Friday, May 29, 2009

[caption id="" align="alignright" width="261" caption="Supermicro 2021TM-BTRF - 4-nodes in 2U with redundant power."]Supermicro 2021TM-BTRF - 4-nodes in 2U with redundant power.[/caption]

Supermicro's been holding the AS-2021TM 4-node-in-2U platform back for several weeks but finally it's out from behind proprietary OEM's. We're talking about the Supermicro 2021TM-B "mini cluster" of course and we've been watching this platform for some time.

Why is this a great platform for right now? The H8DMT-F motherboard, supporting only 64GB of DDR2/800 memory, also supports HT3.0 links to enable the slightly higher HT bandwidth of the upcoming Istanbul 6-core processors. The on-board IPMI 2.0 management (WPCM450, supporting KVM/IP and serial-over-LAN) with dedicated LAN port and two inboard USB ports (supporting boot flash) make this an ideal platform for "cloud computing" operations with high-density needs and limited budgets.

The inclusion of the on-board Intel Zoar (82575) dual-port Gigabit Ethernet controller means VMDq support for 4 recieve queues per port using the "igb driver" as we've reported in a previous post on "cheap" IOV. An nVidia MCP55-Pro provides Southbridge functions for 6xUSB 2.0, 4x SATA and 1xPCI-express x16 (low-profile) slot. This is a VMware "vSphere ready" configuration.

[caption id="" align="alignleft" width="270" caption="Supermicro H8DMT-F Motherboard from 4-node-in-2U chassis"]Supermicro H8DMT-F Motherboard from 4-node-in-2U chassis[/caption]

Each motherboard is installed on a removable try allowing for hot-swapping of motherboard trays (similar to blade architectures). The available x16 PCI-express slot allows for a single, dual-port 10GE card to drive higher network densities per node. An optional 20Gbps Mellanox Infiniband controller (MT25408A0-FCC-DI) is available on-board (PCI-express x8 connected) for HPC applications.

Each node is connected to a bank of 3-SATA hot-swap drive bays supporting RAID 0, 1 or 5 modes of operation (MCP55 Pro NVRAID). This makes the 2021TM a good choice for dense Terminal Services applications, HPC cluster nodes or VMware ESX/ESXi service nodes.

Key Factors:



  • Redundant power supply with Gold Level 93% efficiency rating

  • up to 64GB DDR2/800 per node (256GB/2U) - Istanbul's sweet-spot is 32-48GB

  • HT3.0 for best Socket-F I/O and memory performance

  • Modern i82575 1Gbps (dual-port) with IOV

  • Inboard USB flash for boot-from-flash (ESXi)

  • Low-profile PCI-express x16 (support for dual-port 1oGE & CNA's)

  • Hot-swap motherboard trays for easy maintenance

  • Full KVM/IP with Media/IP per node (dedicated LAN port)

  • Available with on-board Mellanox Infiniband (AS-2021TM-BiBTRF) or without (AS-2021TM-BTRF)

Server Watch: Istanbul, G34, C32, Itanium and Nehalem-EX

Istanbul is launching in June, 2009 and will be a precursor to the G34 and C32 platforms to come in Q1/2010. To that end, AMD will be providing an overview of its next generation of Direct Connect Architecture, or DCA 2.0, which which separates Socket-F systems from G34/C32. This overview will be available as a live webcast on June 1, 2009 at 11:00AM Central Time. In advance of the announcement, AMD has (silently) reduced prices for its Opteron processors across the board. This move will place additional pressure on Intel's Nehalem-EP systems already weakened (virtualization) price-performance.




We expect to hear more news about Istanbul's availability in keeping with Tyan's upcoming announcement next week. Based on current technology and economic trends, Istanbul and G34 could offer AMD a solid one-two punch to counter Intel's relentless "tick-tock" pace. With Nehalem servers sales weak despite early expectations and compounding economic pressures, market timing may be more ideally suited for AMD's products than Intel's for a change. As Gartner puts it, "the timing of Nehalem is a bit off, and it probably won't make much of an impact this year."




