Anyway, day three of EMC world was quite entertaining, even though I didn't get to see any session I can write about because they were all still under NDA. They envolved the Clariion and some featuers of the new V-Max system, and I wrote up some blog posts already. These will be posted as soon as everything has been GA'd.
Besides the stuff I can't talk about, we again had a lot of rain. Even so much that the phrase "record breaking weather" came by on the television. Since the weather was not that good, it set the mood for my test. I tried to get certified at the associate level by taking the Storage Technology Foundation exam. I hadn't taken any classes before, but tried to study from the ISM book and try to wing the test. That didn't work out too well. I missed certification by 3%, and the SAN and NAS part were not the parts that gave me problems. But I will continue studying and take the test again. I'm quite certain that I will be able to make it the next time I take the test.
I once again need to give a compliment to EMC and to ZDnet for creating the bloggers lounge. You could think of it as a small space created inside one of the main floors that gave you the much needed power and caffeine to continue through the day. I have to say that I have met lot's of interesting people throughout the convention, but somehow these people accumulated in the bloggers lounge. For example I got to talk with Chuck Hollis (Global Marketing CTO for EMC) in there, and I will be writing more on the conversation in later posts.
What really made my day, and what made it to one of the most valuable days for me was the networking and teamwork done that day. At the company where I work we were given the opportunity to be the first German customer to test out the new V-Max system. Actually, were so up front in the testing schedule that the things were delivered in the old DMX casings, and without any labels or port infos on the back. We needed the machine up and running by Friday as we were doing some tests and it was about to mess up our schedule quite badly.
In the end, we ended up working with people from SAP, EMC and GOPA backstage behind the Symmetrix booth. The exhibitor booths were all cleaned out, and were taken apart and transported by forklifts back in to crates for transport. That was the point where we were asked to relocate. I mean, having a forklift run over you will not make you any more productive, so I could understand the request.
Anyway, we ended up back in the bloggers lounge where we were actually able to hook up the V-Max to our systems via iSCSI. I think we are one of the first, if not the first worldwide, to connect to the new V-Max this way. We ended up having several smaller problems, but if I may give you one tip. Alway make sure that when you enter the infos for the iSCSI-target, you use the [qbbr=Fully Qualified Domain Name]FQDN[/abbr]. Five minutes after solving the problem, the convention was closed for the day, so we were kicked out.
The great thing was that everyone worked together to get this issue resolved, but provider and customer alike. Sure, this could have been done with people spread out over the globe, but it was just easier when you had all of the people at the same place, and they were able to see what the other person does and directly exchange ideas. This also shows one of the major strengths of these types of events. Sure, they are quite expensive, and yes it's not all work and people have a lot of fun. But it also gives you great networking opportunities, a means of direct exchange with peers and the option of finding the right people for problems you are facing and trying to solve.
All in all I would say that even though I did not visit that many session, it was still one of the most productive days for me!
Just as a small sidenote, I got my first introduction to the Symmetrix Management Console that day since we did not have any out-of-band management set up yet. I have to confess that the version of SMC installed was quite old, but I saw some bugs that I reported back, and I am hoping that the newer versions will no longer display these problems. You wouldn't want to find these on the V-Maxes that have been delivered to our customers (think of LUNs that were no longer masked but still visible, and the other way around).
So, what happened here? Well, there were two main topics that are both related to the new systems that was introduced a while back by EMC.
There was a session on the changes in the new Symmetrix Enginuity version 5874 for the new V-Max system. We were informed that among others the RAID-engine was redesigned. The new version allows for only 1 mirror per device instead of the previous 4 mirrors per device. They now allow all of the features on all of the RAID-levels, and they introduced the possibility of VLUN migration.
Also new was the support for large volumes. The limit increased from 16GB to 240GB. This should help a lot of people who were required to create large metasets before. Also, you can now create 512 hypers per drive.
You will find some changes in the management and provisioning section for this new version of Enginuity. Dynamic provisioning received some enhancements that reduce the number of steps required to present your storage to your host. You now create a storage group, a port group and a device group or initiator group. After that you are basically done. Create some templates once these prerequisites are created and you can present your storage with relative ease. People will also find that bin file changes are speeded up on this new release.
SRDF also received some upgraded numbers. The maximum number of SRDF groups is now at 256 groups per array, and 64 groups per FA-port. Still, you might want to reconsider splitting up all groups on 4 FA-ports.
They also introduced the new so called "DLDEV" or Diskless R2 Device, or in Symmetrix speech a so called R21 device that allows you to cascade to a 3rd site using SRDF/A. DLDEVs need to be on a V-Max though.
