4898 posts • joined 31 May 2010
Re: The solid core of the big storage business
"Enterprise IT cares deeply about value per dollar, but have a very different cost for downtime and data loss than SMBs".
Bullshit. Nobody can afford data loss these days. This isn't the 90s. As for downtime; Enterprises can afford to Adobe the world for a day and they're fine. It's a little embarrassing, but banks to don't under because the debit machines stopped working again for the umpteenth time due to bank IT screwup. Target still sells shit, even after screwing up and selling you. Enterprises can afford downtime, data loss and screwups because they are too big for the consequences to truly affect them.
If SMBs or SMEs have downtime they are done. They'll lose clients instantly because the world they live is is ultracompetitive and their customers are fickle. Perhaps more to the point, the large enterprises they compete against will instantly jump all over any outage or data loss and turn a marketing machine worth more than the gross annual revenue of the little guy towards smearing their name and driving them out of business.
Large enterprises can survive government interventions that border on inquisitions. SMBs can be murdered by nothing more than FUD.
"I am subjecting myself to a risk"
And there is my point crystallized: cover-your-ass-a-service. It's what really matters to the large enterprise (and large enterprise admins), not value for dollar.
"They just don't like it when people consider personnel turnover, serviceability, and risk as part of that cost of ownership."
What are smoking, and can you please share? This is exactly what (good, successful) startups want you to consider. The (good, successful) startup scene is about making products that are easy to use and reliable.
They aren't always (I would argue rarely are) cheap...but they generally do quite directly address things like "what happens if people get hit by a bus". Not by making a certification program to ensure that you have a $20k certification path to know how to properly swap a hard drive when RAID fails, but by making sure that you don't need that level of training to make the damned thing go in the first place.
There are plenty of bad startups out there that are little more than con jobs. I have a list as long as my arm...but there are plenty of startups that are capitalizing on the fact that some aspect of IT has become so viciously overcomplicated that it needs a good pruning. That small sector has developed into a "specialization" which now exists only to perpetuate the need for that particular specialization to continue to exist. They then set about automating/software-defining/completely-reinventing-the-basics away the need for that level of complexity in the first place.
Perhaps one of the better examples of this is Tintri. Tintri "just goes fast", and for cheap. There are zero nerd knobs to tweak. There is no "optimizing" to be done. It is faster and cheaper than the alternatives, period.
When and where Tintri gets a win and convinces a customer to buy a box, the second, third and so forth follow in short order. They are doing quite well - and even slowly eeking into the large enterprise - because they made a product that is just flat out better than big-brand arrays it is competing against. And it's better because there are no nerd-knobs to tweak, not in spite of it.
Despite this, Tintri earns hyperbolic vitriol from a great many enterprise admins who've never touched it. It's new and "untested" (bullshit!) they say. They can't get into the guts and tweak it (that's the fucking point!). FUD, FUD, FUD. Cut through it - usually 10 beers later - and they just don't want it around because they either A) haven't used it before so they don't understand it or B) their job wouldn't need to exist if they bought it.
"If any large enterprise could become more competitive and reduce costs by going with storage startups or the cloud, they would have done it and reaped any benefits, which would prompt their competition to do the same or be left holding a higher operating cost ratio."
Bullshit, bullshit, and double bullshit. That's the same sort of "people are rational actors" tripe as American conservatives spew. People aren't rational actors, and corporations/governments sure as hell aren't.
Corporations and governments are made up of individuals. Those individuals - by and large - have little-to-no loyalty to the company or government they serve. Individually and collectively they care about one thing: preserving the money that is their salary.
You don't get a bonus for picking the most efficient product that can do the job within the safety margins. You get a bonus for picking the "known good choice" and never taking any risk, no matter how small. As stated above: companies at the size of a large enterprise are big enough to cope with being massively inefficient, even to the point of experiencing huge outages, data loss and so forth.
Large enterprises don't need to be as efficient as the next guy. They just need to be able to scapegoat someone if something goes wrong. That means that the sole focus of people that work there is never being ion a position to be scapegoated, even if that means it costs the business more. It isn't their money, they just don't care.
"The reality is that we all have little projects we use to test out new stuff,"
Completely untrue. First off, a huge chunk of large enterprises absolutely do not have internal skunkworks for IT. They let their competition do that and they then follow the herd by adhering to "best practices" and the whitepaper farm. Nobody at that level is going to be out of business because their IT plant is a little less efficient than the next guy, and they can skimp on the R&D that way.
"and if anything were so significantly better than the established low-risk vendors we tend to use, they would quickly become "enterprise vendors"."
Nope, sorry. I've seen lots of situations in which the startups pass muster on the technical side, meet all the business requirements and otherwise are well suited to operating in a large enterprise (indeed, already are in some other large enterprises), but are shot down as a vendor for purely political reasons. Massive FUD from an admin or team worried about their own relevance is one frequent item, but by far and away the most common is some pointy-haired boss who just doesn't want to lose junkets or clout with his existing junket provider.
Besides, you act as though SMBs and SMEs just roll up to a startup, swallow whatever tripe they spew and toss complete unknowns into production. That's bullshit of the nth order. 80% of the companies I work devote around 1/3rd of their IT budget to R&D and PoCs. Dev and Test are frequently a substantial size of production, right down to companies with as little as $3M in gross annual revenue.
Now, I'll admit, when you get below $1M GAR, everything changes and IT starts to become largely disharmonious consumer-based pap, but - quite frankly - so is everything at that level. There's a reason a huge % of companies never make it to $1M.
Above that, however, and right up to the point where politics dominates over sheer corporate survival, R&D/prototyping/PoCs are absolutely critical. IN the SMB/SME space you only get one chance, and you're usually toast if you botch it.
Remember also that in the SMB/SME space, IT isn't an empire. We don't get to dictate terms to the business. The business demands we provide a given service - and level of service - and you get what you get for budget; there isn't any more to be had.
In the SMB/SME space, we only keep our jobs if we're more efficient than the next guy, without incurring any additional risk.
In the large enterprise space you only keep your jobs if, when something goes wrong, you can both point to a "best practices" document and claim "everyone, everywhere does it this way" and you can redirect the blame cannon onto another scapegoat.
More than anything, this is what holds back the evolution of enterprise vendors. The "new guy" company is the easy target when something goes wrong, even if it isn't actually responsible. Noone wants to be the one responsible for introducing new technology or vendors to the mix because they don't want to be the scapegoat.
There's nothing there about "fitness for purpose" or "value for dollar". It's just fear and politics. Even if the thing is entirely fit for purpose and provides superior value for dollar uptake will be painfully slow in large enterprise.
There are always exceptions to everything above, but even those - such as Netapp - are very slow growing. Even when offering better for value for dollar and when equally fit for purpose, Netapp will still struggle inside a large enterprise for specific deployments due to individual ass covering and fear...and here's a company that has "made it" and has a "presence"!
People are not rational actors, and collections of people are even less so. Large collections of people are panicky herds, and I find your belief that individuals within the belly of a "whale" will do what's best for the whale (instead of for themselves) quaint and alarming at the same time.
It certainly doesn't align with any of my experience, or my research. Maybe you, personally, are a good admin; loyal and true and working for the good of your employer. If so, that makes you rare...and I hope they buy you a bloody island, because if that's the kind of admin you are, they'd better not lose you.
