interaction. You decide when to Live Migrate and Cluster Extension makes sure the data can be accessed. Simple as that.

Since your servers and storage are distributed between data centers, the same configuration and software is used for disaster protection. No need to learn additional tools. Use the ones you have!

Finally a simple solution to proactive maintenance with no downtime!

The new Live Migration support in Cluster Extension configurations will make a radical impact on your IT and business teams. Clustering software manages unexpected failures at any time and Live Migration enables maintenance during the work day. The IT team can now do server and storage maintenance during working hours. They no longer have to plan for downtime way ahead of a change. The IT management doesn't have to budget for expensive weekend and night working hours. Get your server and storage patched now, because you can!

The following paper explains the configuration and will soon be updated for Windows 2008 R2 and Hyper-V R2 Live Migration support: Disaster Tolerant Virtualization Architecture with HP StorageWorks Cluster Extension and Microsoft Hyper-V^TMwhite paper

Visit the HP booth at Microsoft's Tech·Ed Europe in Berlin next week for a demonstration and visit Microsoft's blog for more info about the webcast Building Effective and Highly Available Disaster Recovery Solutions Using Microsoft Virtualization

Converged Infrastructure: the new X9000 podcast

CalvinZ — Fri, 06 Nov 2009 08:18:00 GMT

By Calvin Zito, @HPStorageGuy

On Wednesday, I did the first of three podcasts talking about our HP Converged Infrastructure announcement. If you missed that one, I highly recommend that you listen to it. My guest was with our Senior VP and General Manager of StorageWorks Dave Roberson. Today in part 2, I talk with Milan Shetti, former CEO of IBRIX and Lee Johns, Director of Product Marketing about the HP StorageWorks X9000 Network Storage Systems family. As you might have guessed, the X9000 is based on IBRIX. Because the discussion was longer than my normal podcasts, I split it into two parts. In part one, Milan talks about the integration of IBRIX into HP StorageWorks and Lee and Milan give an overview of the X9000 family. Note that the volume on both of these is a bit low but since these were already a day late, I didn't want to make you wait longer to hear these. So turn your volume up a bit higher than usual. Here it is:

If you have difficulty with the embedded player in your browser, click here to listen to the podcast.

In part 2, I continue the conversation with Milan and Lee. In this part, we answer the question what's happening PolyServe, how the X9000 fits into the HP Converged Infrastructure, and discuss the strategic implications of the X9000.

If you have difficulty with the embedded player in your browser, click here to listen to part 2.

Here are a couple of things that can help you learn more about the X9000:

Visit the X9000 product page
Attend an IDC webcast next week on 12 November at 2 PM EST/11 AM PST.

In the next podcast in the series, we'll discuss what's new with the HP StorageWorks EVA and SAN Virtualization Services Platform (SVSP).

Converged Infrastructure podcast with Sr. VP and GM of StorageWorks Dave Roberson

CalvinZ — Wed, 04 Nov 2009 06:01:00 GMT

A podcast with Sr VP and General Manager of HP StorageWorks Dave Roberson discussing how StorageWorks will help power the HP Converged Infrastructure.

...(read more)

What will EVA customers benefit from new NetApp program be? Zip! Zilch

CalvinZ — Mon, 02 Nov 2009 15:51:00 GMT

By Calvin Zito, @HPStorageGuy

In my last post, I included a couple of summary videos from our recent HP StorageWorks Tech Day. The hands-on lab really stirred up a few folks over at NetApp. The week after our Tech Day, they did a WebEx session to try to address some of the comments made by the bloggers about how difficult the management of their FAS system was. I won't go into details about that but I counted at least three different GUIs that they showed during that demo. The HP StorageWorks EVA has one - Command View. But, that's not the topic I want to cover today.

The old "switch-a-roonie"

During their online demo, Vaughn Stewart from NetApp also discussed the NetApp vSeries - a network based storage virtualization product - and suggested that HP and NetApp were partnering to help EVA customers. Vaughn thanked me for attending the demo and talked about partnering with HP. I thought he was trying to connect the fact that I attended as being an HP endorsement of the vSeries. It wasn't. I made it very clear that HP wasn't working with NetApp to put vSeries products in front of our EVA's. I told the demo audience that HP has our own network-based SAN virtualization product called the SAN Virtualization Services Platform (SVSP) that competes with the vSeries and in no way do we recommend EVA customers use the vSeries to virtualize a pool of EVAs. We have talked about the SVSP several times on this blog and it will be discussed in a podcast later this week.

I initially didn't understand why Vaughn brought the vSeries into the demo. But a week or two after the NetApp demo, they announced a new marketing program targeting EMC CX series and HP EVA installed base customers with their vSeries. Now it's pretty clear to me what was going on then. This new NetApp marketing program asks customers to consider putting a vSeries in front of an EVA or CX.