After an interruption I got in to a private V-Max session a bit later then I planned, but I still managed to get some new information.
Currently one of the less official recommendations that you will find is that if you have a large datacenter, you might consider distributing some engine groups in the various areas of your datacenter. Current distance limits you will find are at around 100 meters. Simple reason for this distance limitation is the fact that you are working with latencies. If you take the distance up to 100 meters, you will find that latency will increase with a factor 27. Upping the distance could create some unforeseen issues.
One of the questions was that with FAST we will see a tiering over the various storage media, but what will EMC do to tier my storage on the various storage classes. In a normal situation you want your mission critical data on high end arrays, and work your way down. One could imagine something similar to FAST on a different level that would allow you to better utilize the various availability levels of you storage hardware.
The engineers implied that they are working on this, but unfortunately would not go in to a great deal of detail.
One of the most heard questions so far is probably "When will FAST v2 be coming to the V-Max?". Current timeline indicated about 1 to 1.5 years, but no one was willing to talk about any of the technical details. This raises the question how far they actually are with the FAST technology, and that's a question that produces the same "no coment" remark and look. What they were able to tell though was that they are planning to introduce FAST on the Clariion series array, which will be a major money maker when they are able to deliver. Currently you will find around 300,000 CX's worldwide, and one can only imagine how many people might be interested in purchasing this technology, if and/or when it works. A first version of FAST v1 should be introduced at the end of the year according to Barry Burke.
And even on a V-Max the newer FAST version will bring in some major cash. You will find it as a separately billed option when you would like to use FAST for fat LUNs and thin LUNs.
However, one general statement was clear. "FAST is coming!"
The second main keynote was given by Paul Maritz. After Joe Tucci finished he handed over the stage to Paul, and Paul gave us an overview of what is new with VMware. VMware started off back in 1998 with a workstation version. Customers soon realized that the savings potential was in the server segment. VMware the started developing server based products. And the rest, as we say, is (known) history.
Even though VMware now has a very large customer base, there are still a lot of companies that simply can't switch. They would like to make the transition to a virtualized environment, but they are simply unable to do so do to various reasons. One of the main reasons to switch to a virtualization platform is to increase the flexibility that you have. As Maritz stated, "Virtualization is the most obvious
way of getting more out of multi-core CPU's".
According to VMware, vSphere is no longer about individual hypervisors. They are in the business of a new software layer. that will help customers to achieve the maximum return out of their invest, and to have the possibility to scale on demand. They way to go according to VMware is SME clouds. One might think that in the current economic environment the SMB market should also be of interest, but Maritz did not say anything about the SMB market.
Next item was the definition of one of the most popular buzzwords at this moment. The question was, "What is a cloud?". The answer? "People associate a cloud with good and with anything they like to see in their own datacenter. Clouds are associated with "infinitely flexible" and "infinitely scalable".
This state of mind brings some problems according to VMware. The enterprise can not (be bothered to) write custom applications that are required for a lot of cloud solutions. Application stacks and pillars that are known are built, along with secure environments, but they are hard to connect to the currently offered cloud solutions.
Challenges include the question that once you have made a choice, how do you check out an application that has been checked in to the cloud? They brought the example of "Hotel California" by the Eagles; "You can check out anytime you like, but you can never leave".
VMware developed a solution for this. They introduced a new layer by the name of vSphere. This will allow you to remove the hard link that exists in current virtualization implementations, and allow you to implement the currently existing stacks.
vSphere is the "cloud operating system" according to Maritz, since it's platform is open to partners as well.
vSphere allows you to run all you existing applications. It can be used as the foundation for your own virtual datacenter, and I/O-performance has been on heavy emphasis for vSphere. It is needed and even required for some virtual data center's.
Joint team tested with 1.000.000 million I/Ops, random read and writes. That impressed the heck out of me to be honest, and I could see the same look on a lot of the people who attended the event. Also, the overhead of virtualization was reduced to <= ~15%. An example of load was 5x the current amounts of transactions that are being processed by VISA on a VMware system combined with the V-Max architecture.
Another cool feature was the one thing that will take v-Motion to the next level. The feature is called "Continuous vMotion". Basically, it's full software fault tolerance by using a second instance to move out of rack. They did a live demo of this feature, and I was quite impressed. Also, this opens up a ton a new possibilities, and I will be blogging about some of the ideas that I have this week. They offered the same feature for the storage environment, called "Storage vMotion".