In the meantime, Phil Hughes at AMD has a posted a personal reflection on Opteron's initial launch, starting with the IBM e325 in 2003, and ending with Opteron's impact on the Intel Itanium market by year-end (while resisting a reference to "the sinking of the Itanic"). Phil acknowledges Sun's influence on Opteron and links to some news articles from 2003. See his full post, "The Sun Also Rises," here... As 64-bit processors go, 2003 was much more the year of the Opteron rather than "the year of the Itanium" (as predicted by Intel's Paul Otellini.)




Speaking of Itanium, TechWorld has an article outlining how Intel's upcoming Nehalem-EX - with the addition of MCA technology derived from Itanium - could bring an end to the beleagered proprietary platform. TechWorld cites Insight 64 analyst Nathan Brookwood as saying the new Xeon will finally break Intel's policy of artificially crippling of the x86 processor which has prevented Xeon from being competitive with Itanium. The 8-core, SMT-enabled EX processor was being demonstrated by IBM in an 8-socket configuration.

Tyan Announces "Istanbul Ready" Systems at Computex

Tyan will be announcing full support for AMD's upcoming "Istanbul" 6-core processor at Computex 2009 (June 2-6) for the following system SKUs:

Motherboards:

8-Socket: S4985-SI & M4985-SI


4-Socket: S4989-SI, S4992 & S8802


2-Socket: S3992-E, S2932-SI & S8212



Barebones Systems:

4-Socket: TN68-B4989-SI & GT26-B4989-LE


2-Socket: TA26-B2932-SI



We have no information on the new S8802 and S8212 motherboards or their intended systems at this time. See their announcement card here...

Friday, May 22, 2009

Preview: Install ESXi 4.0 to Flash

VMware's vSphere's ESXi 4.0 now installs directly to USB flash from the install CD without the "funky" methods we've explained in earlier posts. By comparison, the installation process is straight-forward, simple and painless.

[caption id="attachment_591" align="aligncenter" width="450" caption="vSphere ESXi Install to USB Flash (click for animation)"]vSphere ESXi Install to USB Flash[/caption]

After the quick installation to USB flash, the system reboots into ESXi for the first time:

Operton vs. Nehalem-EP at AnandTech

AnandTech's Johan DeGelas has an interesting article on what he calls "real world virtualization" using a benchmark process his team calls "vApus Mk I" and runs it on ESX 3.5 Update 4. Essentially, it is a suite of Web 2.0 flavored apps running entirely on Windows in a mixed 32/64 structure. We're cautiously encouraged by this effort as it opens the field of potential reviewers wide open.

Additionally, he finally comes to the same conclusion we've presented (in an economic impact context) about Shanghai's virtualization value proposition. While his results are consistent with what we have been describing - that Shanghai has a good price-performance position against Nehalem-EP - there are some elements about his process that need further refinement.

Our biggest issue comes with his handling of 32-bit virtual machines (VM) and disclosure of using AMD's Rapid Virtualization Indexing (RVI) with 32-bit VMs. In the DeGalas post, he points out some well known "table thrashing" consequences of TLB misses:
"However, the web portal (MCS eFMS) will give the hypervisor a lot of work if Hardware Assisted Paging (RVI, NPT, EPT) is not available. If EPT or RVI is available, the TLBs (Translation Lookaside Buffer) of the CPUs will be stressed quite a bit, and TLB misses will be costly."

However, the MCS eFMS web portal (2 VMs) is running in a 32-bit OS. What makes this problematic is VMware's default handling of page tables in 32-bit VM's is "shadow page table" using VMware's binary translation engine (BT). In otherwords, RVI is not enabled by default for ESX 3.5.x:
"By default, ESX automatically runs 32bit VMs (Mail, File, and Standby) with BT, and runs 64bit VMS (Database, Web, and Java) with AMD-V + RVI."

-    VROOM! Blog, 3/2009

Thursday, May 21, 2009

Quick Take: AMD Istanbul Update

AMD was gracious enough to invite us to their Reviewer's Day on May 20th to have a final look at "Istanbul" and discuss their plans for the product's upcoming release. While much of the information we received is embargoed until the June, 2009 release date, we can tell you that we've have received a couple of AMD's new 6-core "Istanbul" Opterons for testing and review. We'll look forward to seeing "Istanbul" in action inside our lab over the next couple of weeks. Our verdict will be available at launch.