So I want to spend a few minutes now discussing why I think it would be a bad decision for any EVA customer to consider such a thing. It's my belief that the benefits to an EVA customer would be zip (and interestingly that is the name of NetApp's program).

Improve storage efficiency at what price?

The claim NetApp is making is that EVA customers are not efficiently using their storage capacity. That's a bit laughable given that with an EVA, every spindle is used for data and unless using tiering, we recommend a single disk group which gives incredible storage capacity efficiency. To be in the program, NetApp has to approve the customers' application. The customer is basically signing up to purchase the vSeries in 90 days if it delivers what NetApp will stipulate. Be sure NetApp also stipulates the peformance hit you'll take - but I'm ahead of myself on that one.

My guess is the number of customers that actually get into the program will be rather small and maybe that's a NetApp objective of their marketing program. I suspect that NetApp's real motive is to develop a list of CX and EVA customers that they can continue to call on.

The NetApp claims of improved storage efficiency will come from a couple of categories of services that the vSeries provides for the arrays attached to it.

Thin provisioning
Data replication (snapshot, clones, etc)
Deduplication

The EVA customer already enjoys capacity efficiencies with the first two categories of thin provisioning and data replication. (Note that the EVA doesn't use traditional thin provisioning today but uses a product called Dynamic Capacity Manager that accomplishes similar results by integrating with the OS).

For that matter, if customers wanted to pool their capacity of multiple EVAs and manage it as one pool, the SVSP offers thin provisioning and replication services too. What we don't offer today is primary LUN deduplication. But should customers running an EVA rush to deduplication their block-based mission critical storage? I think the answer is absolutely not and here's a few things to consider:

NetApp has recently claimed 37,000 deployments of deduplication (via their PR department) but in a recent earnings call, their executives said 37,000 downloads. I don't know about you but there's a big difference between the number of customers who download some free software versus who are actually using it, especially in production environments.
There's a trade-off to implementing deduplication with primary, block based storage - and that trade-off is performance. Data that I've seen from a few different sources has said that a top customer concern in a virtualized environment is performance. I've seen throughput testing results that say the performance degradation on a FAS system with dedup can be as high as 65%. Their own recommendations say to run it during low activity and not all of the time. NetApp also makes you sign a waiver stating you understand the risks of lower performance.
We haven't tested to see what the actual deduplication capacity savings would be and frankly there are a lot of factors that would play into that. Since the controllers in the vSeries are the same controllers in the FAS system, it's worth noting that we have found that the percentage of capacity savings is roughly equal to the percent of slowdown.
And that performance hit from deduplication doesn't include any other latencies that the vSeries introduces because of their in-line architecture.

So should an EVA customer put their arrays behind a NetApp vSeries for a potential small capacity savings when the potential performance penalty is high? And keep in mind the vSeries is based on the FAS controller. We've shown in a recent blog post that based on our testing, the performance of that degrades rapidly.

There are some good reasons to implement SAN-based virtualization with a product like the StorageWorks SVSP or the NetApp vSeries. However, for an EVA customer, NetApp's value proposition of getting better capacity efficiency of the physical storage just isn't one of them. A far better answer for the EVA customer is the StorageWorks SVSP. We'll cover this topic in podcast later this week so stay tuned for that.

Tweet this!

HP StorageWorks Tech Day Videos

CalvinZ — Fri, 23 Oct 2009 18:13:00 GMT

By Calvin Zito

I've been a bit busy over the last few weeks and haven't been able to post anything - for that I apologize. I've got several things swimming around in my head that I want to talk about and I'll get to those over the next several weeks.

Today, I want to revisit our HP StorageWorks Tech Day that we held earlier this month and share with you a couple of summary videos that we did at the event. If you missed it, I have two posts on the Tech Day, first was "StorageWorks Tech Day starting now" and the other, "StorageWorks Tech Day - in their words so far...". There's been many more blog posts on from the bloggers who attended and I'll have another post soon pointing to those.

So now to the videos. First up was a video we did around the hands-on sessions we did with the EVA, HP LeftHand P4000 SAN solution, and our SAN Virtualization Services Platform (SVSP). The video speaks for itself so here it is.

(NOTE: In case you have problems with your browser and the embedded video, click on this link)

At the conclusion of the event, we were able to catch several of our guests before they ran to the airport to return home, to get their overall reaction to the event. This needs little set up other than to say we did host the event at the SNIA facility in Colorado Springs which is co-located with our HP site in the Springs. So you that's why you see a SNIA logo in the background and there were people doing their job that a few times were walking behind someone talking on camera.

(NOTE: And again, in case you have problems with your browser and the embedded video, click on this link)

That's it for now - thanks for stopping by to watch the videos. I wanted to remind you that you can follow me on Twitter as @HPstorageGuy.

Tweet this!

Is it time for you to consider storage automation?

