Today, on SAN business, they rely on the OEM partner EMC, which also direct compete with many of the EMC partner at the same time. Equallogic became 2nd option to offer to DELL customers, but we do not see huge pickup in large enterprise environment due to limited protocol supported in single platform, as we are heading to UNIFIED Storage era. Overall, I think this could be visionary bid for DELL to move forward to offer more option to their customers.

View the full reports from here.

I do not see much information so far and If you are interested to be part of the contributor, click “Apply to be a Writer” on top of the page.

Click on Dell TechCenter VMware Technical Wiki page here or http://www.dell.com/vmwaretech. Enjoy!

Equipment List

1. 2 x R710 with Intel 5530
2. 2 x PowerConnect 5424
3. MD3000i with 15 SATA Disks
4. Software ISCSI initiator from vSphere 4

I was impressed with the functionality of the Dell PowerConnect switch which provide the important features as link aggregation, jumbo frames, ISCSI optimization and etc. Here is what I did. I had enable the jumbo frame on the specify port that connected for the storage and ISCSI connectiones. At the same time, I had also turned on the MTU configuration and jumbo frame setting from the MD3000i management console. You may need to repeat the same action for every data ports that provided by the storage controller on MD3000i. Enable the Jumbo frame and configure the MTU value of 9000 on it. On the PowerConnect switch,I had configured the specify ports on ISCSI optimization and jumbo frames enable. Now it come to the vSphere level, which I had to manually enable the ISCSI vswitch to support the jumbo frame and put in the right value for the MTU.

Command for reference

#esxcfg-vswitch -l    
This will allow you to list all the virtual switch you have on the ESX server

#esxcfg-vswitch -m 9000 vswitch1  
this command is to enable the mtu value of 9000 for every nics that connected to the same virtual switch which provide the storage access to ISCSI

#vmkping -s 9000 192.x.x.x   
test the jumbo frame setting

The outcome of the jumbo frame enable, I had able to achieve higher throughput on the MD3000i I had and I am happy with the performance of the storage.

Performance wise, we may know that the Equallogic ISCSI might not beat the huge SAN box which easily cost you double as your TCO on ISCSI. I would like to share my finding relevant on the features it bundle with Dell Equallogic. In FC SAN, we are able to achieve performance and functionality, which require always additional license cost and expensive infrastructure to support it. Today, ISCSI provide more flexibility in term of FC due to the common understanding we all have on the IP technology which we deal with it everyday.

In Equallogic ISCSI, you will entitle every features which bundle together with the storages you purchase.

• Snapshot Volume Manager
• Thin Provisioning
• Raid 5, Raid 50, Raid 10
• Auto Load Balancing
• Web Base Console
• DR Replication
• Storage Replication
• Volume Clone

The details of the available features is more than what I am stated here of course. Imagine if you own a FC SAN today, you may end up paying additional charges for every piece of licenses you require of the functionality. Beside this, virtualization and VMware is become a main player for every Data Center today. Same with Equallogic, it had also become a powerful competitor to compete with the major vendor like NetApps, EMC, HP, HDS, IBM and etc.

Whithout comparing the cost and performance, I am really impress with the simplify management provided by Equallogic. You will not require to be long waiting of the web console, and it is user friendly and easy to be managed. Compare to FC SAN, you will require certain level of skillsets and patient for administration which you may suffer from the slow loading from the console always. Additional to that, FC SAN will become slower when the number of spindle and workload is increase, but Equallogic has it advantage with every array will increase the processing power and throughput. Personal experience, I am only require less than 10 minutes to setup and configure my Equallogic Storage array, and able to start provisioning right after the configuration done. Is Really Fast!!

