Forgot your password?
typodupeerror

Comment Is this a software or hardware implementation? (Score 1) 64

The mention of a NUMA node has me unclear on whether this is a software or hardware implementation. There are several vendors either offering or showing around proofs of concept to try to generate interest, for CXL memory devices(which all essentially look like a NUMA node that is nothing but memory controller); mostly aimed at hyperscaler use cases where you want the improved performance and platform features of current gen servers; but your last gen servers were beefy enough that just disposing of them would be getting rid of a relatively titanic amount of DDR4 that is still faster than most NVMe. Some of those attempt to offer software-transparent compression, some just put CXL on one side and memory controller on the other and allow you to do (mostly) agnostic mixing of memory generations on anything new enough to have some PCIe lanes support CXL extensions.

I suspect that it's mostly my ignorance that is to blame; but what I don't understand about implementing memory compression(especially the schemes that try to do it transparently with high speed general purpose compression/decompression in hardware) is how you compensate for the fact that the amount of memory you need is no longer predictable without significantly more effort(potentially untenably more if you are using RAM because latency is critical).

With normal uncompressed RAM it just demands RAM in direct proportion to its size. Potentially hideously wasteful if there's some memory-backed XML-spew log that would zip down to 10% of its nominal size; but predictable unless you've got memory safety bugs. If you are compressing your RAM suddenly you've got some uses of RAM that are functionally uncompressable and require 100% of the space their nominal size suggests they will; other things might compress exceptionally well and save you 90%; and some might change unpredictably from moment to moment depending on what needs to be stored there.

When you are doing FS compression and dedupe for backups and stuff that is normally manageable; on average enough compression is possible enough of the time that you can safely assume that you'll do better than you would if you just didn't try; and you can just keep an eye on how quickly the big SAN appears to be filling up as versions accumulate and (if tapes or other fixed-sized media are involved) just change the backup media more or less quickly; do you do that for RAM? Just use the big slack area for FS caching or something you can drop on short notice in case a burst of incompressible data comes in? Do you essentially have to rebuild how your entire workload handles RAM so that it considers, at least approximately, how well a given use of memory will compress ahead of time?

Given the sorts of files and data structures you commonly encounter I can easily enough believe that compression is worth the trouble a lot of the time; but unless you are leaving a lot of slack in your available RAM it seems like a situation where, under certain circumstances, you could go from being fine because most of what is in-memory compresses well to suddenly needing as much physical RAM as you do logical RAM because you have a bunch of already-compressed or incompressible data would markedly increase the complexity or potential for things to go wrong.

Comment Re:Think smaller (Score 2) 64

> you apparently desire to use systems beyond their design points

Who doesn't include cost in design?

If my CPU/SoC is plenty fast for my task and the DRAM is faster than I need it to be and a CPU instruction to compress takes less power than a write out to the bus - it would just be wasteful to manufacture and purchase twice as much DRAM as the application needs.

Either the end user gets a better price (and all money is the result of expending energy, so we save again) or the manufacturer makes a larger profit (in a constrained market).

Now then - all you lunatics embedding Electron and costing me 400MB to send an 80 character text message - we need to talk about this.

CRAM seems like a great idea but it's not the solution to not caring about the Craft.

Comment Long Road (Score 2) 74

JPEG-XL is a good format but I just realized yesterday that Google Docs on Android doesn't support inserting a webp image a decade after Google was pushing it. I had one from a website and needed to run it through imagemagick first.

Android supports it, all the apps using android image primitives supoort it, but one of Google's flagship apps still doesn't.

We used move much faster thirty years ago. If an app supported say GIF, PNM, and TGA when JPEG came out it was supported in the next release.

Hopefully this round will be better. It's probably a management problem ... maybe they will listen to their chatbot since they don't listen to their engineers.

Comment Amazon Broke Alexa, Home Assistant FTW!!! (Score 1) 47

Amazon has totally FUCKED Alexa, and I make few apologies for my tone, other than that I was raised in a blue-collar home.

They had an amazing product that used to be, quite frankly, what I imagined the future should look like.

Enshitification ensued... They started whittling away features. Aux ports were removed. I had to find older devices, or pricier devices for aux. Then they screwed up commands. Yes, the very things that it's supposed to do at a basic level.

Now you have to make specific routines, or inference will turn off the porch lights when you say "turn off the patio lights." Despite THE DEVICES BEING NAMED CORRECTLY IN THE APP. Why? Alexa's AI infers that you mean something you didn't say. I asked it to unlearn that and actually use the device name I've been using for a decade. The response? I can't do that, Hal. The workaround is to build out specific routines for all the lights in your home.

ARE YOU KIDDING ME?

Guess who now has to have a real AI build out a DIY solution because enshitification is so bad that TURNING OFF THE GD LIGHTS NO LONGER WORKS.

Seriously, if, like me, you used Alexa for a whole home setup and it's now broken... give Home Assistant a try. You can tie it into Alexa if you are still hung up on a few features Amazon has.

