7532yahoogmail

Disagree. Somewhat strongly. The last thing we need are more nerds in the pejorative sense that can't see past their particular electrons in their favorite elements in the dirt. You gotta at some point lift your gaze. A major issue at offices for team and divisional level roi and competitiveness is silos and the wrong assumption that everything is technical or should be. Anything to pursuade the pendulum to the middle is a benefit. Anything that helps identify and compose parts into a better whole is good.Specialization and narrow focus are good but only when mediated and integrated. It takes both.

According to Stanford prof who launched ramcloud Facebook indeed uses MySQL. But MySQL by itself was hopelessly slow. That's why Facebook has over 4000 memcache servers (this as of 2009). By the time you add ram underlying disks he estimated 75pct of all Facebook data is cached in memory. That's why it works.

op - thank you for posting. Cogent. Well argued. Timely.

You're confusing cause and effect. The goal of the south was slavery and leave if they did not get it - cause. The north was then handed a problem to which civil war. Effect. The south lost. Lincoln was trying to avoid bloodshed by arguing that the union could not be recinded unless all agreed. As such he was arguing for a third way to resolve the issue. The south didn't find third way. It got the problem it wanted and paid the price for it.

Wrong. Absolutely wrong. The continued divisive nature of American politics is not because of enemies or the two party system. It's incompetence and lack of backbone. Neither political party has had the conviction of enlightened reason whence backbone comes to do the right thing. Instead Washington DC ineptitude of politicization of what matters whether in practical administration, or basic fiduciary responsibility has been done. As the problems go from bad to worse DC instead aggravates it in two basic ways:

- plays victim in units of outrage. Knock it of NRA groupies: the Dems aren't gonna take your guns. And on the left: the political correctness of victimization isn't helping the underlying injustice where it rests. The American public has bought into this. Shame on us.

- DC but most especially the US Congress has no agency anymore. They gave up. Politicians do not do today but instead are constantly uttering cheap symbolism about what they will do next time.

Op - thanks for finding and posting. I enjoyed reading it, and was pleased to see evidence intelligent rhetoric with heart. Now at this point Lincoln said he would not stop slavery -- that would change though.

Wow. Hell of a good read. And smart points too.

I do not object to publishing a better result. Like the paper said serious craft goes into that and there's nothing wrong with typing it up and having it published. But it's not science; one day one time some how some way the black boxes have got to open up to address why. This is a very valid question and on point criticism. Even in basic software development why (eg requirements) should be known. It's not consequence free free to proceed otherwise.

Great read and better distinction

Using TLA, spin and others will help compute actual numbers to see reachable states etc

Wow. No.

Engineering school was/is supposed to help us (you) move beyond cynical judgements to thinking.

Agree. We'll put & explained.

Agree - rules engines are legion in commercial envs and a decent language or accessible non Java reit engine is something on my shopping list too.

I was talking to my wife about why something around the house was slow to get done. Well, Rust wasn't having that. For a full 30-mins I was on full defense trying to figure out how Rust got into the house. It's everywhere. And it likes to talk! I'm gonna have to get to know it better, because it seems I have no choice. Ok, satire out of the way, let's get to the real points.

The article was a let down at the end. Yes, less code and less dependencies equals quicker builds. No kidding. It does not deal with Rust itself, however.

But at commercial scale this is a real concern. We're a big C++ shop ... but for reasons that cannot be blamed solely on C++ itself, I quit C++ for the last 18 months for GO weary of the 4-day long build times, the huge executable sizes, and fighting the C++ compiler. The only thing worse than a C++ compiler in a bad mood is Oracle's PL-SQL parser (dumb and silent) or when your wife is mad at you.

Problems committed by programmers:

- builds do not use PCH so C++ builds are indeed slow

- very old legacy libraries have circular dependencies and sorting that out is annoying

- certain important, hard to avoid legacy calls hit into a library chain of dependencies that quickly lead to very large executable sizes

- linking depends on .a files because having tasks link .so files is unreliable in production. Too many tasks, too many libraries, too many versions, too many deployments just too much lead to dependency mismatches leading to cores ... We still link archive libraries not shared but over the last years build teams have taken making the archive files so compiling is usually limited to app code plus whatever self-owned library code was modified. (Not talking language or OS libraries here; that's disciplined. Talking app libraries & tasks for which there are 10000s).