CalvinZ — Wed, 21 Oct 2009 18:47:00 GMT

By Jack Hughes, Storage Automation Product Manager

For what seems like years, the trades have been touting storage automation as the next big thing to improve data center efficiency. No doubt, there is vast potential for automation to help streamline SAN and NAS management. Storage provisioning, back-up, capacity reclamation and configuration management are a few examples of storage services typically requiring lots of repetitive, time consuming manual processes. So why are enterprise organizations, even those who have made the leap into server and network automation, reluctant to bring automation to storage operations?

Perhaps the answer lies in the history and culture of storage administration which has been somewhat shrouded in secrecy and segregated from the rest of the IT community by security measures. Whatever the reason, storage administrators often substitute home-grown scripts for true automation, relegating themselves to endless updates in order to stay current with the ever changing storage infrastructure.

This set-up worked just fine over the years until the disruptive force of virtualization changed everything. The virtualization revolution forced most organizations to re-think the way they’re doing business, and SAN and NAS management is no exception.

What we’re hearing now from customers is that the virtual revolution and its indisputable benefits also comes with a dark side manifesting itself in VM sprawl, over-provisioned storage, and underutilized capacity leading to application performance bottlenecks. Data center and NOC managers are concluding that the old ways of managing storage are no longer viable. Transparency of information about the storage infrastructure including capacity utilization, compliance, and performance is a must. In addition, more and more organizations are considering adding storage to self-service portals to more effectively meet the demands of growing and constantly changing virtual host infrastructure.

The virtualization revolution has provided the impetus to finally make storage automation essential for successful enterprise IT management. But to effectively meet the challenge, you need the right tools. HP Business Service Automation (BSA) is a good place to start. HP Operations Orchestration (OO) is the industry leader in run book automation and is tightly integrated with HP Storage Essentials. Together, these tools provide out-of-the box storage automation flows for rapid deployment of a variety of storage services. In addition, custom flows are easily created with the OO Studio using a simple drag, drop, and wire interface to quickly automate storage services and routines.

In upcoming editions of this blog I’ll talk more about specific use cases for automating storage services, but in the mean time I’d love to hear your thoughts on the subject of storage automation and its relevance in today’s virtual data centers.

Tweet this!

Podcast - new X3000 HA Bundles

CalvinZ — Wed, 07 Oct 2009 05:25:00 GMT

By Calvin Zito

During our very successful HP StorageWorks Tech Day, we also did an announcement. I've already done a podcast on one of the products we announced, the X510 Data Vault - it's time for me to give some love to the other product we announced - the X3000 Network Storage Systems High Availability Bundles. Here's a link to the product page if you want to learn more about the X3000 family.

So without further a do, here's the podcast (about 6 minutes short):

(NOTE: Just in case the embedded player doesn't work with your browser, click here to go to our Enterprise TV page and listen to the podcast)

Tweet this!

Announcing the X510 Data Vault podcast with Microsoft guest blog

CalvinZ — Fri, 02 Oct 2009 05:00:00 GMT

By Calvin Zito

I have a ton of things on my list to blog about in the next few days as there's still much to say about the HP Tech Day. For this post, I'm going to take a slight diversion to share with you a podcast and guest blog from Microsoft's Mark Pendergast. On Tuesday morning, we announced two new StorageWorks products: the HP StorageWorks X510 Data Vault and the HP StorageWorks X3000 High Availability bundles. I have a podcast ready to go for the X3000 as well but this post will focus on the X510. First, here's the podcast I did with Bill Johnson, the product manager for it. (NOTE: X500 is the new family - and yes, we're planning more in the future - while the X510 is the product we announced).

(NOTE: Adding a link for those browsers that can't play the embedded podcast: click here to listen)

Here are a few links to help you go deeper:

Article about the X500 Data Vault titled, "Think data storage has to be complicated? Think again"
Here's a link to the U.S. product page

And here's a short video demo of it:

(NOTE: If this video doesn't work, go to the article "Think data storage has to be complicated? Think again" and there's a link to it on the right side)

And now here's the post from Mark who is part of the Windows Home Server team at Microsoft:

By Mark Pendergrast

We're thrilled to have been invited to share the Microsoft perspective on the Hewlett-Packard DataVault launch with readers of the HP Around the Storage Block Blog. But we're even more excited to celebrate this important new milestone for the Windows Home Server ecosystem - a dedicated product entry into the Small Office Home Office (SoHo) and micro business space!

As we've posted about before on the Windows Home Server team blog, there is significant value for having a Windows Home Server in a SoHo or micro business. From backing up client PCs to offering remote access to their server (and the files on the Data Vault ) when they're away from the office, a Windows Home Server-based product offers a great solution for a business that doesn't have - or want - a sophisticated IT infrastructure. We thought this was such a good match that we recently added a dedicated 'Windows Home Server SoHo' page on our product website (lots of good info up there, including some compelling case studies). But Microsoft and HP aren't the only ones who recognize this value, as business pubs SMB PC Magazine and Inc have caught on to this fact as well.