Re: The solid core of the big storage business
"Enterprise IT" giants make the bulk of their money from...enterprises. Shocker. You're absolutely correct that a large enterprise brings in more revenue per client than an SMB or SME...but there are a sweet holy hooligan more SMBs and SMEs than large enterprises.
Why isn't EMC making their living off of SMB and SME clients? Because there's better value for dollar with the startups, or even with Dell, HP and so forth.
Enterprises don't give a rat's ass about value for dollar. Enterprises are all about massively conservative approaches to everything. Resistance to change borders on an elemental force. Everything at every level with every single person has absolutely nothing to do with advancing the interests of the company itself and everything to do with "covering one's own ass."
Enterprise administrators are the epitome of fear. If they don't know it inside out and backwards then it is evil. No ifs ands or buts. If there isn't training, a certification and so forth then there's no way to ensure that asses are covered. Manuals must exist that qualify as tomes. Certifications must exist so you can say "if I get hit by a bus, you don't have to actually exert brainpower thinking about who to hire, you just hire this shiny certificate." Everything is codified, procedure and the buck stops nowhere because nobody can ever possibly be to blame for anything.
SMBs and SMEs just don't live in that world. They need to be faster and more nimble than large enterprises if they want to survive. They need to be able to do as good (or better) a job while charging less, and that means that "value for dollar" is the driving force behind IT.
Enterprises will uptake technologies that are today considered "startup" territory, but only once 5-10 years have passed since initial introduction. The startups have to either be eaten by an existing enterprise IT vendor, or they have to have ballooned out to some huge size where the majority of the company is no longer engineers, they're content creators and sales people. Documenting every possible configuration and inviting CIOs out to lunch to convince them to spend 100x the money on their solution as they would on a similar solution by a rival startup.
Obviously, large enterprises are doing something right, or they wouldn't be so large. By the same token, it increasingly seems like large enterprises exist to serve the needs of other large enterprises, with large quantities of money flowing 'round in circles at the top and ultimately never really leaving that world.
Large enterprise in increasingly incestuous and simply choosing not to cater to the other 80% of humanity. The top 20% caters to the top 20%...but is also populated by execs and shareholders intent on pulling as much money out of hte system as humanly possible. How long that is sustainable is an open question.
In the meantime and betweentime, all those more agile SMB and SMEs are getting more and more comfortable living in a world where they don't really need to interface with large enterprises at all. They're moving too fast, they're changing too fast, and they don't really want to wait for suppliers or customers to catch up.
The next few years will be interesting. Which will win out? The breakneck pace towards efficiency, automation and innovation seen at the bottom, or the overwhelming inertia of the top?
Into object storage on commodity hardware. See: Caringo.
Lobbying by commercial entities should be
made illegal considered treason.
Being a Microsoft Partner.
As a Microsoft Partner who has seen diminishing returns of late, I would normally write an enormous rant here about this. Instead, I will link you to http://www.crn.com/news/channel-programs/240165273/microsoft-partners-in-uproar-over-cloud-sales-commission-cuts.htm. This sums up the situation quite nicely for partners; the good, the bad and the margins.
Re: ASCE's journals
Funny, ARXIV hasn't destroyed the discipline of Physics yet...
Re: Great terminology!
Uh, "lithobraking" has been around since the earliest Soyuz landings. At least. That's a fairly old term.
Re: The nutcase brigade would never allow a NASA mission to Venus
If we aren't causing the rise in Earth's CO2 levels, what is? Also, where does all the CO2 from our combusted fossil fuels go? Faerie farts? The extant biosphere cannot absorb anything close to what we're pumping out. There are no plants that can grow fast enough to use up that CO2.
Worse; plants have this nasty habit of being on the surface. They don't tend to "sequester" the CO2 again, with the exception of some of the CO2 leaving the system via oceanic sequestration (algea and higher life forms dying, falling to the bottom of the ocean and being buried/subducted.)
So there are some problems with the hypothesis "humans are so insignificant as to not be able to affect the global climate."
1) We are releasing several hundred million years' worth of sequestered carbon into the atmosphere.
2) The extant plants can't absorb it at anything like the rate we emit it.
3) We keep doing this "deforestation" thing on massive enough levels to make me very sad when I look at Google Earth images of British Columbia or Brazil.
4) The more CO2 in the atmosphere, the more the heat gets trapped here.
5) The more CO2 in the atmosphere, the more acidic the oceans become.
6) The more acidic the oceans become, the less CO2 gets sequestered via ocean organisms doing their growth/consumption/burial thing.
7) Humans like to breathe air that isn't filled with particulates, so (most) of our societies have been moving towards pollution controls which reduce the amount of particulates we crank up into the atmosphere, thus reducing the amount of radiation reflecting material in the atmosphere, giving us all the climatic CO2 effect of a lovely series of volcanic eruptions with an ever decreasing amount of soot to block out the sun.
Anyone who does the sums and thinks we aren't affecting the climate is a goddamned idiot. We are; and fairly rapidly (on geologic timescales) at that. The flip side of this is that if we hadn't gone and done this, we'd be facing the start of another ice age in about, oh, 6000 years or so. So we've unintentionally geoengineered our planet to be more suitable for us than it was heading towards...but we may well have gone too far in the other direction on this.
So there are questions that we need to get answers to:
1) Is there a "new balance" oceanic ecosystem that can cope with the increased acidification on a short enough timescale to cope with the mass extinction we've initiated?
2) Will this "new balance" ecosystem be able to ramp up it's CO2 sequestration enough to start reversing the CO2 levels? By how much, on what timescale and will we be right back to facing the Ice Age problem again if it adapts quickly?
3) How much of the commercially important biodiversity are we going to lose when the extant oceanic ecosystem is no longer sustainable? How will we adapt to this?
4) Tundra/Taiga thawing is releasing massive amounts of Methane, accelerating climate change and in turn accelerating thawing. Should we/can we ignite the Methane in order to turn this very powerful greenhouse gas into less potent CO2?
5) What kind of technology needs be invented to convert Tundra/Taiga into farmland? (Muskeg is impassable to our current technology.) How much do we need to convert to meet the requirements of our species in light of the changing climate?
6) How will rainfall patterns change, and how will these changes affect our ability to grow necessary crops?
7) Can we alter the rainfall patterns we expect to be seeing through forestation/reforestation (forests alter rainfall patterns by altering both local albedo and the local hydrological cycle.) Should we? And Where?
8) Can we green the desert/prevent the expansion of deserts due to change in rainfall patterns via fission-backed desalination and irrigation? Should we? And where?
9) What areas are at risk from flooding due to sea rise or increased storm activity? What should we abandon, what should we reinforce?
10) Much of our current agricultural technology relies on petroleum-based fertilizers. As the climate changes our energy demands will increase while at the same time we are reaching the limit (if we haven't already) of BBL/day relevant hydrocarbon extraction. (You can't make fertilizer from natural gas.) What technologies need to be invented or adapted to cope with a future in which these fertilizers are less plentiful? Can we green the desert/farm the tundra without them? Should we be caching reserves of these critical substances in order to deal with the upcoming "fringe farming" requirements while transitioning our more easily arable land towards farming techniques that don't require petroleum-based fertilizer?