Thus on the whole we can blame the organization not C++ for not being as good as it should at commercial level, very large scale software management. Getting rid of legacy code or refactoring it is another weakness: for the above reasons the effort is often big, and there's always so much new work to do making management of resources tough.

We can blame C++ for other things however:

- the language is far too complicated

- the language involves some duplication of effort between headers and source files

- C++ inherits C's problems with #defines, macros, and other nasty things that break builds at scale with bad things in global scope. Just having a pre-processor is bad. C++ maybe should have been link compatible with C but it dragged in the whole edifice. Other OOP languages were smarter.

- C++ errors arising out of templates or certain other STL areas produce messages which are 2K+ each. It takes time to see what the hell when wrong. C++ often confuses you with the details. I hope GO generics does NOT do that.

- Making code allocator aware and capable i.e. to make things behave properly for performance, memory testing when everything should use a non-default allocator, debugging, and so on is real effort. Memory errors are not that easy to track down in C++ for something that appears to care about safety.

- C++ language complexity drifts into design complexity immediately. If you're <5yrs in C++ you can't really attack a serious project without having Meyer's C++ books side by side.

- A lot of what makes a C++ class or method "good" i.e. narrow contract, assertion checking, unit testing comes, if it comes at all, from the organization's engineering culture not from C++ itself. In other languages it's more baked into the language.

Of course GO avoids many of these problems by design to say nothing of quick build times. But GO built on 20 years of industrial experience while others created it along the way.

Other OOP languages may be better, but sorry the die has been cast. Ditching C/C++ for something better will still likely need a back door to C because there's too much of it to drop it entirely. Those working close to the kernel will need a C backdoor as well.

Agree. The guy needs to get a room with himself, get over it, and come back with something to say. Linux also isn't for desk tops by and large.

>So they did the next best thing: they changed to please the market

Slow down. This is the hackernews equivalent to "yada yada yadaing" over the real stuff. You say points big and silly you can't backup. I work at a business news organization, and know someone who just left WSJ. Now, think again how you'd tell them face to face they're niche? You're gonna tell them how the media business works? Like what are you going to say?Are you claiming FB is a new organization? In fact, are you really saying anything at all?

Those issues are important, but what I find most concerning about your reply is "the way our economical system work".

You're either not in management, are an incredibly crappy manager, or don't know anything about it. You do it for the money like some lame reach for that Tesla R&R refrain to argue for lower intellectual (ethics/morals) standards ... that's the beginning of the end for organizations ... what you fail to get is that other organizations who are not so easily sold your sale of good will be still doing the news and fighting the good fight.

Those who understand money the best and make the most over the long term know best money is NOT the measure of all things.

LMAX is a java thing. It's high speed, low latency messaging system used a betting facility in the UK somewhere where in certain betting situations, the number of messages drives up explosively high, and need to be well handled. Thus high, high speed and low latency with reliably low latency were key.

>However, it is also the case that sometimes the person on the other side is not well-motivated

Correct! There are some people fortunately < 5% from what I can tell who are mal-adaptive and sometimes mal-adaptive and intelligent. That's a different ball game indeed.

In human relations a kind of Kolmogorov complexity measure in which we communicate the most information in the least symbols or words --- well illustrated with your 'wanna get dinner' --- I think is adjacent to directness and openness. That is, why was it a guy can't spit it out? I like you and wanna get dinner with you? Fear, feeling, and self-esteem issues more likely. Now, it's probably not street smart to have that out with the potential invitee, however, being open about those feelings with a good friend in a hear-to-heart so that it enables one to move forward more directly to me seems like a win.

I am familiar with Blanton's Radical Honesty if that's your reference. What was your experience?