Instead of typical benchmarks, we'll be focusing on Istanbul's implications for vSphere before the new Opteron hits the streets (remember 6-core is the limit for "free" and "reduced capability" vSphere license). If what we saw from AMD's internal testing at Reviewer's Day is accurate , then our AMD/VMware Eco-System partners are going to be very happy with the results. What we can confirm today is that AGESA 3.3.0.3+ 3.5.0.0+ is required to run Istanbul, so start looking for BIOS updates from your vendors as the launch date approaches. The systems we reported on from Tyan back in April will be good-to-go at launch (our GT28 test systems are already running it require a beta BIOS).

SOLORI's take: We made a somewhat bold prediction on April 30, 2009 that "Shanghai-Istanbul Eco-System looks like an economic stimulus all its own" when comparing the AMD upgrade path to Intel's (rip and replace) where VMware infrastructures are concerned. That article, Shanghai Economics 101, was one of our most popular AMD-related postings yet, and - judging from what we've seen already - it looks like we may have been correct!

While we're impressed with the ability to flawlessly vMotion from socket 940 to socket-F, we were more impressed with the ability to insert an Istanbul into a Barcelona or Shanghai system and immediately realize the benefits. We're going to look at our review samples, revisit our price-performance data and Watt/VM calculations before making sweeping recommendation. However, we expect to find Istanbul to be a very good match to on-premise cloud/virtualization initiatives.

SOLORI's 2nd take: VDI and databased consolidation systems running on 4P AMD boxes are about to take a giant leap forward. We can't wait to see 24-core and 48-core VMmark scores updated over the next two months. Start asking your system vendor for updated BIOS supporting AGESA 3.5.0.0+ (Tyan are you listening? Supermicro's AS2041M is already there), and get your 4P test mule updated and prepare to be amazed...

Wednesday, May 20, 2009

VMware's vSphere - Available Today

VMware's new flagship product, vSphere , has hit general release and is now available.

As we reported earlier, vSphere's license model has changed so existing SnS customers will need to either:

  1. Check your e-mail for updated licenses;

  2. Redeem their VI3 licenses (under SnS) for new vSphere versions;

  3. Download the vSphere trial and request evaluation license (recommended);

  4. Contact their VMware Partner for assistance;


We are strongly recommending a 30-day trial period for Existing VMware customers to vet vSphere in your environment and Eco-System. We'll be releasing some guidance for upgrades and vSphere ESXi deployment to flash over the next 30-days. We also recommend:

  1. Remember that vSphere's ESX Server 4.0 is 64-bit ONLY - your 32-bit machines are not upgradeable;

  2. Download the vSphere Evaluation Guide from VMware and review it completely;

  3. Take advantage of VMware's On-Line Guided Evaluation Training;

  4. Check the vSphere Hardware Compatibility Guide for issues specific to your hardware;

  5. Arrange for a Demonstration and Training through your VMware Partner;

  6. Backup your vCenter database (or virtual machine and database) prior to upgrading;

  7. Sign-up for free vSphere 4 QuickStart training;


Not all of the announced features may be available in licensed version your SnS upgrade entitles you to receive. Please make sure that you are working with your VMware Partner or Consultant to insure that your VI3-to-vSphere trial, training and upgrade goes smoothly.

Thursday, May 14, 2009

Quick Take: Oracle to Buy Virtual Iron

Oracle extended its spring buying spree by announcing the purchase of Virtual Iron Software, Inc (Virtual Iron) on May 13, 2009. Citing Virtual Iron's "dynamic resource and capacity management" capabilities as the reason in their press release, Oracle intends to fill gaps in its Xen-based Oracle VM product (available as a free download).

Ironically, Virtual Iron's product focus is SMB. According to a Butler Group technology audit, Virtual Iron "has one limitation that [they] believe will impact potential customers: the management console currently can only manage 120 nodes." However, Virtual Iron's "VI-Center" - the management piece cited as the main value proposition by Butler and Oracle - is based on a client-server Java application, making it a "good fit" with the recent Oracle acquisition of Sun Microsystems.