11) We are already using water from our aquifers far faster than the aquifer recharge rate. How will changing rainfall patterns affect aquifer recharge? How will we have to adjust our water usage and agricultural practices? Can we use fission-backed desalination to refill the aquifers faster than nature itself would allow, and should we?
12) If we do change any of our current practices (for example, our very water-intensive farming techniques) how will that alter the climate? Will local variances in water evaporation or albedo (due to forestation/reforestation/greening of the desert/farming the tundra) have larger effects that we should consider? What effects are those, and how do get all the relevant political bodies together to make plans that deal with the "ripple effect" of large-scale changes undertaken by one organization?
We aren't going to stop climate change. We aren't ever going to get people use less power or otherwise sacrifice for a "greater good" that is generations in the realization. We need to accept that, and start looking at technologies and techniques that will enable adaptation to the changing world.
We live in a world where one man can choose to cut down an entire forest, altering the weather across the entire region and ultimately subtly changing the global climate. One person's signature can set into motion a chain of events large enough that we really should be figuring out what the repercussions are, and how best to adapt to those repercussions.
We still have a group of people so obsessed with their own false sense of insignificance that they actually prevent us from moving beyond "can we affect the planet on a global scale". We can, and we do. What we need to be doing is qualifying how so that we can quantify the externalities current business, governance and commercial practices are not paying for and ensure those costs are properly costed as part of the cost of goods and services. We then can ensure that mitigation and adaptation efforts are funded and properly coordinated.
That isn't religion, or radical belief, or hocus pocus. It's pragmatism. Life is change; those who adapt, survive.
Re: Why not work?
"The thing about having local employment is that it pushes up property prices. If there are jobs, people will move to the area to take them. If there are no jobs, house prices drop - or become affordable, if you prefer that description."
I have an ADSL connection and can reroute through the LTE in my phone whenever I want. Hence there are innumerable "jobs" available from wherever I choose to be. Telecommuting, it's a thing. And unless there are 8 figures involved, I'm never working an office job again.
Re: Social, not technical changes
"Herding the elderly or the disabled or families or singles into ghettoes in order to provide some ideal environment for their needs would be counter-productive, wasteful and ignore the great diversity across all ages."
I think you've got it backwards. If we just isolated "families with children" into their own communities and left the rest of us the hell alone, life would be grand. How much infrastructure is just there to support screeching sprog?
I'd pay good money to live in an adult-only and adult-oriented community. Sprog are expensive, noisy, require massive upkeep and maintenance and all manner of unholy rights-limitation occurs in the name of protecting them.
Give me a community where "think of the children" is met with a blank stare and "why?" I don't want to think of the children. I care nothing for sprog and have no intention of having any. Sprog should be raised in their little sprogified bubble cities until such a time as the NIMBYs decide they are old enough to take care of themselves. Then they can spend a few years in a halfway home known as "post-secondary" before being released into the real world of cities designed exclusively for adults. If they choose to return to hell (I.E. Sprogtown) in order to crank out a wailing fleshbag of their very own, that's their choice. The rest of us can live in peace and never, ever, "think of the children" again.
Re: Social, not technical changes
"So what do the elderly need? Yup! their own cities. But cities, or more likely communities of a few hundred or thousand homes, that are designed just for them. Ones that don't have cracked and uneven paving slabs. Ones that don't need the infrastructure of jobs and schools to be built as well. Ones where the supermarkets don't have aisles and aisles full of babies' nappies and cosmetics - but instead have products and layouts tailored to the wants and needs of the over-70's. And of a scale where it won't take all day to get from one end to the other. And cities that don't have steps, stairs, slopes or a maze of twisty little passages, all the same. Possibly even having the streets colour-coded and homes and shops with entrance doors that don't need Harlequins' scrum to push open, oversized signage and house numbers and are visible from the road for those with less than 20-20 vision (or even proximity detectors that announce the address as you approach."
I'm 31, and I'd pay really good money to live in such a city. Especially if it came with a "no children because our infrastructure doesn't support them" rule. Add some mountains in the background and a bunch of trees/forest for visual happy and dear me, you've described my personal idea of a Utopia*.
*Yes, for me, San Francisco actually is hell.
Re: Sceptics and/or Cynics United and Unlimited, this way please ------->>>>>
"supposedly on Mars"
Drive 'round and check, you oik!
Re: Does their caching work for secure connections?
Just MITM the SSL certs. Surely the NSA will loan them the appropriate tech...
Re: WYSIWYG is the problem
"I wonder what El Reg writers use."
Can't speak for anyone else, but I can tell you what I use. 50% of my writing is done using my personal Server 2008 R2 VM with a heavily customised version of Word 2010*.
The ribbon bar was completed excised from the application. I have disabled most "features" and "formatting" bits. For all intents and purposes it is an instance of Notepad with spell check, a decade's worth of custom dictionary, word count (very important!), version control and the ability to pass the document back and forth to my colleagues and get feedback via comments, change tracking etc.
About 30% of my writing is done in LibreOffice writer 4.2, which is what I run on my netbook. In every way that matters to me it is identical to Office 2010, and superior in a few ways. The only reason I haven't switched away from Office entirely is apathy. Office 2010, modified to meet my needs, works and works well. A properly set up LibreOffice would work well too, but that would require reconfiguring what I have, so I'll probably just run both on different machines until end-of-support for Office 2010 makes me switch.
The other 20% of my work occurs in Google Docs, though this is increasing. To put it bluntly, if there is going to be collaboration outside of my company, it's almost always going to be Google Docs. It seems to be what my clients use.
I should probably point out that the peculiarities of The Register's CMS mean that it is simply cheaper (time-wise) and easier to write everything in HTML. I don't use features like "bold" or "italics". I write my formatting in raw HTML for every single article, whitepaper and so forth.
Maybe these newfangled productivity suites with their newfangled interfaces and auto-helping default settings have a purpose for some/most/everyone-who-is-not-me. Can't speak to that. What I can say is that I've been using productivity suites since I was three years old. I cut my teeth on things like Wordperfect 5.1. When I write, I want to write. I don't want to think about "where is command X?" or "why is it doing that now?".
I want to know where my controls and commands are. I don't want it to auto-format or reconfigure a single thing. If I want formatting, I'll code it. If I want a command, I'll go where I have gone for the past 30 years of my life.
The future and all it's touch-enabled, auto-assisting, Clippy-friendly 0.8px-after-your-paragraph interfaces belongs to a newer generation. It is for people who are not me; those who grew up mashing txt msgs into their keypads and relying on T9 predictive text. Those who instinctively trust the computer to "get things right".
I don't. I can't. It's not in me. So what do I write on? That which feels familiar, comfortable and safe**. The future and all it's children can have the rest.
*I upgraded from Windows XP and Office 2003 only about three months ago.
**The religious wars are for those who don't make a living off of their writing.
"What is going to cause people to suddenly start buying a lot more Cisco?"
Legislation that makes other "value for dollar"++ competitors illegal. That, and Cisco will soon be able to deliver a complete Cisco-branded stack covering everything you need in the modern datacenter. So they'll get the service revenue once they move on to the C) Extinguish: phase of the standards game.
Re: How anonymous will they be able to remain...
Not very, as in most major NA cities you need to get a permit to protest. (Or at the very least, keep the cops informed of time/date, leave a contact person with them who can help the cops round up anyone who breaks the law, etc.) More to the point, the majority of Anonymous isn't behind this in any way, so there isn't going to be a huge turnout.
