Follow Slashdot blog updates by subscribing to our blog RSS feed


Forgot your password?
DEAL: For $25 - Add A Second Phone Number To Your Smartphone for life! Use promo code SLASHDOT25. Also, Slashdot's Facebook page has a chat bot now. Message it for stories and more. Check out the new SourceForge HTML5 internet speed test! ×

Comment Re:If it ain't broke... (Score 1) 205

Removing features is what made Firefox great. Firefox became a well-known piece of utter shit when it had added feature after feature and bloated to an enormous, complicated hulk of options lost in hundreds of options. Then alternate browsers came along with their slimmed-down feature sets, and people moved.

Chrome is ditching menu items few people use. It might not die of featuritis.

Comment Re:A John Deer bonfire... (Score 2) 445

Everyone seems focused on the farmers and their poor little butthurt selves.

What about the downstream cost? These failures reduce productivity and thus increase the cost of food. They draw money to John Deere for no value-add (rent-seeking). These things reduce the total number of products you can buy with your money (wealth), and reduce the number of people receiving (jobs) the money spent for a given investment of labor-hours (wages).

The inefficiencies of requiring a tech to stop by just to sign-off on a hardware change that actually works--and to charge $500 for the tech to do so--result in a reduction of wealth across the entire economy at every income level, and a loss of (primarily lower-income) jobs. This is an attack on all Americans and on all recipients of American agricultural exports.

Comment Zram? (Score 1) 63

Are we getting zram configured with swap device size = 4x RAM, mem_limit = 50% RAM, vm.swappiness = 100? That will give effective doubling of RAM for approximately no performance hit.

've not found the performance asymptote yet. The crude theoretical limit is exchanging 100% of working RAM for 3x the compressed space (100% compressed to an average 3:1, although 4:1 happens sometimes--typically you average 3:1). The frequency of page decompression increases as you reduce the working RAM (the part not holding compressed data). Page decompression takes approximately twice as much time as a worst-case CPU cache miss (full row-precharge, RAS, and CAS), so decompressing pages with relative infrequency is cheap, and can be effectively free.

Generally, a block of code operates multiple instructions per byte of an immediate working set, so e.g. 16KiB eats 400,000 CPU cycles decompressing and then the application spends 4,000,000 cycles operating on that area. The application will use part of its hot working set as well, so the time spent working on that page spans more cycles than just that. Depending on how fast the program works through working set, you can end up expending approximately 0% of CPU on swapping into zram; or, if the working set space is tiny and swapping is frequent, you can expend much of your time swapping in and out.

Prefetching and caching further complicates this. The Linux kernel can background-prefetch swap by reading sequential pages ahead or by taking explicit hints via madvise() such as WILLNEED (get the page ready), SEQUENTIAL (aggressive read-ahead), or RANDOM (read-ahead not useful) from the application. If the system uses 99.7% of the CPU, then there are 3mS per 1 second interval to decompress pages into a cache (without freeing from zram), and to compress pages into zram (without freeing from RAM--mark as not-dirty). That's 4.8 million cycles per 1.6GHz core--on a 4 core phone, that's plenty to compress many pages per second, and decompression is way fast. Efficient prediction can really reduce the cost of swapping into zram to a real-time 0.

As I said: that's if you have the CPU time unused. At 3mS per 1 second interval, as above, with 26 cycles per byte, a 4k page takes 106,496 cycles to decompress. With four cores loaded to 99.7%, that's 45 pages per core or 180 pages, 720k per second you can afford to swap in--no room for swapping out. If you're not running through that much cold-set data per second, zram costs power usage, but not performance. As well, the amount of data you can churn through is limited by nominal CPU usage, and the churn in practice is nowhere near the theoretical limit (effectively a MOV %eax,$addr loop with $addr+=4096 iterations), so low-CPU-usage operation would tend to inflict less power consumption.

I didn't go looking for the performance asymptote because the return between 2x and 3x RAM capacity isn't worth bothering with. With half the working set, the amount of swapping is negligible; even when you start digging deep into swap, the rate of data moving in and out of zram is low enough to not inflict a visible performance impact. The real-time impact vanishes as soon as the CPU is more-idle, so if there's a 30mS stall every 10 seconds you suddenly have time to catch up on 3mS of slowdown and break even. This is, thus, a fine place to simply settle for now, without worrying about the variability of workloads like you'd have to if you pushed to the limit based on large data analysis of common workloads.

Comment Re:The death of Twitter (Score 1) 195

There's actually a girl petitioning to have Twitter ban anyone who says something mean. She's complaining that people say violent things or threaten to rape women... which, of course, we all recognize from third grade when everyone would threaten to blow you up or something. We're pretend-adults now, and that means sometimes someone 5,000 miles starts yammering about how they would rape you, as if he could.

Comment Re:Jumping ship before the bottom falls out. (Score 1) 200

Capitalism is a system which can generate flaws due to outside meddling. Businesses are part of the capitalist system, but can do things to manipulate it--hence why we have things like anti-trust laws to keep illegal cartels from price-fixing everything and breaking capitalism.