So we congratulate HP on making the first entry into this market with their dedicated line of Data Vault line of products. Because HP has built in the right set of features, hardware specifications, branding, and of course channel/marketing support, we're confident that they're on to something big here! We look forward to partnering with them on the launch and beyond.

Mark, Windows Home Server Team, Microsoft

So there you have it - a jammed pack post with a podcast, a video and a Microsoft guest blog. Phew!

Tweet this!

StorageWorks Tech Day - in their words so far....

CalvinZ — Thu, 01 Oct 2009 05:25:00 GMT

By Calvin Zito

I've been home from our HP StorageWorks Tech Day for less than 24 hours and I still am floating on a cloud (No Foskett - not that kind of cloud!). When we first started talking about doing it a couple of months ago, I never would have imagined the incredible response we've had to it. But I'll leave some of my thoughts going into it and now for another post. For now, I wanted to point you to some of the posts by others who attended our event in Colorado Springs. You can read a bit more about the event by reading my post titled "StorageWorks Tech Day Starting Now".

So here are links to the posts I've seen so far from the attendees:

HP Tech Day 2009, Day 0 by Devang Panchigar. Devang included some great pictures of one of the most beautiful places in Colorado, Garden of the Gods
StorageMojo off to HP's Storage Tech Day by Robin Harris. Robin liked that we didn't require an NDA but missed our chance for cocktails in the agenda.
HP Storage Tech Day by Rich Brambley. Rich has a widget tracking the event Twitter hashtag on his blog.
HP StorageWorks Tech Day 2009, Day 1 by John Obeto. I met John at HP Technology Forum and am really glad he attended to learn more about StorageWorks.
HPTechDay 2009 Day 1: HP StorageWorks Technology by Devang Panchigar. Devang gives lots of details of not only the sessions but the conversations he had during the day and evening out.
HP StorageWorks TechDay & SMB Announcement by Simon Seagrave. Simon gave a summary of Day 1 and talked about the announcement we did at the beginning of Day 2
The Price of Quality by Ray Lucchesi. Ray focused on what he saw in our tour of the EVA test lab.
HPTechDay: HP really 'gets' storage! by Nigel Poulton. Nigel states that his opinion WAS that we didn't get storage; his opinion changed during the event. This is one of my favorite posts.
HPTechDay 2009 Day 2: HP Converged Data Center by Devang Panchigar. Devang gets the prize for the most thorough and timely updates. His Day 2 summary talks about our converged infrastructure discussion.
HP StorageWorks Tech Day 2009, Day 2 by John Obeto. I know John got sick after returning home but he toughed it out and put this post up.

NOTE: Somehow in editing HTML, I deleted a post on my list from Rich Brambley. Here's a link to it: HP tells storage virtualization future with LeftHand.

There were a few articles from a few folks who didn't attend but were watching the information pour across Twitter:

Tech Day gives a peek into the future of storage by Rick Vanover, Tech Republic. Rick was invited to Tech Day but couldn’t come; thanks for the article Rick!
HP lays out sketches of storage roadmap by Chris Mellor, The Register. The Register actually picked up chatter from Tech Day and wrote about it.
HP StorageWorks Tech Day 2009, Day 1 includes HP Total Care expansion announcements by Shane Pitman, TechVirtuoso.com. Frank Owens from TechVirtuoso was at the event - Shane published this article.
HP drops roadmap nuggets at StorageWorks TechDay by Beth Pariseau, ITKnowledgeExchange.com Storage Soup Blog

There were some interesting comments over Twitter, but I'll save those for another update this week.

Tweet this!

StorageWorks Tech Day starting now

CalvinZ — Mon, 28 Sep 2009 04:43:00 GMT

By Calvin Zito

If you don't follow me on Twitter, you may not be aware that we have a blogger event going in on Colorado Springs. We've brought a number of prominent storage and virtualization bloggers and over the next day and a half, have a packed agenda. The topics we'll cover include:

Storage virtualization for enterprise customers - virtualize infrastructure, not just servers
Shared storage for virtual servers (SMB-focused)
Unified storage
Deduplication
Converged Infrastructure

We'll also have hands on sessions and demos of the HP StorageWorks Enterprise Virtual Array (EVA), SAN Virtualization Services Platform (SVSP), and HP LeftHand. Here's a list of who is here (the "@name is their Twitter user name):

Rich Brambley (@rbrambley) http://vmetc.com
Nina Buik (@NinaBuik) Connect Community (its a long URL so this is a hyperlink)
Stephen Foskett (@sfoskett) http://blog.fosketts.net
Robin Harris (@StorageMojo) http://storagemojo.com (Robin has already post a blog - click here to see it)
Greg Knieriemen (@Knieriemen) http://www.storagemonkeys.com/index.php?option=com_myblog&Itemid=136
Ray Lucchesi (@RayLucchesi) http://silvertonconsulting.com/blog/
John Obeto (@JohnObeto) http://absolutevista.com
Frank Owen (@fowen) http://techvirtuoso.com
Devang Panchigar (@StorageNerve) http://storagenerve.com (Devang also posted a blog - click here to see it)
Nigel Poulton (@nigelpoulton) http://blogs.rupturedmonkey.com
Simon Seagrave (@kiwi_Si) http://www.techhead.co.uk

I'm grateful to all of them for taking time out of their busy schedules to learn more about HP StorageWorks.