This isn't 4Chan. Try some of the more outlying colonies. The bulk of the hivemind does not support these ridiculous actions.
Re: [offtopic] kudos for the windows taskbar config
That's how everyone here sets up their task bars. Have since forever. The part where this arrangement is pretty crap in Win 8 is one of the reasons I'm less than keen on it.
*Looks at conference attendee sheet*
Oh look, a new no-fly list.
I suspect that you may be an idiot. One person "cutting ties" with China or the USA doesn't affect a goddamned thing. All it does is serve to put that person at a disadvantage. The same is true of one entire nation. For such a thing to have an effect it must be done as a power bloc.
The reasons are many. The first and most obvious is that economies the size of China or the USA won't notice the lack of contribution of a single individual and will barely notice the lack of contribution of an entire nation. Secondly, so long as other nations respond to political and economic pressure from these "superpower" nations, then any nation which tries to take an ethical stand can (and will) find themselves on the wrong end of an economic blockade from the current western power bloc.
If the majority of western nations were to band together and sever ties with the US, China and Russia they would survive the attempt, economically, at least. I would per perfectly willing to participate in such an event, cutting all my personal economic ties with those nations, no matter how hard that would be, or how much sacrifice it would entail.
But what purpose does it serve to do so unilaterally? I will accomplish nothing by doing so and I will also remove any chance I have of obtaining the financial or political capital required to see my ideals considered, let alone made manifest.
What I preach is a federated economic union of civilized powers that embed ethics and international cooperation as a foundational principle in what would ultimately be a new form of government. The USA, China and Russia would never be a part of such an entity because they cannot unilaterally exert power over it. Thus I would say "leave them behind and move humanity forward."
That isn't related in any way to one individual's purchase choices. They are so completely and utterly disconnected in scope and scale that to call the lack of one hypocrisy in relation to the other demonstrates nothing more spite on behalf of the accuser.
For the record, I do choose products from civilized nations wherever possible. I'm entirely willing to pay more in order to support the economies of nations whose politics I agree with. My segregation isn't absolute, however, I am in fact working towards such a goal.
Said personal economic choice has nothing to do with my belief in how nations should act at scale. They are different beasts entirely. When I choose who I buy from I am choosing based on my personal ethics. It imposes nothing on anyone else. It is my choice, and I alone bear the consequences of that choice.
Acting at a national level, everything is different. The ethics of the individual are completely fucking irrelevant at that scale. What matters is security and stability. Security of resources, stability of economy, stability of relations and security of your people.
This is best achieved by having strong relationships with rationally-run countries that behave in a predictable and honourable manner, presuming, of course, that your nation is also a rationally-run nation that behaves in a predictable and honourable manner. "Surprises" don't go down well on the international scene. Change needs to be slow, multilateral and controlled. There is no room for cowboys.
A strong international federation of nations that has a codified foreign policy, trans-national law and courts, codified admittance and ejection policies, harmonized economic policy and so on and so forth...this is where strength comes from. With the possible exception of Russia, no nation - not even Canada - has all the resources required to survive in the modern world. No nation - not even the almighty US of A - has a military capable of defending against all foes.
Most importantly, no human being - not a single fucking one of us - has the knowledge to predict the results of interfering in the natural development of other nations. Far too much (if not most) of the tragedy in human history has stemmed from the inability of our many and varied leaders to resist the urge to meddle.
The ethics of international cooperation and foreign policy have fuck all to do with personal likes or dislikes. They have everything to do with learning from our fucking mistakes and applying that knowledge to better governing our nations. The ethics of nations is about the needs of the many outweighing the needs of the few, not the desires of the one influencing only that one.
I preach and advocate evidence-based legislation and a union of nations who can and will adhere to that concept. I believe that we need to be cautious and cooperative in our international endeavors. I believe also that we cannot let other nations push us around to suit their agenda; we need to have strong enough ties within our power bloc to say "no" to nations like the USA who refuse to play nicely with others.
Playing nicely involves things like recognizing, and ratifying participation in international courts. It involves adhering to terms of treaties, even when they don't suit your current political goals. (E.G. the terms of the NAFTA treaty are not merely a means to economically cripple Canada and Mexico, they also impose restrictions on the US that is must adhere to.)
I don't preach anti-Americanism, no matter how hard that may be for you to comprehend. Nor do I preach anti-Russianism or anti-Chinaism. I preach global legal harmonization, recognition and enforcement of human rights and a strict limit to the power of corporations and politicians.
When the US is ready to ratify international courts, abide by it's treaties, address it's wealth gap, and start addressing the power imbalance of it's society (starting with Citizens United) then I think it would make a wonderful addition to any international community. The USA is filled with amazingly good people who try to do great things. It just isn't mature enough as a nation to play with others internationally in a rational, predictable and globally advantageous manner.
If you cannot see the difference between personal choice in sourcing products and a desire to build a better a more stable world at the scale of international interactions then I must return to my original statement: you're an idiot.
Edit: as a side note, I loathe traveling into the US. With very few exceptions, I don't do it simply "for business" and I would never do it "for shopping." (Seriously?) When I go into the US it is because people I like and/or care about have asked me to do so. I don't go to VMworld or Spiceworld "because of business." I go to meet human beings that I believe are good people. I would love it if they all came here to hang out, but it is those events that they choose to attend, and it makes sense for me to go so I can meet up with as many of them as possible all in one go.
Re: Where have you been Murphy?!
"and you'll be better off if we're on your side rather than being "neutral""
No, we won't. The USA does far more harm than good. It is a destabilizing and deleterious presence. Western nations would be far stronger if the USA simply wasn't there.
I would far prefer that civilized nations simply cut off all ties with the USA, Russia and China. The rest of the developed world could federate and work together towards common cause; there's nothing any of those nations has that we explicitly need. Let the poxy whoresons annihilate eachother, or sink eachother into some godawful economic depression. I don't care.
Until a nation is ready to play with others as equals then the rest of the world simply shouldn't interface with them. None of us have the knowledge and experience to play god; we shouldn't go interfering in their culture, or attempting to "advance" them (technologically or culturally) artificially. Each nation needs to find the patch towards international cooperation and peace on their own.
The rest of the developed (and developing) world combined has more than enough resources to build a strong defense force and a self-sufficient economy. We just don't need barbarians.
So to hell with the WTO. To hell with globalization and the infrastructure of American economic imperialism. It's time to form a true international federation for mutual economic and defensive benefit, where rules regarding interference in other nations and acceptance of other nations into the bloc are codified at the outset.
P.S. don't you dare trot out "our boys died to save your asses" yankee patriot bullshit. My ancestors bled and died same as yours. The threat was global; all nations were at risk. If I recall correctly your nation not only was late to the party, they seriously considered joining up with the bad guys for both world wars.
Besides, however brave your antecedents may heave been, the USA today is an emphatically shitty copy of that proud nation that existed then. If your ancestors were alive, they'd kick you in the crotch and leave you in agony on the floor for the sheer hubris of thinking that the corrupt oligachy of today's America is even a pale shadow of the nation that created a generation of men who understood the concept "the needs of the many outweigh the needs of the few".