There's a point to minimum wage, and a lot of artifacts caused by it--the drift of minimum wage by inflation creates an excess of wage-depressed jobs (inflation lowers the wage), and then adjusting the wage reduces the number of available jobs. I think minimum wage is outdated; at a point, technical progress makes the cost of supplying basic needs cheap, and so welfare services can transition to a Universal Basic Income.

Structuring a UBI that isn't destructive is still hard--I designed a Universal Social Security which has to control for risks and handle transitions--and that warrants a lot of thought and consideration before just screaming that we should "give everyone free money." A viable basic income acts as a patch on capitalism, as well: it ensures that people have both a share of the economy (at least, my USS does) and thus benefit from trade and technical progress in full and it gives them an alternate option. Instead of working 40 hours at $8/hr or working 0 hours for $0, you can work 40 hours at $8/hr plus the benefit or work 0 hours for just the benefit (i.e. work 0 hours for more than $0).

The thing about having money is more money is worth less. If I make $40/hr, I can get $5/hr by doing more work... but it's only a little better off than current, and I don't want to work 80 hours per week for $1,800 when I can work just 40 hours for $1,600. If I make $5/hr, an extra $5/hr means I bump from $200 to $400, which is a huge boost in my standard-of-living (imagine living on $800/month, and then suddenly you have $1,600/month). Imagine if you have enough money for subsistence--you can get a roof over your head, enough food to eat, utilities, and soap to wash yourself, but not much of anything more at all--and suddenly someone's offering you 100% more on top of that. You can squarely give them the finger if they offer you $50/week to break your back, but you're going to benefit hugely if they offer to double your income.

Setting the standard-of-living like that and allowing people to rationalize about the improvement in their quality-of-life cuts to the heart of capitalism's assumption of rational actors: people aren't going to die without the money, so you have to offer them a wage which benefits them. At some point, that wage is going to be worth the 40 hours of work to a sufficient number of employees.

Comment Re:Failure is always an option (Score 1) 200

They basically lied about what the purpose of the app was, calling it a ride-sharing service when it's a taxi service.

Everyone else also lied about the purpose of the app, which allows independent drivers and passengers to find each other, in a bid to declare Uber drivers are employees--yet nobody has declared Amazon Mechanical Turk users "employees".

We're not really equipped to understand the gig economy.

Comment Re:Failure is always an option (Score 1) 200

Once Uber is gone, we can go back to having no centralized system to distribute ride hails and ride offers. Independent ride-sharers can struggle to find passengers; passengers can pay inflated prices and have longer wait times trying to find a driver, while drivers can spend more time driving around without passengers and make less money per hour despite charging passengers more for the time spent actually transporting them.

Comment IBM to discriminate against 2,000 students (Score 2) 32

IBM to practice discriminatory hiring practices against 2,000 students over 4 years in a bid to reduce the likelihood of qualified college graduates receiving degrees. Inflation of the supply market for degree students and subsequent downward pressure on salaries to save billions over the next decade. Landlords gearing up for the Evict College Students To House More Veterans Credit.

Comment Re:and china is going to face lot's of people out (Score 1) 297

America has outsourced manufacture to China, reaping the benefits of a great trade advantage: with under 5% unemployment, we have access to cheap goods and have a smaller export economy than import economy. We go out to people who make crap cheap, get that crap from them, and sell them relatively little.

When robot automation--the tag we're giving to the next visible step in technical progress--takes over manufactories, one of three things will happen.

If that automation comes at a pace the economy can handle, then the purchasing power increase will turn over jobs at a non-critical rate. China's manufacturing labor force, as a particular example, will experience a small nudge upwards in unemployment, and will recover those jobs as prices come crashing down and export markets dramatically expand to create new demand. They'll end up needing 10 Chinese workers where they previously needed 50, and selling 50 products where they could only sell 10, getting a net zero loss of employment.. America and Europe will end up wealthy as all hell importing Chinese goods to the same specifications as always (which, face it, is typically a WalMart supplier demanding cheap-cheap-cheap, although there are plenty of high-quality goods coming out of China), but at a fraction of the cost.

If that automation comes at a rapid pace beyond what the economy can handle, China will experience loss of employment exceeding expansion speed of its exports. Unemployment will soar, and it will take years for China's economy to recover. The goods produced will still be cheap, so America and Europe stay wealthy--and the export market to those continents will at least help China recover.

If that automation makes it cheaper for America to produce goods at home than to import them from China, then China's export market collapses. America ends up with locally-made goods because Chinese goods are more-expensive than USA-made goods; meanwhile America is insulated from loss of export markets because its export markets are small, as it has the great advantage of an import trade without the risk of an export trade.

America's market is self-sustaining, in large part. We produce a lot of economic activity servicing domestic needs, rather than exporting; we're insulated from global market shifts in that way, so anything that boosts the productivity of foreign nationals just makes us stronger, since we can import their stuff and make something else here for ourselves.

Imports make us strong. Exports make us the lap dogs of other nations, subject to their whims lest they embargo us.

Slashdot Top Deals

Chemist who falls in acid is absorbed in work.