I run the performance test on my ESX 3.5 server to compare the I/O performance Vs FC SAN, I realize that the performance is acceptable with the amount of money we pay for it. Simply because you may not virtualize the servers which require the real I/O intensive performance. I am able to achieve approximately 140MB/s with FC SAN for read/write, with Equallogic, I manage to achieve 115MB/s as maximum throughput in my VM. Again, this may be impacted due to the software ISCSI initiator. ISCSI HBA will able to improve the performance with minimize the overhead on ESX host. For my test, I only manage to run with single array. If we have more array in the future, it will able to increase the disk performance and storage throughput. 10Gb Ethernet are also on the way to the market next year. Equallogic are also design for SRM solution which provide by VMware to simplify the DR solution. With this storage solution, we will no longer require a big network pipe for SAN storage replication as we did for the FC SAN previously.

Latest array PS 5500E are providing 48TB in RAW with SATA, which will be a good option for DR solution to provide cheaper hardware cost & better functionality. If I has been asked to reduce my CAPEX for SAN purchase, the only option I can think now is ISCSI as my option. Cisco 3750 is the recommended switches for DELL Equallogic, it is much more cheaper if we compare to the brocade FC SAN swithces.

Never the less, FC SAN are still the best option in term of reliable and performance, but as it is a tough time now for budget spending, I believe Equallogic has provide us an additional option with limited budget.

This features provide more option which will allow the users to snapshot, backup, and restore the files, volume, VM or even a single file that you need. Many of us may think about using the VCB for our VM backup today, the Dell Equallogic had provide some interesting package which allow us to avoid of VCB in our environment, and provide better backup and restoration process.

If we talk about disk base backup, which is VTL, it always cost involve in term of disk space and software licenses. With the latest features from Equallogic, we will able to avoid the extra investment require on VTL, but provide the similar functionalities on disk base backup, and from disk to tape backup. If I bought the equallogic previously and sign up with the maintenance, I entitle the upgrade of the new features today. It will be a excellent surprise for my investment. As economy crisis, IT budget is been tight and require to work smarter, this should be a great news for the consumers. Personally, I will still say that the 10Gbe will be my option as to get rid of the fiber channel storage that we current use for VMware. As 48 spindles in a single array, we may need the bigger through put from the array to reach the client always.

According to DELL, we should able to see the official launch on 10Gbe on 1st quater of 2009.

1 of the good example, IBM had ship their regional office to Malaysia from Singapore previously, because they saw the potential market grow in this country as well as more talent source in Malaysia for IT related area. Many of the IT giant are setup the IT hub, data center as well as corporate office in Malaysia to enjoy the TAX free holiday as well as cheaper real estate cost and man power resources. There are HP, IBM, DELL, SHELL, EDS, HSBC, Prudential and etc around in Malaysia. Guess what, most of them are even having their production data center in Malaysia itself.

Now we go back to VMware, virtualization is growing in Malaysia, but the present from VMware are more relay on the partner in here. Training are not provided as what been provided in Sinagpore or Australia. Most of the time, even in singapore training center, the attendees are not Singaporean. As economy crisis now, to attend a training in Singapore will be 3 times more expensive for someone who attending a training in Malaysia. If I not mistaken, they have less than 10 employees in malaysia for VMware itself. It just not big enough to attract the confident of the potential giant customer from Malaysia market if you do not present yourself strong enough as your competitor.

Some customer are willing to go with Microsoft Hyper V just because the support, present and Microsoft Malaysia. As you can also see the Teched having in Malaysia every year for SEA, I believe VMware should consider their option to ship the conference location to Malaysia instead of Singapore. Of course, we do hope VMware will consider a VMworld Asia in the future and be held in south east asia.

Before you can use blade, you require higher power consumption per rack to support approximately 30 to 32 blades per racks on 42 servers rack. At the same time, the cooling unit design in you DC require to be customize to ensure your blade chassis is working in perfect condition. Once you have this, then you may able to start think about Blade.

ESX on Blade have been some idea I personally thought before. The products I specify looking is the latest DELL Blade M1000e. The power and cooling in my DC is not a big issue. When I do analyzed the possibilities, I found couple of show stopper to deny my decision to move forward on that. As the enterprise architect point of view, Blade will be more suitable to consolidate those machine which require to run on physical VS Virtualization. The reason of that, is not really the matter of CPU or Memory you can have in the single blade, is really about the redundancy and performance we focusing on our virtualization. The limited number of pass through, NIC, and FC per blade is really not able to meet the number of VM we tried to achieve per host. We require redundancy, teaming as well as performance through put in term of networking and storage with the ESX servers we have. When we do calculate in term of cost per VM, the number had not show up as significant saving as we expected.