Lest we forget. There is a reason this saying is tied to an international holiday. Your nation has forgotten the very important lessons that are tied to those three words. And for that reason I am not "thankful" for the US of A. I'm fucking terrified of you bastards; far more so than Putin's KGB Mafiosos or China's rush towards a stable middle class.
Re: MS SOP, Stage 2
I thought stage 2 was "extend"? (Embrace, Extend, Extinguish.)
This almost seems like a sane, helpful, developer-friendly move by Microsoft.
...what's the catch?
Re: About time some plaintiff's actually realize their lawyers are screwing them
I do entirely take issue with your asinine assertion that "the Democrat Party is the Trial Lawyer Party" is a " factual statement". This is false. Both of the American political parties are equally in bed with trial lawyers and equally infested by them at all levels.
This is not a "slight political statement" by you at all. It is indicative of significant bias. Your followup post merely confirms it. You are not an objective observer of USian politics and thus aren't going to be able to suggest workable solutions that solve systemic issues because your view of the world is blinkered by partisan politics.
Also, for the record, "you've managed to elect a totally incompetent narcissist to the Presidency not just once but twice" is utterly false. My country doesn't have a President. Though I note that the US's past two presidents would be easily described by your chattering inanity.
Perhaps you need a lie down.
Re: About time some plaintiff's actually realize their lawyers are screwing them
"But since the Trial Lawyers' Party controls the White House and the Senate"
Oh get over yourself. The Republicans are just as made up of MBAs and lawyers as the Democrats. And they are all as guilty of compromising their ethics over government pork and campaign donations as the next guy.
The differences between the parties boil down to this:
Extremist Republicans would have the US enslaving non-whites, evicting foreigners, women barefoot and pregnant, sex education was taboo, science was banned, homosexuals were murdered and contraception equated with witchcraft. English would be the official language and some flavor of protestantism the official religion.
Extremist Democrats would have the US living as an agrarian society where births were highly regulated (to control population), science banned (it's not "natural" or "organic"), wealth redistribution would be dialed up to 11 and men would be "paying" for the sins of other people's grandfathers for generations to come.
Both are batshit fucking crazy, and both groups of extremists would spend themselves into a debt hole that would make the extant problems the US faces look quaint.
In the middle, however, you find the majority of Americans. These are people that, on average, are socially progressive and fiscally conservative. They want to see the wealth gap narrow, but not to the point of guaranteeing equality of outcome at the point of a gun. They want to see the government debt dealt with, but not with such drastic action that it results in a reset of quality of life for the average American back to the 1930s.
Average Americans just don't give a flying fuck about sexuality, religious choice, country of origin or so on and so forth. Other people can be who they want to be; what matters to the average American is that they have a good job, a reasonable expectation of financial stability in the future and that they leave a better world to their children than the one they themselves were born into.
Both parties are corrupted by the extremists. The extremists are - by their very nature - willing to put a lot more time and money into convincing everyone of their cause. That means placating the extremists heads off a great many problems early on and it ultimately becomes the focus of every party and every individual campaign.
The problem is that extremists are allowed a disproportionate voice. This gets to party financing, political advertisements and more. Regular people - who are by default fairly apathetic - can't have their voices heard amongst the din.
They also - at least in the USA - don't have a choice. Both parties are completely batshit crazy. There is no "Sanity party of America" that provides a centrist view. There is no party to go to in the USA for people who are socially progressive and fiscally conservative. Hell, that's rare in almost any western nation.
People corrupt. That means special interests worm their way into the heart of all political parties, especially when the money is allowed to flow completely freely. A newly emerged party would be no different from the established parties, because the fundamental mechanisms that cause the imbalance of voices is never being addressed.
Thus your lawyers - and hollywood, oil and gas, argibusiness, big pharma, etc - are all over both parties like a bad stain on the back of one's undies. Lawyers don't court "just the Democrats", because that would be idiotic, and lawyers are anything but. You go after both parties so that regardless of which one wins, you win. That is how every single lobbyist on earth plays it.
Additionally, those professions which attract the power-hungry to begin with (such as lawyers) will ultimately vomit forth political candidates at all levels of government and for all parties at roughly the same rate. This is because most political candidates don't stand for anything. They merely crave power. Thus they will work with any party that will have get them elected and push any agenda or platform they feel will get them elected.
Neither Republicans nor Democrats are (on the whole) heroes or idealogues. Some are, but damned few on either side.
What should stand out is that this isn't the case everywhere. There are a hell of a lot more idealogues in Canadian politics (as one example) as well as Nordic politics and even German politics than there are in the US or the UK. (Though Canada's new election laws are having a dramatic effect on the reduction of ideologues at all levels.)
So, blame not a given party, or even a given pressure group. The system in that nation is irrevocably fucked. Only some very dramatic overhauls can set things right...but the power climate is such that it make take a revolution for that to happen.
The day Citizens United is thrown out is the day the wheels start turning back towards the people. I fear that will not come within my lifetime.
Re: Illegal cartel behaviour
"Is that a good outcome, if two companies conspiring to avoid poaching were both driven into bankruptcy, so that all the workers who had their salaries pushed down now become jobless and probably can't recover the bulk of the fine due to that bankruptcy?"
Yes. It's called "setting an example." They do it with proles often enough, and they set laws for individuals such that they are punitive to the point of ruinous all the time. (See: $100k+ for torrenting a single MP3.)
The idea here is deterrence. Corporations do not have morality. They can only be dissuaded from behaviors through deterrence. A slap on the wrist is not deterrence. It isn't enough to cause a shareholder revolt, executive firings and other dramatic and drastic repercussions that will ultimately make those who run companies think twice before breaking the law.
Personally, I'd put a contingency in the law to attempt to mitigate bankruptcy problems, but I think it is perfectly acceptable to drive a company out of business if it breaks the law, especially when the law they are breaking affects many individuals. Examples would be cartel behavior, abuse of monopoly position, conspiracy to depress wages or externalizing costs of manufacture by destroying the environment.
A) Ensure that when a company is driven out of business due to deterrence-class lawsuits the administrator for the company's bankruptcy procedures can go after the executives and board members. Make piercing the corporate veil a hell of a lot easier when the decisions taken (and the laws broken) are more than just incidental infractions of procedure and bureaucracy.
My standard for such a judgement would be this: if a regular citizen would go to jail for the act(such as murder, environmental destruction, etc) - or for defrauding an equivalent number of people out of an equivalent amount of money (cartel behavior, wage depressing, etc) - that the corporate veil can be pierced.
B) Stipulate in damages calculations that any damages calculation that has a reasonable chance of driving the company to bankruptcy be put before court appointed experts such that they can determine a reasoned balance between the maximum % of the penalty originally awarded and keeping the company from bankruptcy.
If the damages assessed are such that only a minute fraction of the damages would be paid out in order to stave off bankruptcy then the company should be placed into administration and as much of the company sold off as possible to both meet it's extant debt obligations and the settlement obligations, even if that means wrapping up the endeavor altogether.
C) In the event that a company will be driven to bankruptcy or wrapped up completely as the result of such actions there should be a pre-designed social safety net to help employees transition. I'm not talking welfare here - which is mostly aimed at helping people through longer term economic downturns - but a form of employment insurance that is more short term and tactical and aimed squarely at helping the people who lost their job in the bankrupting company get a job at the company that will be filling the void.