I think I ran across this at Bloomberg.com:

"Linguistic scholar George Lakoff was among the first to acknowledge the Sanders milestone, comparing it to a President Richard Nixon quip from 1973. Lakoff tweeted, 'When you negate the frame, you activate the frame. When Nixon said, ‘I’m not a crook,’ people saw a crook.' Lakoff didn’t go there, but President Bill Clinton likewise negated the frame to activate it in 1998 when he insisted that he had not had 'sexual relations with that woman.'

Context and contextualization is an important point to honest, open communication. What might appear as factual differences or a stubborn opponent might really be stepping into the conversation with intersection free frames. Sometimes we tend to frame things in such as way as to remove our agency, or posit the other guy as the jerk etc.. So knowing your frame, and knowing a frame often enters into it (ex. DBT deals with this) is an important element to honesty to self and honesty with your your audience.

Talking without a filter; that is without constantly editing oneself to make it PC or conform to the normative organizational human structure in the room is a kind of openness too. On the other hand merely free-form raw, honest feelings or bottom lining the situation to avoid social norms to let the "truth" out isn't per se really open.

To are caveats here: there are a range of defensive behaviors (see below on Human Element and Dr. Schutz) so that while one may come across as honest and authentic (ex. not PC, not catering, not-careful) are in fact non-self-aware behaviors one exhibits to avoid conflicts with self-esteem.

Consider a prototypical alpha-male: as long as I criticize and blame someone on their lack of competence and failure to succeed ... could seem like honest feedback. Or it's the fog I hide behind to avoid dealing with myself. As long as the other guy is on the hook, I don't have to look at myself. All the more so if this is my go-to in difficult situations. Other people don't do criticism. Their go-to is playing the victim, or playing it off (what problem? what are you so upset about?) etc ... these behaviors often arise in heated, hard to solve situations when one is unable to cope well.

Openness in the good way, and the ultimately the most beneficial way wherever pairs of people interact has a strong focus on self, feelings & fears about self, and is less outward looking that might otherwise be thought at first. And it's worth pointing then genuine openness needs safety. An office that's doesn't promote safety will just get a bunch of people who say what they have to or what they can get away without without losing their job or so pissing off someone that there's payback.

A really nice assessment and description. Periodically I fall into "give advice because you are deeply desperate for validation". I'd like build on your words and summarize what I learned from still another person Dr. William Schutz, and deal best I can on honest communication v. perception. It's an interesting dilemma to me.

First, assume that all I can do is observe behavior: what I see, hear, read. I cannot figure out why a person is exhibiting a behavior; guess sure. But know? No way. What's between the ears is between their ears and inaccessible to me.

Second, assume the PCA (principle component analysis) of behavior is control, inclusion, openness. Read "Human Element" or get an old copy of FIRO from him or his son Ethan Schutz --- excellent stuff and perfect for the office: it's like healthcare on the battle field: pointed, focused, can-do, common sense, but not so simplistic and removed for the bigger world of medicine that it's silly or merely palliative. With that setup in mind:

1) you cannot resolve significance issues through control. More generally you cannot fix a problem along PCA axis 1 by doing something along another orthogonal axis 2. Often makes it worse. Giving advice is control behavior, which the writer says, was really about significance. Yep, that's me sometimes. It's helpful to know when I misuse one skill to badly fix something else.

2) Behaviors are goal seeking and directly connect right into feelings which hits right into self-esteem. See the book or smarter people here. This is feature rich location of being human.

3) I've worked 30+ years and spent the last 14 years working for large companies. As posters here have said, behavior comes with a zillion motivations. But from time to time I have dealt with programmers, managers, young, and, old who strongly point out they should --- more: it'd be dumb not to try! --- to manage perception on the other side because perception is reality.

Now in some artificially distorted way, it does capture a truth but at the expense of omitting a lot of relevant context. But:

-- As Schutz says, we know we ought to be open but in the fact that's the last thing we'll ever do because it's not safe. Openness requires safety. If I start being open I might say something to get myself fired. If my boss talks openly I might get yelled at. That's anxiety making. If a co-worker talks openly about me I might get fired. Better to keep quiet about that co-worker so he'll be quiet about me. Fear is a lot of what prevents openness.