In additional to that, the more ESX machine we have in our Virtualization farm, it always require additional efforts to manage it for long term basis. There are many cases that users had built the ESX server with only 2 gigabits NIC for VMnetwork, which end up facing the performance issue in term on the Networking as well as the single point of failure. Virtualization is not performance sacrification. If we do plan properly, we will gain performance in virtualization vs under utilization physical machine.

Here is those finding I have and I will say that the Blade will not fit the virtualization requirement to achieve High availability and performance requirement. If we will have enough money to be spent on Blade environment, I believe you should have sufficient budget to go for something more suitable like R900, R905 and others 4U servers which provide more memory and CPU you need.

High Gas/Petrol price become an global issues, no matter which region or which country are you from, this had become and issue which drive the Operational Cost for a Data Center to keep alive from daily basis. In Malaysia, the goverment had recently increase the commercial eletricity for 26 %. Imagine that if you DC consume RM 30000.00 a mount from power perspective, you had to pay RM 37800.00 a month. that had been significant impact the entire IT budgets plus the operational cost. As IT always be the main driver for most business today, we may need to provide a highly efficient Data center solution which able to recover the ROI within the shortest period as possible. Virtualization & Consolidation had come to the point for this.

As if we compare the power consumption from major chip maker like AMD and Intel, the watts per processor had stack and remain the same for the last 3 generations at least. The only improvement they made was really the perfomance per watt. 6 cores and 8 cores had been down the road, I will be strongly encourage who had not adapt to virtualization need to start virtualize or prepare to virtualize 80% of thier production environment.

My environment currently had running the entire DR solution with VMware technology. In production, I do have more than 50 production VM which provide web hosting, middleware, file & print servers and etc. Imagine you had a tight budget with only 50k USD, how many of physical servers will you able to buy from there? and wat about the amount of power you need to absorb on monthly basis? That is the real cost as many of you may had not see the electric bill. For my case, my cost center had to paid for the power bill ourselve.

To achieve 15:1 in VMware is no longer a big thing with the high capacity server from DELL, HP and IBM. By doing this, you can avoid the multi million renovation to expand your DC which may had nearly full. Technology is cool, but again as human being, we had to work smart. High efficient Data Center sometimes do equivalent to High Productivity of the support team too.

Couples of important point that need to be consider during the implementation of Virtualization is :

1. Hardware compatibility
2. Storage choices
3. networking equipment
4. System architecture
5. Support and operation maintenance
6. CPU model and brand ( AMD or Intel )

This topic I will be more specify to the server model for virtualization. In couple of test and real case experience, I do compare the cost, performance, services and reliability within IBM, HP and DELL before I decide to move forward with my final decision.

DELL had recently launched the R900 and R905 this year specifically to support for 4 physical CPU sockets which able to host up to 16 cores of CPU with the latest quad core technology from both Intel and AMD which allow the memory to scale up to 256GB of physical memory if you go for the 8GB/module in DIMM slot. 1 interesting you may need to look at the servers is the on board 10Gbps capable network ports. The server itself had come with 4 on board NICs with capable to run the next generation ethernet 10Gbps. As network bandwidth become a big challenge after the virtualization, this connection will provide better cabling management and of course higher throughput once the 10GbE in place. The additional PCI slot on the 4U servers do provide flexibility to add-on fiber channel HBA or additional Ethernet card to provide redundancy and fail over path for HA purpose.