Oracle has not announced plans for Virtual Iron, pending the conclusion of the deal. Oracle's leading comment:
“Industry trends are driving demand for virtualization as a way to reduce operating expenses and support green IT strategies without sacrificing quality of service,” said Wim Coekaerts, Oracle Vice President of Linux and Virtualization Engineering. “With the addition of Virtual Iron, Oracle expects to enable customers to more dynamically manage their server capacity and optimize their power consumption. The acquisition is consistent with Oracle’s strategy to provide comprehensive enterprise software management and will facilitate more efficient management of application service levels.”

SOLORI's take: If the deal goes through, Oracle has found an immediate job for its newly acquired Sun Java engineers - getting VI-Cener ready for enterprise computing. Currently, Oracle VM is a "barebones" product with very little value beyond its intrinsic functionality. With the acquisition of Virtual Iron and its management piece, Oracle/Sun could produce a self-sufficient virtualization eco-system with OracleVM augmented by Virtual Iron, Sun Storage, choice of Oracle or MySQL databases, and commodity (or Sun) hardware - all vetted for Oracle's application stack.

Virtual Iron was supposedly working on Hyper-V and KVM (RedHat's choice of virtualization) management features. Though we doubt that Oracle VM will evolve into a truly "virtualization agnostic" product, the promise of such a capability is the stuff of "cloud computing." Sun's VDI and xVM server group will have a lot of work to do this summer...

Wednesday, May 13, 2009

Intel's $1.1B Euro Slap On the Wrist, Must Sell 2.3M Chips

May 13th, 2009  - besides being my birthday - marks the day that the European Competition Commission drew a $1.1B Euro fine (about $1.4B US dollars) on Intel for going "to great lengths to cover up its anti-competitive actions" and in the process “harmed millions of European consumers.” This according to the EU commissioner Neelie Kroes, in an address in Brussels today. The fine could have been as large as $4B Euros, and will go to the EU's annual budget - not consumers.

Commissioner Kroes was seen holding up an Intel PII/PIII processor card (SECC2) during the news conference, giving some scope to what has been a very long and drawn-out process: going back to 2000. At the heart of the matter has been Intel's "llegal anticompetitive practices to exclude competitors from the market for computer chips called x86 central processing units (CPUs)" - namely AMD. These were apparantly manifested in behind the scenes rebates and discounts in exchange for a reduction or termination of AMD-based products.

In a press release from Intel's President and CEO, Paul Otellini, the fined chip maker offered this defense:
Intel takes strong exception to this decision. We believe the decision is wrong and ignores the reality of a highly competitive microprocessor marketplace – characterized by constant innovation, improved product performance and lower prices. There has been absolutely zero harm to consumers. Intel will appeal.

Intel must cover their fine immediately with a bank guarantee which will stay sequestered until their appeal is either exhausted or the decision reversed. Based on EU's hunger for this type of commercial justice, the money could be tied-up for many years. But the question remains, does Intel have a history of anti-competitive behavior beyond the test of rigorous competition?

Intel's history tells a compelling story: the EU joins Japan (2004) and South Korea (2008) in finding Intel engaged in anti-competitive behavior. The question remains: how will the EU's decision play in the US courts as AMD's ongoing antitrust suit (2005) against Intel continues to unfold? Delayed until 2010 due to the lenghty list of depositions scheduled for the case, the EU's decision will likely do more to tarnish Intel's new "Promoting Innovation" Campaign than settle the dispute.

So what does Intel need to do to weather the EU's wrath? In product terms, Intel needs to move 2,262,752 of its Nehalem-EP (5500-series) chips to cover the loss. Based on a predicted 40M unit replacement market in the US, thats less than 5% and it's under 2.5% of the market if they are 2P systems. However, Intel's promised a 9:1 value for the replacement with some estimating that number moves to 18:1 with good results for SMT (depending on the workload).

What does this mean from an Intel 5500-series sales perspective? Here's our estimate, using Intel's 9:1 and 18:1 math (not forgeting the 4.5:1 for the dual-core):






































































































NehalemUnits NeededRetail Value9:118:1
W558012,545$20,072,000.000.56%
X5570121,713$168,694,218.005.48%
X5560168,227$197,162,044.007.57%
X5550174,450$167,123,100.007.85%
E5540531,715$395,595,960.0023.93%
E5530419,636$222,407,080.0018.88%
E5520183,533$68,457,809.008.26%
E5506262,704$69,879,264.005.91%
E5504250,051$56,011,424.005.63%
E5502106,312$19,986,656.001.20%
L552010,516$5,573,480.000.24%
L550621,350$9,031,050.000.96%
Total2,262,752$1,399,994,085.0012.97%73.49%

By these estimates, Intel will need to close 86.5% of the total replacement market to be able to cover the EU fines. All this assumes, of course, that they don't offer discounts off of their "published" per-1000 chip prices. Good luck, Intel, on an exciting marketing campaign!