Comment Re:Aux port - how could it even technically pause? (Score 1) 47

I don't know the protocol but old phone headsets had a 2.5 or 3.5mm jack with an extra ring that got you play/pause/hook/next/last.

Hypothetically that could have been implemented. I had a collection of Alexas that got binned as soon as they got caught spying for police so I never got that far. ESP32 is better for nerds anyway.

One thing Australia does right is a statute naming removal of features as a violation of contract requiring full refunds in these circumstances.

Comment Re:First responder perspective (Score 1) 199

> AM radios in cars only cover the small intersection of people who don't already have an emergency kit containing an AM radio, but do happen to be in a working vehicle during a disaster.

I feel like the number of people with a working vehicle is much, MUCH larger than the number of people with "an emergency kit containing an AM radio."

The main point being that, if you happen to be traveling at the time in a potential emergency situation (either because bad luck or actively trying to evacuate), you can use the AM radio in the car to receive news and important information.

Just put the radio in the car where it's most likely to be used when needed.
=Smidge=

Comment Re:You need this for an emergency (Score 1) 199

> The electronics that drive such powerful motors produce HUGE quantities of RFI

The electronics that drive such powerful motors are inside thick, cast aluminum housings, as are the motors themselves, and those two things are usually bolted directly to each other to form one massive lump. I don't think you appreciate how much RF shielding goes into all that already because, y'know, there are a lot of other electronics in the vehicle that might get fucked up by it. The $5 worth of metal" would be the shielding can around the radio itself, not the HV inverter circuitry that is already encased.

The "Electric vehicle electronics interfere with the AM radio signals" argument is complete horseshit. The AM radio in my 2020 Kona EV often works better than the FM radio for some reason. It's not an especially expensive vehicle so the cost of making it work certainly isn't a reason to not do it.
=Smidge=

Comment Re:If they are thermally efficient enough (Score 1) 128

Stupid and malicious are different.

The offered narrative is "let us build the data center AI control grid now because it's only temporary until we can move it to space".

You and I both know that's not thermodynamically possible with known science.

So do the people saying it.

We have a real problem with Positive Projection where we are decent folks so we project that on people who are not. That is an error even though most people are decent folks. The parasites are not.

I only recent learned that Hanlon's Razor comes from a humor book about Murphy's Law from the early 80's. It's not some ancient axiom of wisdom - it is used by the Cluster B disordered to mask their nefarious deeds.

If you talk about this with most people these days you'll get the Positive Projection script executed like an autorun.

Everybody should turn off autorun whenever possible. Major risk.

Comment Re:We're probably going to find more (Score -1) 34

> Gardasil

It's sold as an "HPV vaccine" but it only targets about 4% of HPV viruses, specifically the ones most likely to cause cervical cancer in women in their 40's. It's described in the Merck literature.

Not even the HPV most likely to cause throat cancer in men (usually acquired from lady parts).

If cancer treatment advances at the current rate (AI discovery docs estimate 9 years for the supermajority) it's possible that the Gardasil fatalities will have killed more teens than prevented deaths of women.

It's like a Drake Equation for cancer - the coefficients will determine the narrative either positive or negative. This is where free choice is ethically mandated.

Unfortunately there is considerable religious fervor about such things so very few people wants to scientifically discuss nuances.

Comment Re:Constructive responses anyone? (Score 2) 70

Why isn't EU sponsoring specific features and fixes it needs?

Or assign some of their own developers to submit pull requests.

Or hire *some Europeans* who are unemployed because their war is killing industry.

Let's hear from their project manager instead of faceless wankers and the people responsible for sales.

Comment Re:Do you actually use them day today though? (Score 1) 105

Here:

Those dudes probably don't know how to make the difference between file cache and memory usage. All computers including those using Linux will use ALL their memory for file caching e.g. caching the content of files into memory.

Here is an example:
free -h
                                                        total used free shared buff/cache available
Mem: 7.8Gi 617Mi 586Mi 53Mi 6.6Gi 6.8Gi
Swap: 15Gi 66Mi 15Gi

This computer has 8GB of memory, ~586MB of free memory, and ~6.8GB of available memory because it uses the spare ~6.6 GB for file caching, all OSes do that. That memory used for file caching is available instantly for the OS at anytime and must be excluded from the memory the OS uses. All spare memory will eventually go to file caching. Again all OSes work like that.

So 8GB ram 586MB free and 617MB used by the OS and running programs so 6.8GB available

So you need to be able to tell the difference between free memory (you shouldn't have any or very little if your OS works correctly) and *available* memory. That memory used for file caching is avaiable on demand at any time for the OS and running programs

Also don't look at "virtual memory" used you need to look at "resident memory"

Example:
On the same host as above:
1004 mysql 20 0 1759176 355056 7560 S 0.0 4.4 61:13.76 mysqld

mysqld uses 1.7 GB of virtual memory but only 355MB of resident memory. That 1.7GB of virtual memory doesn't really matter. All OSes including Windows work the same way although they often name thing differently. You need to know how to interpret what you see...

Slashdot Top Deals

Real Users never know what they want, but they always know when your program doesn't deliver it.

Working...