I will also suggest to stick with 128GB memory instead of 256GB as you may experience CPU bottleneck once you have the higher number of VM running on the production ESX. Guess what, a lot of the consultant will always encourage we configure 1 Vcpu or 2 Vcpu as starting for each VM we created. But in real case, we will have to make it to 4Vcpu or 8Vcpu in the future, that will due to the business grow and data processing increase from time to time. If we virtualize the servers and sacrifice performance, that will not become a big selling point for virtualization. As you may need to re-think, the storage for VM is mostly running on SAN or ISCSI, which may be more expensive solution compare to local HDD.

4 physical CPUs and 128GB memory is the best option at this moment as if you plan for HA or DRS in your environment, as a safe play to minimize the down time, I will not encourage to host a huge number of VM on 1 single hosts. You may need to consider if you have 40 VMs on 1 single host, the hardware failure on 1 host will bring down the 40 VMs which is in production.

For warranty and services, DELL always commit better services to my company with a more reasonable and affordable pricing. you may enjoy the same benefit from HP but you require to pay more in that case. For IBM, I will say x86 platform servers are just not their focus, as they always slow respond on bug fix release on their firmware or driver on x86 platform.

I would like to share couple of my finding in the real Prove of concept and test that myself had personally setup and experience here. VMware do support hardware base ISCSI HBA and software base ISCSI through its VMkernel. Couple of thing that you may want to consider before we really decide to proceed further with the ISCSI. Networking become more and more important since the last decade to be operate most of the important pieces in the Production Data Center. Networking had also become the major issue for most of the time especially in VM environment which may need a bigger bandwidth to support the multiple VMs that been consolidated to single Physical Host.

I had been invited by the Equal Logic vendor to run the real test with the demo in my datacenter. Below is the major finding I would want to share

Test Equipment
Server – DELL PE 2950 8GB and 2 x Quad Core 2.0 Ghz
Storage Switches – DELL Gigabit Switches
Storages – Equal Logic PS 5000 with SAS HDD
Operatin System – SUSE Linux, Windows 2003, ESX 3.5

Impressive

1. High Processing speed due to the processor build in for each storage bay. It can be scale up to 12 storage bay in the cluster basis. Each enclosure contains 16 physical spindle drives with SAS technology
2. Simplify management – the entire process to configure the storage to be useable is less than 15 Mins. Its all web base and able to run on the open source browser such as firefox
3. Maximize through put through the software ISCSI initiator been tested on servers and my personal laptop. It able to suck up 97% of the gigabit through put from my laptop gigabit connection and the server gigabit connection as well.
4. High redundancy with global hotspare configuration recommended
5. Impressive load balance feature which able to scale from storage and perfomance perspective. Additional enclosure will provide additional spindle power and processing power from the stroage bay. Compare to Clariion series currently, which always provide slow perfomance when the storage are only 60% populated.
6. Shorter commissioning process and reduce provisioning time line. almost plug and play
7. RAID 50 available as an option to be configure during the provision process

Disadvantages

1. Now is time to think about long term strategy in Data Center before it become another mess as old days which we manage the Fiber Channel without director switch with fabric port. In order to gain the perfomance and scalability, each of the network connection, uplink and downstream will direct impact to the through put for each storage box. In Fiber Channel world, as if you run in 4Gb FC switches and cascaded, you will at least have 8Gb redundancy and load balance trough put from switch to switch perspective. In ethernet, we may have to look at 10Gbps uplink from switches perspective. Conclusion, the switch uplink will direct impact the entire storage throughput to the client
2. As you may start to manage the ISCSI with distributed or seperate from the normal ethernet in DC, this could generate extra workload from management perspective as well as support operational overhead
3. ISCSI over 10GbE are in roadmap but yet to be release, as the current gigabit ISCSI price seems to be little bit too high to be compareable with the fiber channel SAN.
4. Software ISCSI had higher overhead in the Server resources compare to FC HBA storage

Summary
My opinion here is to wait for the 10GbE release on the ISCSI before to really decide for ISCSI to replace the major FC SAN Storage for High Availability purpose. As for now, it may be suitable to be deploy in Disaster Recovery Solution, Development VM Farm and Unmanage location example factory, branch office which do not have the complete Data Center solution. This is specifically for solution related to ISCSI in VMware.