Friday, May 8, 2009

We've been challenged to backup our comparison of Nehalem-EP systems to Opteron Shanghai in price performance based on prevailing VMmark scores available on VMware's site. In earlier posts, our analysis predicted "comparable" price-performance results between Shanghai and Nehalem-EP systems based on the economics of today's memory and processors availability:

So what we've done here is taken the on-line configurations of some of the benchmark competitors. To make things very simple, we've just configured memory and CPU as tested - no HBA or 10GE cards to skew the results. The only exception - as pointed out by our challenger - is that we've taken the option of using "street price" memory where "street price" is better than the server manufacturer's memory price.

Here's our line-up:




















































































SystemProcessorQty.Speed (GHz)Speed (GHz, Opt)Memory ConfigurationStreet Price
Inspur NF5280X557022.933.296GB (12x8GB) DDR3 1066$18,668.58
Dell PowerEdge R710X557022.933.296GB (12x8GB) DDR3 1066$16,893.00
IBM System x 3650M2X557022.933.296GB (12x8GB) DDR3 1066$21,546.00
Dell PowerEdge M610X557022.933.296GB (12x8GB) DDR3 1066$21,561.00
HP ProLiant DL370 G6W558023.23.296GB (12x8GB) DDR3 1066$18,636.00
Dell PowerEdge R710X557022.933.296GB (12x8GB) DDR3 1066$16,893.00
Dell PowerEdge R805238422.72.764GB (8x8GB) DDR2 533$6,955.00
Dell PowerEdge R905838442.72.7128GB (16x8GB) DDR2 667$11,385.00

Here we see Dell offering very aggressive DDR3/1066 pricing [for the R710] allowing us to go with on-line configurations, and HP offering overly expensive DDR2/667 memory prices (factor of 2) forcing us to go with 3rd party memory. In fact, IBM did not allow us to configure their memory configuration - as tested [with the 3650M2] - with their on-line configuration tool [neither did Dell with the M610] so we had to apply street memory prices. [Note: the So here's how they rank with respect to VMmark:










































































SystemVMware VersionVmmark ScoreVmmark TilesScore/TileCost/Tile
Inspur NF5280ESX Server 4.0 build 14859223.45171.38$1,098.15
Dell PowerEdge R710ESX Server 4.0 build 15081723.55161.47$1,055.81
IBM System x 3650M2ESX Server 4.0 build 14859223.89171.41$1,267.41
Dell PowerEdge M610ESX Server 4.023.9171.41$1,273.59
HP ProLiant DL370 G6ESX Server 4.0 build 14878323.96161.50$1,164.75
Dell PowerEdge R710ESX Server 4.024171.41$993.71
Dell PowerEdge R805ESX Server 3.5 U4 build 12007911.2281.40$869.38
Dell PowerEdge R905ESX Server 3.5 U3 build 12007920.35141.45$813.21

As you can easily see, the cost-per-tile (analogous to $/VM) favors the Shanghai systems. In fact, the one system that we've taken criticism for including in our previous comparisons - the Supermicro 6026T-NTR+ with 72GB of DDR3/1066 (running at DDR3/800) - actually leads the pack in Nehalem-EP $/tile, but we've excluded it from our tables since it has been argued to be a "sub-optimal" configuration and out-lier. Again, the sweet spot for price-performance for Nehalem, Shanghai and Istanbul is in the 48GB to 80GB range with inexpensive memory: simple economics.

Please note, that not one of the 2P VMmark scores listed on VMware's official VMmark results tally carry the Opteron 2393SE version of the processor (3.1GHz) or HT3-enabled motherboards. It is likely that we'll not see HT3-enabled scores nor 2P ESX 4.0 scores until Istanbul's release in the coming month. Again, if Shanghai's $/tile is competitive with Nehalem's today (again, in the 48GB to 80GB configurations), Istanbul - with the same memory and system costs - will be even more so.