I'll be blogging here about what is going on and hope to have a few podcasts later in the week. If you want to follow the conversation real-time, we'll be using the hashtag #HPTechDay on Twitter. If you don't use Twitter, here's a URL where you can see all of the "tweets" using this hashtag: http://search.twitter.com/search?q=%23HPTechDay.

Tweet this!

Understanding FAS ESRP Results

CalvinZ — Sat, 26 Sep 2009 04:59:00 GMT

By Karl Dohm, Storage Architect

Welcome back to the next in a series of posts where we take a closer look at NetApp and its FAS series of storage arrays. The discussion topic today is Microsoft's Exchange Solution Reviewed Program (ESRP) and its tie to FAS throughput.

The FAS has some controversial history with regards to performance. From time to time the issue comes up and in response NetApp has generally denied the problems exist. Often we find the opposite stance in posts from NetApp lauding their performance, for example in Kostadis Roussos' post where he refers to WAFL write performance as 'surreal'. But, as I have said in previous posts, there are some justifiable reasons this controversial subject keeps surfacing.

First of all, let's touch on why an average storage consumer should care about array throughput. An array with better throughput, i.e. the ability to service more I/Os from a given set of spindles, can result in requiring less hardware to do the same job. The bigger the throughput difference, the more to be saved on purchase price, warranty cost, power consumption, floor space, cooling, etc. Array throughput statistics can be meaningful when evaluating value in a storage array. It seems NetApp also finds this array attribute important given the amount of blog posts and papers they have on the topic of performance.

Recently in the comments section of a blog post on understanding WAFL, NetApp's John Martin and I had a small debate as to whether a synthetic load generator like IOMeter could be used to characterize how an array will perform in production scenarios. I made the argument that this type of tool can be used to circle the wagons around the I/O characteristics of a real world application, and that through multiple point tests of the load components of the application one could get a reasonable assessment of how well the box will behave. John's opinion was more along the line that synthetic workload tests were not suitable to provide an indication of how well an array would run with a production application ("Synthetic workloads in isolation lead to non typical results"). He referenced Jetstress as a more accurate indicator.

I took his queue and had a look at the FAS2050 ESRP results paper which describes MS Exchange like throughput of the FAS2050 array. Even though ESRP isn't intended to be a benchmark, a scan of ESRP results tells me that many vendors seem to use the forum of ESRP as a way to post throughput results relative to how their array handles MS Exchange load. It kind of makes sense since there seems to be no Exchange related benchmark out there, and ESRP is the closest controlled thing the industry has to work with.

The NetApp ESRP paper provides insight into how NetApp would recommend setting up the 2050 for Exchange loads, and it shows throughput results in a heavily loaded 10,000 mailbox Jetstress test. This paper sparked our interest because the described results seemed good and did not correlate with results from synthetic load generators that produce a similar pattern as Jetstress. Maybe John was right. We decided to peel back the onion a bit and take a look under the covers of this ESRP test to figure out what was going on.

We happened to have access to a FAS2050 and decided to try and recreate the ESRP results as published. It turns out that the IOPs value that NetApp published was in fact roughly re-creatable given the data in the paper. On the surface this can be viewed as NetApp having made an honest submission to ESRP, and within the letter of the law one could reasonably argue that they did. But we also learned that NetApp found a way to make their results come across as favorably as possible, meaning the results have little relevance as to how well the FAS will run MS Exchange.

After a rather lengthy setup experience, we finally configured the aggregates, volumes, servers, LUNs, MPIO, and HBA attributes as described in the ESRP paper. We even set the diagnostic switch "wafl_downgrade_target" to a value of 0 in accordance with the recommendations in the paper.

One might ask, as we did, what does "wafl_downgrade_target" do? In its TR-3647 paper, NetApp describes the switch as follows: The "downgrade_target" command changes the priority of a process within Data ONTAP that handles incoming SCSI requests. This process is used by both FC SAN and iSCSI. If your system is not also running NAS workloads, then this priority shift improves response time."

I think his description is telling us that the NAS process consumes bandwidth when there is no NAS work to do. Also, given the NetApp messaging around unified storage architecture, a recommendation to use this switch seems like a bit of a contradiction. Would you consider it normal to be asked to set a switch that generates the following response? "Warning: These diagnostic commands are for use by NetWork Appliance personnel only". Last but not least, this switch resets itself if the array reboots. I'll leave it to the audience to draw their own conclusions as to whether use of this switch is truly a recommended practice in customer environments.