A recap of the sessions of day 2 will be posted, but since I had a lot of NDA sessions I can't post everything just yet. I will probably combine day 2 and three to keep the posts interesting, and I will post more as soon as the NDA's are lifted.
Cool things are going to happen, and I was lucky enough to receive a sneek preview. I am looking forward to day number three.
Talk to you tomorrow!
Most interesting today for me were the keynotes by Joe Tucci from EMC and Paul Maritz from VMware. This blog post is meant as an overview and some of the points that I found quite interesting. It is by no means complete, and if you want to get a full overview, then I would recommend that you check out this link to find a more complete recap of the keynotes.
First of was Joe Tucci who started with the main numbers for last year, and gave a focus on some of the main topics for this year. One point he made were the so called "hot topics". Among these were:
• Increased utilization
• Business continuity
• Backup to disk
• Deduplication and compression
• (Automatic) storage tiering
• Thin provision / virtual provisioning
• Unified storage
One of the points he made was the importance that VMware currently has within EMC. The VMware share comes down to a whopping 48%.
We have seen that EMC was one of the first, if not the first, to introduce SSD (or EFD drives. Since the introduction of these drives a market change could be noticed. According to Tucci EMC customers could see a 78% price decrease in the last twelve months for EFD drives. Current EFD drives offer up to 60% more IOPS, 17% lower costs and 27% less power and cooling.
Next item on the agenda were the main challenges when it comes to running your own data center. Main points can be seen as protection and continuous availability in the form of clones, snaps and backup to disk. These measures are normally in place, partially or combined, to ensure continuous availability. Other issues include information security, verification and protection, the prevention of leakage on data moves and then there's security management and compliancy.
According to Tucci we currently have a situation where we work with an information and policy based intelligence. However, EMC is transitioning from a platform to a framework. The same can be said for archiving, and EMC views VMware as an approach that is not agent based (an agent on each instance).
What's next in it? EMC says that the key points are virtual data centers, cloud computing, virtual clients and virtual applications.
Virtual datacenters should share the same basic attributes that a physical datacenter also shows. It needs to be trusted. You need control, reliability and security no matter if you are in a virtual or physical environment.
EMC's answer to this starts of with a question. "What do customers like?". And the answer is probably not that easy to answer, but EMC tried to do so anyway. Some of the things they came up with include that it's dynamic, "efficient" (which is a very broad perception), on-demand and flexible, where you could probably interchange the last two that are mentioned.
Virtualization in the datacenter will create doubts on the trust that one has in it's own datacenter. One of the targets could be to move your own datacenter and convert it to a virtual cloud. VMware can help to federate and help migrate between the physical and virtual tier. In such landscapes we are starting to notice the limitations that are impeded upon us. for example the speed of light is a limit that we need to work around. We can't change these limitations, but this situation requires us to find alternative solutions.
When using a partner cloud, you may have security concerns. Three main pain points can be described; storage, information management and security.
EMC tries to combine the benefits of the various levels and/or solutions and combines them in a so called "federation layer". This should provide a customer experience that is the same, no matter on what platform the customer is working on, be it his own trusted environment or a partner cloud.
So much for Tucci's part. This is a rough roundup of the keynote and there was a lot more information, but I wanted to put this online while it is still fairly fresh in my head. I will be doing a recap of the VMware keynote tomorrow morning.
For now I'm off to bed, and I'm looking forward to day 2 of EMC World.
For now I just wanted to give you a quick overview of what happened and what will be going on today. After flying to the US on Saturday I met up with one of my contacts from EMC. Met him at the bagage claim in the airport, picked up our rental car and after a small struggle with the Garmin we were actually able to go to the Hard Rock Hotel Orlando. Met some people I knew there, after some dinner called it a night.
Yesterday we used the time for some shopping. We were lucky enough that the kind people from EMC who take care of us in Germany collected the badges and the gifts, so I was able to pick up the backpack a little early. It's absolutely great!
In the evening we went over to the venue and enjoyed some drinks, and a great session by the Gin Blossoms. I was looking forward to meeting some people I sort of got to know online, and I ran into Stu, StorageNerve and EdSai. Didn't get too talk too much because of the volume, but I assume I will get a chance today. Got the recommendation from Stu that I shouldn't have twittered as much. Look who's talking....
So, what's up for today? A lot of tweeting. At 9:45 I will be looking at the keynote by EMC CEO Joe Tucci and VMware CEO Paul Maritz. I'm going to check out some Symmetrix session, and I intend to check in on the EMC bloggers lounge. Heard some good stuff about it.
See you later today when I've got more news and when I can give an impression of day 1 of EMC World!