Update: AMD's Margaret Lewis has a similar take with comparison prices for AMD using DDR2/533 configurations. Her numbers - like our previous posts - resolve to $/VM, however she provides some good "street prices" for more "mainstream" configurations of Intel Nehalem-EP and AMD Shanghai systems. See her results and conclusions on AMD's blog.

Wednesday, May 6, 2009

Add SSD to Your ZIL

[caption id="" align="alignright" width="200" caption="Samsung's new SSD generation using multi-level cell (MLC) flash and a multi-channel flash controller with NCQ and 128MB SDRAM cache."]Samsungs new SSD generation using multi-level cell (MLC) flash and a multi-channel flash controller with NCQ and 128MB SDRAM cache.[/caption]

Tom's Hardware has a good review on the state of current SSD options out there. As discussed in previous posts, the ZFS file system offers hybrid storage aspects out of the box. This game-changing technology allows for "holy grail" levels of price-performance with the key technology being SSD for caching. That's the value proposition our friends at Nexenta have been preaching.

To see what this means in a ZFS storage environment, go no farther than Sun's blog: Brendan Gregg has posted a great blog on how ZFS' L2ARC can be comitted to SSD to dramatically increase effective IOPS and drastically reduce latency. The results speak for themselves...

Quick Take: Nutty Intel VT Story

ZDnet has an interesting story that's getting some traction about Windows 7's XP mode and how you may not be able to run it on your Intel platform. Since the technology relies on Intel-VT or AMD-v to work, if your chip doesn't have it, you're cooked. Unlike AMD's all-or-nothing approach that creates uniformity across server and workstation platforms - delivering all features to all but the "Semperon" versions of the AMD64, Intel likes to market "reduced feature" versions to keep price points meaningful.

Intel's approach also makes it a nightmare for consumer end-users to determine what they get from their money, as described very well in ZDnet's blog:
"Here’s a real-world example. Dell’s Vostro 420 is a well-built, no-frills desktop PC designed for the small and medium business market. The screen [graph] below shows the current lineup of CPUs that you can choose from when you build this system to order at Dell’s website. Four of the six options support Intel VT; I’ve circled the two CPUs that don’t support VT.

(see ZDnet's blog entry for graphic and story)
In the past entries, we've looked only at the high-end processors as applied to system prices, and we'll continue to use those as references through the end of this one. We'll take a look at other price/performance tiers in a later blog, but we want to finish-up on the same footing as we began; again, with an eye to how these systems play in a virtualization environment.

We decided to finish this series with an analysis of  real world application instead of just theory. We keep seeing 8-to-1, 16-to-1 and 20-to-1 consolidation ratios (VM-to-host) being offered as "real world" in today's environment so we wanted to analyze what that meant from an economic side.

The Fallacy of Consolidation Ratios


First, consolidation ratios that speak in terms of VM-to-host are not very informative. For instance, a 16-to-1 consolidation ratio sounds good until you realize it was achieved on an $16,000 4Px4C platform. This ratio results in a $1,000-per-VM cost to the consolidator.

In contrast, let's take the same 16-to-1 ratio on a $6,000 2Px4C platform and it results in a $375-per-VM cost to the consolidator: a savings of nearly 60%. The key to the savings is in vCPU-to-Core consolidation ratio (provided sufficient memory exists to support it). In the first example that ratio was 1:1, but in the last example the ratio is 2:1. Can we find 16:1 vCPU-to-Core ratios out there? Sure, in test labs, but in the enterprise we think the valid range of vCPU-to-Core consolidation ratios is much more conservative, ranging from 1:1 to 8:1 with the average (or sweet spot) falling somewhere between 3:1 and 4:1.

Second, we must note that memory is a growing aspect of the virtualization equation. Modern operating systems no longer "sip" memory and 512MB for a Windows or Linux VM is becoming more an exception than a rule. That puts pressure on both CPU and memory capacity as driving forces for consolidation costs. As operating system "bloat" increases, administrative pressure to satisfy their needs will mount, pushing the "provisioned" amount of memory per VM ever higher.