Once the array was freshly initialized and everything was set up, we ran the test and observed the results of roughly 2200 average disk database disk transfers/second per host. Within noise levels, this recreated the results as posted in their ESRP paper.

The main problem we have with how NetApp did this testing is that after the initial run, every time this test is run it runs slower than the previous time it ran. The 2nd run showed results of approximately 1980 transfers/second per server, about an 11% drop. By the fifth run throughput had dropped to approximately 1555 transfers/second per server - a 30% drop. After a couple more runs we were down to 1450, 34% slower than the first run.

I didn't have the patience to run enough times to figure out where this decay curve flattens out.

At this point I decided to run a "reallocate measure" against one of the database LUNs, and the FAS reported the value to be 17. According to the NetApp man page for Reallocate Measure: "The threshold when a LUN, file, or volume is considered unoptimized enough that a reallocation should be performed is given as a number from 3 (moderately optimized) to 10 (very unoptimized)". Allow me to translate - the database LUNs are very fragmented. For those who might be confused by the use of the word fragmentation in this context, this is not NTFS fragmentation - its WAFL fragmentation.

Now things were starting to make sense. We were seeing the same sort of decay curve as shown in the IOMeter results posted in Making Sense of WAFL - Part 4. Every time the test is run, the random component of the Jetstress database accesses fragment the LUN further and the throughput numbers get worse. An array like EMC CX or HP EVA wont undergo this sort of decay curve since these arrays do not have internal WAFL-fragmentation problems like the FAS does.

That's not all. After the throughput test, Jetstress executes a checksum test of the databases to be sure the array did not corrupt any data. After a few runs I noticed an interesting pattern. On the FAS, the length of time needed for the checksum calculation also degraded as the database LUNs went through their WAFL-fragmentation. When the LUNs were fresh and defragmented, the checksum calculation took about 2 hours. By the fifth run, when the database LUNs had a WAFL-fragmentation measure of 17, the checksum calculation took over 10 hours - a 250% slowdown To summarize we saw 34% slowdown on database throughput and a 250% slowdown on checksum calculation by just letting the ESRP test run for about 48 hours before taking measurements.

So, drawing this to a close, I think there is a reasonable argument that NetApp should have results more like 1450 (or less) disk transfers/second/host as opposed to the 2220 transfers/second/host they did post. Most would expect that results in a test as visible as ESRP are measured after a reasonable burn in period. After all, when someone runs MS Exchange, they usually run it for longer than 2 hours.

Tweet this!

Thin Provisioning with the XP Disk Array

CalvinZ — Thu, 24 Sep 2009 04:49:00 GMT

By Tilman Walker, HP Enterprise Storage Consultant

Imagine a customer that is the world leader in their market (no specifics, but they are in the environmental friendly energy business). The customer environment is very (!) dynamic - and this is mostly due to their fast business growth. In their environment it is hard to perform proper capacity planning.

About 12+ months ago the customer had outgrown their EVA installed base and was looking at some "big iron" - so the account team offered the HP StorageWorks XP24000 with Thin Provisioning (THP) on the complete frame. HP and the customer perception was that THP was the ideal approach for this environment:

Allowing them on-demand fast creation/allocation of additional LUNs (change comes unpredictable in their environment)
Ensuring optimal performance by leaving data distribution to the array (largely offloading the data layout work from the storage administrators)
Brings the EVA ease-of-use to the high-end environment

Said and done: THP was implemented on ~400TB spread across 2x XP24000 with ~300 servers (mainly Windows, some VMware, some Unix). Data was migrated from the EVAs using External Storage/AutoLUN. What worried the customer originally was to run out of space in one of their THP pools. Since then, their worries have ceased and space utilization is under control - of course, the first capacity upgrades are already under way.

Net result is that the customer is very happy with THP (just confirmed in a meeting!). THP is a perfect fit to allow them to survive in their dynamic environment. Performance measurements show a perfect average response time across all LUNs (as you would expect from THP). But, of course, a big part of this superb customer satisfaction is owed to the great HP Services personnel on-site.

So all in all, a well-working, stress-free XP Disk Array with THP environment. All I wonder is: why don't we use THP in considerably more customer environments!?!?!?!

Tweet this!