The above isn't perfect. There's gaps that people smarter than me need to think on, correct and expand on...but the needs of the people outweigh the needs of the executives...or the shareholders. Corporations are given too much leniency, especially when it comes to actions that affect thousands or even millions of people. The status quo does society a disservice. It needs to be altered. I believe that alteration needs to be rather dramatic.
When I demanded Microsoft unfuck it's VDI licensing, this is emphatically not what I had in mind.
I care what J.H. thinks. Thus your statement is incorrect. In fact, I can name at least 250 (probably more, if I think about it) members of the VMware community alone that would consider themselves "fans" of J.H., including at least a dozen CEOs. I have been asked to arrange introductions come VMworld between J.H. and some of these folks, so I'm pretty sure that the apathy (or in your case outright hostility) is limited to a fairly narrow(minded) subset of the readership.
Edit: and just to make sure I get a nice Ad Hom in here to keep the average low...while J.H. may make the odd very human error in his writing, your ceaseless bellyaching has left me with only one inescapable conclusion regarding this whole issue: you, sir, are uncompromisingly inferior.
That's because Lenovo sells things people actually want to buy. With OSes people actually want to use. Thinkpad Uber Alles.
Re: Getting more peopel to adopt IPv6
"Sorry, Trevor, but I'm really struggling to see how anyone can design a protocol that is resistant against people just ignoring the protocol and doing something else."
It's very simple. You accept the proposals that were repeatedly submitted for incorporating NAT officially into the spec. At the very least Prefix translation NAT, but NAPT66 as required for various emergencies. You put aside the end-to-end religion and you focus on reality.
The issue here is that actual solutions to the problems encountered were proposed. They were rejected because they broke end-to-end. End-to-end has become a religion. It is in the way of solving real problems. Smart people with credentials are proposing solutions. The hivemind says no.
"Actually I'd hold your judgement on that. We (as in end-users) haven't really tried that yet. As IPv4-fixated ISPs try increasingly unfriendly options (like CGN) to postpone that job they don't want to do, customers (largely isolated from the problem until very recently) may start to take an interest and, then, letting the market sort itself out may prove to be a perfectly reasonable way forward. We're told that the backbone is already IPv6-friendly, and modern OSes are certainly happy to use it. ISPs and their bundled routers are really the only sticking point and in many parts of the world there is competition in that market."
That is exactly the sort of airy-fairy "hope"-based thinking that has driven the IPv6 theologists from day one. It hasn't happened yet. It is extremely unlikely to happen in the future. The belief that people will pressure their ISPs and device vendors into behaving is based on the idea that humans are rational actors. People are not rational actors. Every single piece of economic theory based around that ridiculous idea is false and doomed to failure.
What people will start doing is paying money for IPv4 addresses. They will also start using NAT with IPv6 and damned be the nerds that cry "no!". It is happening today. It will continue to happen in the future.
The idea that end customers give a rat's ass about the end-to-end model was patently ridiculous from the start adn that hasn't changed one whit. In fact, in a post-Snowden world, there are a lot of people who are nearly violently opposed to the end-to-end model for any number of reasons. There will be no grassroots revolution demanding ISPs and device vendors get their shit together and properly support IPv6 protocol spec in order to make the end-to-end-model possible.. Nobody except the religious ivory tower elite and lazy developers who loathe having to actually engage brain and think about NAT when designing applications cares.
Market pressures will not force ISPs and device vendors to conform on IPv6, they'll force developers to design applications that work with IPv6 NAT. ISPs and device vendors are so powerful they dictate terms to end customers, not vice versa. That dynamic will not change within my lifetime.
Developers, on the other hand, are cheap and disposable. For every recalcitrant douche who refuses to write their IPv6 application to cope with NAT there are 10,000 more willing to write a similar app that will. End customers do dictate to developers. That's where the fold will occur.
Re: Getting more peopel to adopt IPv6
"Then you could avoid a number of pointless and vapid arguments by criticising your ISP and device manufacturere in future rather than IPv6. Remarks like "How does IPv6 handle these scenarios?" lead the naive reader to believe you are blaming the protocol."
I am blaming the protocol. Many of us have been saying for well over a decade that exactly this was going to happen, despite protestations of the ivory tower elite. Shock of fucking shocks, the shit we warned about actually came to pass.
It is the job of engineers to design for the real world, not to create religions and ideologies and expect the world to conform.
The protocol should have been designed such that it would take into account that A) device vendors are not going to put even the faintest bit of effort into creating devices that do more than the bare minimum and B) ISPs will not all "follow the rules" and assign whole prefixes. This was mentioned SEVERAL times by people far more important and well credentialed than me.
The response of the ivory tower types? "The community must pressure these organizations into compliance." That was a spectacularly stupid plan for dealing with these issues and it didn't fucking work.
So, I have two options: I can cripple myself and the companies I support by trying to support a religious ideal of "end-to-end" that I don't actually believe is all that important (things work just fine without honouring that today), or I can say "fuck the theologists", break the spec and have shit Just Work.
I choose the latter.
Re: Getting more peopel to adopt IPv6
To my understanding radvd still requires the systems ask for new IPs when a change occurs. In an IPv4 world, I never have to have my internal systems change anything, ask for a change, restart, hup or whatever. The external IP changes but the internal IP stays the same. Everything behind the firewall continues to work *exactly* as it was before, with zero administration. All that changes is the edge device (which picks up that the IP address changeover has occurred) and DNS (driven dynamically by the edge device.)
Now, I could try mucking about with prefix validity lifetimes, but then I'm still changing the IP address that the applications on that system see. There's all sorts of applications that need restarts to handle address changes and that's very, very bad.
The solution, of course is using ULAs with 1:1 NPTv6 or Map66 at the edge.
Ivory tower types my not like that we all have 30+ years of legacy cruft to drag around, but fuck them in the face with a rototiller. I couldn't care less. We do have 30+ years of legacy cruft and that isn't going away.
Applications don't like having their IP addresses changed. That means that you either have to set up the application for all possible IP addresses (and defend all possible IP addresses) before the app starts. Frankly, this is often not possible in cases where you are trunking in a second ISP to handle load changes or ahead of a known outage/changing contracts/etc.
Alternately, you have to restart your apps every time a change occurs. That's just flat out unacceptable.
Radvd doesn't solve these problems. All it can let you do is assign new global IPs to your systems when a change occurs, assuming that the stars align right and the things actually handle multi-IP stacks properly, actually honour route expiration and so forth.
Load balancing, as you said, requires NAT. I don't think the future is overloading NAT as we have in the IPv4 world, unless you live in Canada where the ISPs are douchecanoes that don't hand out prefixes. (May they burn in the eternal fires of their own greed.)
At a minimum you are going to do 1:1 prefix translation NAT to get proper load balancing, which is exactly what I use and advocate, and something that makes the ivory tower nerds' heads explode in an ideological rage.
To them, end-to-end is a religious concept that takes precedence over ease of use, profitability, manageability and even common sense. They will attack your professionalism, question your parentage and I wouldn't be surprised if they'd just shank you in the street with a sharpened toothbrush for having the temerity to suggest that "horrible internet breaking kludges" like 1:1 prefix NATing are required in the real world.