Until "hot add" memory is part of DRS planning and the requisite operating systems support it, system admins will be forced to either over commit memory, purchase memory based on peak needs or purchase memory based on average memory needs and trust DRS systems to handle the balancing act. In any case, memory is a growing factor in systems consolidation and virtualization.

Modeling the Future


Using data from the Univerity of Chicago and as a baseline and extrapolating forward through 2010, we've developed a simple model to predict vMEM and vCPU allocation trends. This approach establishes three key metrics (already used in previous entries) that determine/predict system capacity: Average Memory/VM (vMVa), Average vCPU/VM (vCVa) and Average vCPU/Core (vCCa).

Average Memory per VM (vMVa)


Average memory per VM is determined by taking the allocated memory of all VM's in a virtualized system - across all hosts - and dividing that by the total number of VM's in the system (not including non-active templates.) This number is assumed to grow as virtualization moves from consolidation to standardized deployment.

Monday, May 4, 2009

Shanghai Economics 101 - Continued

Let's look at some more real world applications of what we've learned from the VMmark results for Nehalem and what it means in a practical comparison. We'll award Nehalem-EP's SMT a 25% bonus for in our comparisons when vCPU/core count is taken into the measurement. In a 6:1 consolidation, this means 60 vCPU's for 2P Nehalem and 48 vCPU's for Shanghai. Using this bias, the following cost characteristics are revealed for VM's with average memory footprints of 1.5GB, for the Nehalem-EP 3.2GHz system:










Nehalem-EP Configuration
Street $
1536MB VM's, 1 vCPU's
Max vCPU's (6/c)
Cost/VM

2P/8C, Nehalem-EP, W5580 3.2GHz, 6.4GT QPI with 24GB DDR3/1333
$7,017.69
13
60
$539.82

2P/8C, Nehalem-EP, W5580 3.2GHz, 6.4GT QPI with 48GB DDR3/1066
$7,755.99
28
60
$277.00

2P/8C, Nehalem-EP, W5580 3.2GHz, 6.4GT QPI with 72GB DDR3/800
$8,708.19
42
60
$207.34

2P/8C, Nehalem-EP, W5580 3.2GHz, 6.4GT QPI with 96GB DDR3/1066
$21,969.99
57
60
$385.44

2P/8C, Nehalem-EP, W5580 3.2GHz, 6.4GT QPI with 144GB DDR3/800
$30,029.19
60
60
$500.49

2 x 2P/8C, Nehalem-EP, W5580 3.2GHz, 6.4GT QPI with 144GB DDR3/800
$60,058.38
120
120
$500.49


We'll compare this to a Shanghai 2P system at 3.1GHz vs. the Nehalem-EP system:










Shanghai 2P/HT3 Configuration
Street $
1536MB VM's, 1 vCPU's
Max vCPU's (6/c)
Cost/VM
Savings per VM
Savings %

2P/8C Shanghai, 2393 SE, 3.1GHz, 4.4GT HT3 with 32GB DDR2/800
$5,892.12
18
48
$327.34
$212.48
39.36%

2P/8C Shanghai, 2393 SE, 3.1GHz, 4.4GT HT3 with 48GB DDR2/800
$6,352.12
28
48
$226.86
$50.14
18.10%

2P/8C Shanghai, 2393 SE, 3.1GHz, 4.4GT HT3 with 64GB DDR2/533
$6,462.52
37
48
$174.66
$32.68
15.76%

2P/8C Shanghai, 2393 SE, 3.1GHz, 4.4GT HT3 with 80GB DDR2/667
$8,422.12
47
48
$179.19
$28.14
13.57%

2P/8C Shanghai, 2393 SE, 3.1GHz, 4.4GT HT3 with 96GB DDR2/667
$11,968.72
48
48
$249.35
$136.09
35.31%

2P/8C Shanghai, 2393 SE, 3.1GHz, 4.4GT HT3 with 128GB DDR2/533
$14,300.92
48
48
$297.94
$202.55
40.47%

2 x 2P/8C Shanghai, 2393 SE, 3.1GHz, 4.4GT HT3 with 128GB DDR2/533
$28,601.83
96
96
$297.94
$202.55
40.47%