HP LeftHand on the VMware Community Podcast

CalvinZ — Tue, 22 Sep 2009 20:15:00 GMT

By Calvin Zito

Last week, I was invited by John Troyer, the host of the VMware Community Podcast, to join his weekly podcast. I met John at VMworld at the beginning of the month and he needed a partner to be a guest on the podcast. The format is a Q&A with the live and chat audience. On the call from HP were:

John Spiers, former CTO and found of LeftHand Networks, now our HP LeftHand Evangelists
George Wagner, Product Marketing Manager
Brad Katz, Support Engineer focused on integration with VMware
and me, HP Storage Guy aka Calvin Zito

I learned a lot and thought you might benefit from listening to this too. However, I can't figure out how to easily embedded the podcast here on my blog so let me give you a couple of options to listen to it:

Click on this link to open a pop-up streaming version of the webcast (note - it's about 55 minutes long)
Right click on this link and select "Save as" to download the MP3 file - it's a 24MB file

One question that came up during the podcast was a discussion about the pricing of our HP LeftHand VSA (Virtual SAN Appliance) software compared to a physical iSCSI-based array. We've talked about VSA on previous discussions here so I won't define it - if you're not familiar with it, click here to check out the product page where you can learn more. Someone on the podcast said that the cost of two VSA licenses was $10,000. and what's the point when you can get a cheap iSCSI array for that. So I wanted to talk more about that. First, the $10,000 price is a bit high. The U.S. list price is around 15% less than what was discussed on the call. So why is there value in software that can take direct attach storage on an ESX server and turn it into shared storage? Here are a bunch of them:

We have a cheaper iSCSI based arrays in our portfolio with our HP StorageWorks MSA family or our recently announced X3000 so it's not as if we don't know that you can get cheaper physical disk arrays.
You have to factor in up to 10TB of disk capacity which is what a single VSA supports - so compare the cost of 10TB of a physical array to the VSA allowing you to share up to 10TB of DAS that are probably sitting there today wasting away.
You get up to 10 VSA licenses with our HP LeftHand P4000 Virtual and Multi-site SANS. An incredible value.
We provide bundles with our servers that make the total purchase of the whole infrastructure - server, network, and storage - very attractive. These are the HP Virtualization Bundles that I've mentioned here previously.
VSA provides all the value of our P4000 SAN including replication, thin provisioning, Smart Clone, Snaps, Volume Copy and more. Last I looked, one competitor was charging an additional $60,000-80,000 for these value add features that are included FREE with both our VSA and P4000.
VSA can be spit across sites. A traditional iSCSI SAN - and this is key - can not.
With VSA you can manage other SAN technology behind it if it is shared as a LUN to the server with VSA.
With our BladeSystem, VSA can take advantage of existing Flex-10 infrastructure to manage QOS of your bandwidth
VSA is software not hardware. It is "greener" and subject to larger discounts for volume.

So with VSA software, we aren't just providing an easy way to turn DAS into shared storage for VMware but it does so much more.

I hope that context helps as you listen to the podcasts.

As always, you can follow me on Twitter by going to http://twitter.com/HPstorageGuy. I'd love to hear from you and talk to you more about all things storage.

Tweet this!

My very late VMworld summary

CalvinZ — Mon, 14 Sep 2009 20:21:00 GMT

By Calvin Zito

Ok, I know VMworld ended 11 days ago but last week was more than a little busy with Labor Day and playing catch up. I also had a bit of an excuse for holding off because I knew the video that I have at the end of this post was coming. So thanks for reading this more than a little late summary of VMworld.

HP Super Session

HP had a "Super Session" on Tuesday morning. There was a great storage demo and I'll have some details (a video) on that. I have a lot of notes from the session but I'm only going to cover it at a high level.

Our Executive VP of the Technology Solutions Group Ann Livermore kicked the session off. The session title was "Stop Virtualizing Servers, Start Virtualizing Infrastructure". Ann began by talking about industry trends: data center transformation, the information explosion, and delivering everything as a service. She went on to say that the challenges that IT face are around being able to deliver what the business needs today while preparing for tomorrow and working with a legacy infrastructure that is rigid and complex.

HP's answer to this is a converged infrastructure. This will be built on standard components where the whole infrastructure is virtualized: servers, storage, and the network. Our vision is to do this in a way to unify and optimize the data center, taking an integrated holistic approach. And make it easy to manage - both the physical and virtual infrastructure.

Ann highlighted that HP can deliver this the way our customers want - in house, outsource it to HP, or parts of the service delivered via the cloud and integrated into the customers environment. Ann then briefly discussed the announcement we did on September 1:

The HP Virtual Desktop Infrastructure Reference Architecture for VMware View addresses the performance bottlenecks and management complexities of other offerings
Direct administrator access, through VMware vCenter, to the physical infrastructure to manage server health, power use and remote control for the first time with the new HP Insight Control software for VMware vCenter
Simplified storage management by monitoring and configuring HP StorageWorks EVA within a virtual machine using the new Command View EVA management suite

Ann then invited Mark Potter, Senior VP of Enterprise Systems and Networking and Rob Taylor VP from EDS. Mark talked about managing virtual infrastructure as being top-of-mind for customers according to the latest "The Info Pro" wave study, and in fact the #1 issue of managing and monitoring virtual infrastructure jumped from the #11 issue in the previous wave to being the #1 issue in the latest wave.