I can't stand those fascist wastes of carbon. I would not shed a tear if each and every last one of them get cholera and shit themselves to death. We wouldn't be in this mess, requiring "kludges" like prefix NAT if they had removed head from sphincter at any point in the multi-decade development of the IPv6 protocol to acknowledge the actual functional reality of the world in which the protocol - and the applications that use it - must actually function.
The network will adapt to serve the needs of the applications that make the business money. The business will not adapt to serve the desires of the people designing the protocol. That's life, and the ivory tower types need to fucking deal with it.
Re: Getting more peopel to adopt IPv6
My ISP doesn't hand a prefix. It only hands off individual IPv6 addresses to devices directly connected to the modem*. Nothing else.
No other ISPs offer IPv6 to end customers at all here.
Even if I could get prefixes, what if I want to dual-home, or to switch from one ISP to another? The end-customer and SMB ISPs don't offer BGP to us, and that's assuming we're even trained to handle such a thing. I can buy dual-port IPv4 routers that do load balancing and failover and don't require me to renumber my entire network to accomplish it every time there's a failover.
How does IPv6 handle these scenarios? Hmm?
I'm deeply interested, because all I get from the ivory tower types it "sit on it and rotate, those scenarios don't matter, prole."
My response to them is "your end-to-end doesn't matter, assclown" followed by IPv6 NAT. When the protocol is ready to meet my needs then I'll use it as designed. Until then, fucks given about ideological purity of the protocol = 0.
*I don't care if you want to "blame my ISP." Eat 10,000 sacks of wiggling phalluses if that's your response. There are no choices of ISP for the end customer. What the ivory tower douchepopsicles have failed to comprehend from day one is that the ISPs dictate terms to customers, not the other way around. And the ISPs give zero fucks about anything except how to extract the most possible money. I don't care about what the spec is, or how it's intended. Only how it is actually used and what's available to me. Both from ISPs and from device vendors. Everything else is masturbation of the most pointless and vapid variety.
"I suspect the resistance I often observe regarding IPv6 addressing, loathing of SLAAC, and devotion to DHCP, is fundamentally Calvinistic."
No, it has everything to do with wanting control over out own networks and endpoints. Even little things like "renumbering" in failover or dual-homing scenarios for SMBs that don't have BGP. We don't care what ivory tower intellectuals want. We want functional, cheap, secure and private. IPv4 does that now. IPv6 destroys it.
Re: "one that we have never heard of"?
"Yep - that seems most likely to me too. Windows Phone is already selling more than Apple iPhones in 16 territories."
Poverty tier territories. How is it against Android and Symbian in the same places? Or against "nothing at all?"
Windows Phone: the mobile OS where you have to give a really long think about using it, even when the alternative is "nothing at all."
Why not build your own VSAN?
Do check that AHCI is supported first, hmm? Oh, it's not? You need to pay for ...and pay for...and...oh! How interesting! I'll just...wait, a little bit of...wow. That's expensive.
Maybe, maybe not. It really depends on who is obtaining clue when.
"Dude, what the hell do you think Motorola is going to do; you think they're sitting under some huge mountain, cracking their knuckles as their evil plan to trick users into divulging information which is on the hardware of Motorola phones already bears fruit?"
Yes. There's no money in shipping hardware; or most software, for that matter. The real money is in advertising. Do I believe that Moto - and every other tech company out there - want to know where I am and what I am doing 24/7/365? Absofuckinglutely. That's big money, and they'd be doing a disservice to their shareholders if they didn't attempt to scrape and sell it.
"Again, you assert "worst case" that is, to be blunt...dated. I run huge databases virtualised all the time. Ones that pin the system with no ill effects and no noticeable difference to metal."
Whatever happened to your previous statement that it is only by pushing the system to the redline that we learn tings? Which of the two assertions isn't true? :)
I don't see a contradiction. I pin my systems. In testing and in real-world workloads. I believe it is absolutely required. What i don't believe in - and let's be perfectly clear here - is finding edge case scenarios that don't work and brandishing them as a reason to avoid a technology in all instances. If there are edge case scenarios or configurations that don't work, let's find them and then either fix the issue or not use the technology for that application.
That said, I can - and do - push my systems to the redline with my workloads and I do not see the results you see. That says to me that your results are dependent on your config and your workload. Thus I cannot use your scenario as a generic "virtualisation imposes a huge penalty" catch-all, nor can I extrapolate from the fact that you encountered a high-overhead scenario to state categorically that this is why something like "virtualised server SANs" are a bad idea.
"losing 40% of performance would also crank up your costs by a similar amount. That's not an insignificant hit to the bottom line."
I agree, losing 40% of performance is a big hit. That said, my experience from both synthetic lab testing and real-world results do not show a 40% hit, or anywhere near. Closer to 6% for redline workloads with 4% being the average.
4-6% falls into the "perfectly acceptable tradeoff for convenience" category for me. Again: I cannot accept your "40%" assertion without testing, and thus I will use my own numbers for the time being (and the workloads that I am aware of) and say "virtualisation is a great technology with a more than acceptable tradeoff."
"But the most important point I would like to make is this: "Don't listen to my numbers - produce your own based on your workload." By all means, use my methodology if you deem it appropriate, and/or point out the flaw in my methodology. But don't start with the assumption that the marketing brochure speaks the unquestionable truth. Start with a null hypothesis and go from there. Consensus != truth, and from what you said I think we both very much agree on this."
When have I ever accepted consensus on anything? Point me to an article where this has occurred. I test things all the time. It's my job. If I disagree with your take on virtualisation it's because your numbers not only aren't close to mine, they're in a different postal code.
I don't have a chip on my shoulder about virtualisation, or metal, or really any technology. Frankly, I don't give a damn one way or another. What I am saying is the following:
1) Your numbers have to be reproduced before they can be believed
2) Determination of how relevant your workloads are to real-world workloads as run by, well, anyone has to be made.
3) If you can evidence reproducible workloads that show 40% virtualisation overhead then there are people at VMware that will want to see this, reproduce it themselves and solve the problem by making a better hypervisor. I know many of them. They're good people.
In my experience, virtualisation is between 4% and 6% overhead for every workload I've tried. If you've workloads outside that range, I consider them an exception. An interesting one, worthy of investigation, discussion and remediation, but until we get more widespread testing on various workloads to see where they fall between my experience and your own I simply don't have enough data to kybosh hypervisors as a concept.
Again, you assert "worst case" that is, to be blunt...dated. I run huge databases virtualised all the time. Ones that pin the system with no ill effects and no noticeable difference to metal. I also strongly disagree with your assertion that you cannot give up an erg of performance in the name of convenience; that may be your personal choice, it certainly isn't mine.
As for "running virtualised causing a substantial overhead on memory I/O" I have maintained this particular item for some time. Specifically that "features" within most hypervisors to optimize RAM usage create a dramatic overhead on the system and they need to be weeded out. There is also the issue that many virtualised systems = many OSes caching to RAM. This changes the game versus each system having it's own dedicated setup, more than CPU sharing, I believe.
Databases used to be a big problem on hypervisors. 3-4 years ago. We've come a long since then, and it's only the true edge cases that still show issues. That said, isolating an edge case enough to reproduce it on modern equipment and hypervisors is always a fun exercise.
