One Classy Dame - part the third

Found another paper, only two pages, that makes the case for non-filesystem storage with SCM.

The existing OS structure of file systems as a kernel-level service may no longer be necessary with storage class memory, and causes unneeded complexity and lower performance.

The paper is undated (another paper by these authors notes it's from 2011), so the idea of using SCM the way I want it used has been living for some time. As mentioned in these missives, with regard to RDBMS use of storage, I've often said that industrial strength RDBMS have all provided access to 'raw' devices (in *nix terms), although most vendors have been discouraging that approach for some time.

In addition, some applications, such as databases, bypass the file system but still rely on the lower levels of the storage stack.

The latter paper is more complete, in that it documents a PoC implementation on linux. And is somewhat different from a single-level store on SCM.

It seems that there are a few identifiable issues:
1 - a mix of DRAM and SCM makes the most sense, since code need not be persistent and need not be hobbled by slower access
2 - kernel code that knows how to handle access to both types of 'RAM'
3 - application code that knows how to write transactions to SCM, rather than files
4 - limitation of SCM by the amount of memory available on a X86 motherboard; currently 256GB, modulo https://www.quora.com/What-is-the-most-RAM-a-computer-has-ever-hadbespoke> boards not in general circulation.
5 - unlike disk based storage, expansion has a (nearly?) hard limit, so RDBMS applications would have to result to evicting aged data to SSD/HDD on a regular basis

Here is a Master's paper from 2019, so rather current, on transaction semantics. The paper isn't geared toward RDBMS or ACID, rather to general data consistency. A bit dense, but worth the effort.

Deja Vu All Over Again - part the fourth

Well, we're revisiting Olde The Manchurian President's stupidity. All over again.

The White House explained that its May 9 decision to dismantle the directorate was intended to "streamline" operations. In reality, it was far more than that. Memories of the Ebola crisis in 2014 have faded, and the Trump administration implicitly is signaling that it flatly rejects the notion that health security ranks as a true national security policy priority.

This is what happens when poorly educated shitkickers in the empty states get to say who runs the Damn Gummint.

Thought for the Day - 24 February 2020

OK. So, today the Dow dropped 1,031 points. If you know of any econometric model that predicted that, let me know. Ditto for any econometric model that knows what to do with that info. Most of the real world is driven by events, not data streams.

I Am A Patriot

I pledge allegiance to the Hair of the Fascist State of Trump, and to the Barr for which it stands, one Tyranny under Ivanka, divided, with poverty and disease for 99%.

Krugman vs. Zombies

It's too much to ignore

What's your name?
Who's your daddy?
(He rich) Is he rich like me?
Has he taken, any time (any time)
(To show) to show you what you need to live
-- 'Time of the Season'/The Zombies 1968

In today's rant, Krugman calls out zombies in the Right Wingnut brigade.

And crucially, the housing bubble was an international phenomenon; Spain had a bigger bubble than we did, followed by a worse slump. Did the U.S. liberals force Spanish banks to make bad loans?

And, of course, what's worse is that Spain's experience was largely based on bad vacation home loans. This is one of them.

The Great Recession had its roots (not that I'm following any orthodoxy that I know of) in the DotBomb. Following that meltdown, all the Big Money Holders went looking for some other place to stash their excess moolah. What they wanted was high return at low risk of another meltdown. No such instruments exist, of course. But, the answer was obvious to everyone: mortgages, particularly residential. Not spectacular returns, but better than Treasuries, and there's never been (so the legend went) sector/nation wide collapse of home mortgages. The problem was that if you had hundreds of millions (or more) of moolah, buying up individual mortgages was out of the question.

Enter, stage right, securitization instruments. There was a new problem: where was the necessary supply of securities to sop up all that excess moolah? The answer stage further right, was Countrywide, making loans for McMansions to the poor. If it all stopped there, then the mortgage companies would have gone belly up once it became clear that the poor couldn't pay for McMansions. But no one noticed when Blythe Masters invented the credit default swap (CDS). This grenade allowed anyone to bet on the solvency of anyone else in the form (titularly) of insurance, regardless of whether the bet was made by anyone involved. The result was a chain reaction through the finance sector when the Viagra wore off. The assumption, clearly, by the likes of Countrywide and the regular banks that lined up like lemmings, was that if a few/some/many of these subprime McMansion mortgages went stinky, well we still have the house, so we'll just sell it again and clear the note. The 'asset' didn't disappear. But supply doesn't create its own demand, alas.

Only the nuttiest of the Right Wingnuts still bray that supply side mantra, 'supply creates its own demand'. If that were true, producers would continue to not only continue production in the face of deflation and collapsing demand, but take advantage by boosting output. You do believe that's how the Real World Works, don't you? If it were true, there would never be recession, much less depression in any economy any where any time.

Among the early examples of mortgage-backed securities in the United States were the farm railroad mortgage bonds of the mid-19th century which may have contributed to the panic of 1857.
-- the wiki

What's that fable about those who ignore history?

Thought for the Day - 17 February 2020

Working through a missive, which deals in some degree with the status of STEM in the economy and may appear in the next few days. The main point being, as Dr. McElhone was fond of repeating, "the answer is intuitively obvious to even the most casual observer". What's obvious is that much of STEM use in both the private and public sector is in non-producing slots. So, it comes as welcome support that real reporters have found explicit cases where that's true.

The former employee said that there were other red flags: There were more managers than engineers at Essential [fancy smartphone vendor that just went paws up], and many quality assurance engineers, even though there was only one (poorly selling) product.

I shouldn't say so, but I told you so.

A Must Share

All in all, this might be the funniest post I've seen in a very, very long time. You must read. If you have a developed sense of humor. How I came to find it is certainly TMI.