During the super session, Adam Carter, HP LeftHand Product Manager, came out and gave a very impressive live demonstration of a single SAN environment in an ESX cluster. In the iSCSI-based SAN, Adam had set up two HP LeftHand P4000 arrays that simulated being stretched across the SAN in a multi-site configuration. While the distance between the multiple sites was only 10 feet, Adam said that depending on the WAN between the sites, the distance can be 100 miles. He also said that with the P4000, the software required to set up this disaster tolerant, high availability solution is included free. I grabbed a low-res video of the demo Adam did:

(Please visit the site to view this media)

What's impressive about this is that with traditional arrays, you'd have to set up two SANs, one at each site to have the fail-over capability. I looked at this recently for one competitor and just the software we're talking about is between $30-60K. And again, with HP LeftHand, it's all included for free, nada, ZILCH. Very impressive set of features that are included.

Other impressions of VMworld

Stephen Foskett organized a storage Tweetup on Tuesday night - I met so many people from both the vendor community as well as storage analysts. It was a big highlight of my week and was great to be in one room with a lot of the very smart storage people I engage with in the industry. I also got to spend some time with Alex McDonald from NetApp. If you've read our blog, you've seen some of the many conversations we've had with Alex and his other colleagues at NetApp. We didn't talk too much about our day jobs but it struck me afterward that it was good to be able to just hang out with other storage vendors that we vigorously compete with and have a beer.

Wednesday night was the VMworld party. That was a great chance to unwind and just have some fun. Earlier in the week, I had met storage bloggers Devang Panchigar and Ed Saipetch; it was fun hanging out with these guys along with Stephen Foskett and John Troyer (John manages social media at VMware). Here are a couple of pictures:

Me and Stephen Foskett at the VMworld party

John Troyer, Devang Panchigar, and Ed Saipetch rocking out to Foreigner.

I have a couple of other posts that I did around VMworld. Here's a short summary of what those were and links if you want to check them out:

HP Data Protector for VMware (podcast)
Virtual SAN Appliance for remote/branch office VDI (podcast)
VMworld event summary with Paul Jones, VMware alliance manager (podcast)

A couple of the negative sides of the event were:

The venue was too small for the number of attendees. Of the fourteen sessions I signed up for (several weeks ahead of time), six were full and I couldn't attend them without getting in the "standby" lines. When I saw those lines, there were more people waiting than seats in the room. The fee to attend isn't cheap (I paid over $1500 even though HP is VMware's best partner in terms of sales) so you'd expect that you could get into the sessions you want to attend. Talking to a former colleague of mine at HP who now works in the field for VMware, he told me that many customers (especially in government) are hesitant to send people to an event in Las Vegas (where they can accommodate much larger crowds) because it's perceived to be a boondoggle. Either VMware needs to limit attendance or move the event to a bigger venue. Really, there's no justifiable reason to pay as much as attendees do for this event and have so many sessions full.
My wife would tell you that I'm a picky eater - I think it's more that I enjoy good food (I'll eat almost anything expect liver). At VMworld, lunch every day was a boxed sandwich lunch. I'm not sure if it was too hard to feed 12,000 + attendees a decent lunch or if it was a cost savings measure. At HP Technology Forum, breakfast and lunches were hot meals that you looked forward too. The food in the Solutions Expo on the opening night wasn't very good either. Again, my compare is to our HP Technology Forum where there was lots of variety including made to order pasta, fresh sliced Prime Rib and lots of other very good choices. Maybe I didn't wander around enough but the food I found was cheese and crackers and a few appetizers. The one good thing about the box lunches at VMworld is that it "forced" me into the local area and I found a "Farmers Market" that had a great selection of international foods that were very reasonably priced. That ended up being where I had lunch every day.

And now the video I (note I didn't say you all) have been waiting for

While at VMworld, I was asked to have a video crew follow me around to get a sense at what a blogger does at an event like VMworld. I wish the crew would have followed me on Wednesday to get some video of the rockin' Foreigner VMworld party but hopefully you get a feel for the show and what I did at the show as a blogger.

Tweet this!

Harnassing the power of the cloud podcast

CalvinZ — Fri, 11 Sep 2009 22:23:00 GMT

By Calvin Zito

It's been a busy week since returning from VMworld and frankly I still have a blog or two about VMworld but I'm probably not going to get to those until next week. So for now, I came across this podcast talking titled "Harnessing the power of the cloud" hosted by Dana Gardner, Principal Analyst at Interarbor Solutions. Pete Brey, WW Marketing Manager for HP StorageWorks, who has blogged here recently about IBRIX is one of four panelist discussing cloud computing. Pete talks about delivering to market classes of scale-out storage and delivering storage platforms that are simple and easy to use. He also mentions an HP StorageWorks customer that is using cloud-based storage today. This is worth listening to.

Here are a couple of links with more information:

More on cloud
Free copy of "Cloud for Dummies" (Note: Registration is required for this - I'm going to get one for me because I am admittedly a cloud dummy!)

Tweet this!