So if I seem skeptical, that's why. You write like someone who did a bunch of testing in the ESXi 4 era, went "pfaugh, virtualisation" and then put up a "get off my lawn" sign until the end of time. 2-4 years ago, I wouldn't have put a gigantic 100GB DB2 instance in a hyeprvisor. Today? Not a problem. Oracle still gives me shit...but that's Oracle. MSSQL doesn't bat an eye about being virtualised and Pervasive runs like a dog no matter what you stuff it into.
MySQL can be tuned to run in anything. I have virtualised instances that work fine, others don't. I haven't, however, seen a different to metal worth writing about in years.
Now, maybe my databases are "poorly optimized." They certainly are I/O bound in the extreme. That said, I test with real-world workloads, not theoretical constructs. As I said above, I'd love to assemble a lab with a real-world workload that can reproduce what you're saying. It sounds fun to explore.
That said, if I seem skeptical, please bear in mind that your discussion does mirror any of dozens of conversations with some rather closed-minded anti-virtualistion folks that can't let go of stuff from the beforetime and look at what is on the table now.
Thus testing. IT should be about the numbers, not about religion. Not for you, me, or anyone. Ultimately, that was the point of the article I wrote: there's too much religion in IT. From marketing and sales to even the phoney baloney whitepapers many companies knock together.
Let's get down to the testing. Reproducible results that we can then determine applicability, market impact, use cases and so forth. That's the information needed to properly advice clients. :)
"On the subject of leaving resources dedicated to the host/hypervisor, that is all well and good, but if you are going to leave a core dedicated to the hypervisor, then that needs to be included in the overhead calculations, i.e. if you are running on a 6-core CPU, and leaving one core dedicated to the hypervisor, you need to add 17% to your overhead calculation."
I never said "leave a core dedicated to the hypervisor". I said reserve it some space. Typically 500Mhz or so.
As for this:
"the I/O saturation was a non-issue because the write caching was enabled, the data set is smaller than the RAM used for testing, and the data set was primed into the page cache by pre-reading all the files (documented in the article). The iowait time was persistently at 0% all the time."
I would have to conduct my own testing. My lab results consistently show an ability to saturate RAM bandwidth on DDR2 systems. Your results smell like an issue with RAM bandwidth, especially considering that's where you're pulling your I/O. I will look to retry by placing the I/o on a Micron p420M PCI-E SSD instead.
I also disagree with your assessment regarding near/far cores on NUMA setups. Just because the hypervisor can obfuscate this for guest OSes doesn't mean you should let it do so for all use cases. If and when you have one of those corner case workloads where it is going to hammer the CPUs ina highly parallel fashion with lots of shared memory between then you need to start thinking about how you are assigning cores to your VMs.
Hypervisors can dedicate cores. They can also assign affinity in non-dedicated circumstances. So when I test something that I know is going to be hitting the metal enough to suffer from the latency of going across to fetch memory from another NUMA node I start restricting where that workload can play. Just like I would in production.
Frankly, I'd also start asking pointed questions about why such workloads are running on a CPU at all, and can't I just feed the thing a GPU and be done with it?
I flatten my systems all the time, not just in testing, but in production. I run full-bore render engines in a virtualised environment and I just don't see the issues you describe. That makes me very curious where the tipping point between my workloads and your simulation is. What needs to change in order to experience this dramatic drop in capability? Do I need to be on the lookout for it in my future workloads, or is it an artifact of using an ancient CPU or a peculiar testing configuration.
I don't have answers to these, but I've added it to the list of things to find out.
@Gordan; yup, I had missed it. In my defense, I hadn't slept in 4 days due to datacenter migration.
Let's address a few issues in the testing methodology you state:
"1) Testing is done by fully saturating the machine."
Testing should always be done by pushing the machine to the red line, otherwise we learn nothing.
"2) Not leaving any cores "spare"."
Leaving cores "spare" doesn't present a real test. However, the host instances should have reserved RAM and CPU on any production virtualisation deployment. It's a fairly common mistake not to enable this, and typically results in Xen/KVM showing badly compared to properly deployed instances. The hosts instances need wiggle room to do their jobs, especially with "noisy" VMs.
3) Pinning cores helps, especially in cases like the Core2 which has 2x2 cores, which means every time the process migrates, the CPU caches are no longer primed.
I pin cores all the time and never run into the issues you describe here. I have flattened multiple generations of systems and still don't see the disparity you do. What I wonder is if it is related to the Core 2.
Back in the Core 2 days I used AMD stuff, and they were well ahead of Intel in terms of hardware virtualisation support. Today's processors have any number of improvements over that old design and the introduction of proper hardware support in these generations of processors may explain the discrepancy.
The only time I have ever seen results like you describe is when I am able to saturate the RAM bandwidth. This is entirely possible with DDR 2 systems, especially when you are allowing memory deduplication on the systems, something that - at least in ESXi - is enabled by default.
I'd also have to look at your I/O subsystems as being suspect. It smell a lot like I/O thrashing. I will see if I can scrape together any equipment from that era and place it against both the AMD Shanghai systems I have as well as my modern Intel Xeons. I am very curious to see what will happen when I pin them.
Hey; took a brief look at this, and noticed a few problems straight away. First up:
"(VMware Player 4.0.4, Xen 4.1.2 (PV and HVM), KVM (RHEL6), VirtualBox 4.1.18)"
Only Xen and KVM are hypervisors, and they are the two that are the easiest to tune improperly. You don't have ESXi or Hyper-V here, and they are the real test of what virtualisation can do. VMware Player and VirtualBox are not hypervisors...or at least not Type 1 hypervisors. There is going to be a huge penalty for running those. Everyone in the industry knows that. That's why they aren't advocated for production anything.
I am really shocked you got such bad numbers for Xen and KVM, which leads to me wonder how they were configured...but being Xen and KVM, if you look at them funny they'll run like crap.
Very interested to see numbers with ESXi and/or Hyper-V!
Re: read cache does nothing
Yep, in my testing you have to have at least 30% read as part of your workload for it to have a tangible difference. As I have said many a time: storage isn't one-size fits all. Everyone's a little different and there's more than enough money in the space for everyone.
...even if I don't quite understand why anyone (excepting very select niches) would choose some of 'em
Do you happen to have information on specific workloads I can test in my lab that would prove your claim? I'd love to test that and write it up. Please get in contact if you have details!
Re: didn't you answer your own question ?
Not all CSAs are complex. Proximal is "fire and forget". vFlash will be there in August, I'm sure. There are others that are as simple, or close to. It's only when you start layering on the features that the CSAs get into "job security" territory...and I start wondering "why don't just go full-hog, use a server SAN and be done with it?"
Re: Pretty good reading
Twitter finds a way. That makes me think you just aren't working hard enough at your trolling. :)
Re: What's this thing suddenly coming toward me very fast?
Re: 17TB ??
No kidding. I have installed more than 17TB of flash in Q1. Me. With my broke-ass clients. 17 Terabytes whaaaaaaaaaaaa?
- Product round-up Too 4K-ing expensive? Five full HD laptops for work and play
- Review We have a winner! Fresh Linux Mint 17.1 – hands down the best
- Vid Antarctic ice THICKER than first feared – penguin-bot boffins
- 'Regin': The 'New Stuxnet' spook-grade SOFTWARE WEAPON described
- You stupid BRICK! PCs running Avast AV can't handle Windows fixes