-- While words are pouring out one should not assume the speaker is open in two facets. First, the speaker may have low self awareness. If so, trying to make sense of that is doubly impossible. Two, the implied success of getting one over me by having the counterparty play to my perception requires low self-awareness my side. And among other things implies lack of choice/agency my side which is along the control axis to respond appropriately. So ... really where does the cause start and effect end. It's more nuanced.

-- The insistence on perception as reality is seated, I feel, either in trauma or in that shadow of maladaptive behavior some people come with. But it's the insistence that to me, indicates the perpetrator is the most insecure of all: they don't believe they have control, or are significant, or would want to be included ... and so in the absence of choice through control ... lie to themselves and the world to get by. They're fragile and they cast the world in a fragile light too.

https://thehumanelement.com/pages/firo-theory/ https://www.amazon.com/Human-Element-Productivity-Self-Estee...

OP has Solarflare NICs. So surely > 1MM pps is possible on that HW? But as you opened with 1 million per second on the Linux stack, I gather that kernel by-pass and such were by definition out of scope. The goal here was to always pass through the kernel. But if so, why use Solarflare? Why not see if one can do + 1MM pps on a nice, even beefy but not Solarflare/Mellonx NICs whose motivation includes kernel by-pass.

Don't get too impressed here by finance. Almost everything we're talking about here Linux Kernel Developments, SolarFlare (or Mellonx), core isolation (cpu set) was invented elsewhere. Finance merely buys it; it's a great client of all this tech. The only vaguely created-in-finance thing he/she references but then not even by name is https://martinfowler.com/articles/lmax.html which comes from ring buffers coming from CS EE networking itself.

The author specifically pointed out metric was packets per second not bytes per second because getting rather higher numbers with other units was easy.

There's a line from the BBC series 'Absolutely Fabulous' paraphrasing here: "You get your dry cleaning back and it's a revolution" ... the jab here was banal things have become blown way out of proportion ... which they later associate with 'New labour' whether (-) overstuff the action with empowerment overtones (-) business' attempts to conflate routine service to be on par with love, family, and a sort Grandma as a dry cleaner who was always there for you to give love, a smile, iron your clothes all these many years.

In fact both avenues are so overplayed it betrays and reveals for what it is: a desperate need to be seen and taken seriously, which is why we're blowing more time talking about it here. What's going over there such that this became a real conversation?

If you wanna blow off computers for a while, for God sakes just do it and stop soliciting attention. You want to go cold-turkey on drugs, alcohol, girl-friends, job, computer, ... join the club: it's going on all the time. A revolution? Try MLK for but one relevant example. When did routine become such a big ask?

The article is junk. Nebulous blather ... Something which software unlike math, physics, Chem, EE, Chem Eng I think tolerates too much.

We could restate title as: "I'm _x_ and won't teach my kids to _x_ and niether should you"

where x is anything more complicated that cleaning a room:

- gardening

- writing a paper

- interpersonal skills

- etc

I find these kinds of near-journal-article-for-self fairly useless. If you think our stuff is boring where'd you leave intel/amd etc doing statistical process control in the domain of mother nature that's got the standard model in her favor? More boring? Less? Or dumb question?

Abstraction is a sort of entropy / Shannon / Kormogorov issue. So let's discuss it there not semi-liberal-arts school fogginess.

Folks let's please keep science in science. One day if QC gets commercial all these flowery articles will disappear. QC is math based. We'll need to deal or get left behind, and by then all this handwaving won't matter in the least.

Now, the other bad of software dev is that today's work is generously semi-formal at best in commercial settings. Not because CS is art, but because requirements gathering, human factors, corporate culture are strongly reactive in the software realm, where mother nature is directly absent.

Here we could help each other to understand management and management us to move this whole ediface along. And here less technical articles ala HBR work well.

The following enters into the OP's link somewhat sideways, but in an important way I think.

There's an old 60's analogy attributed to Fritz Pearls: you can touch the menu; you can read the menu; you can lick the menu; you can eat the menu. But you didn't each the meal. That is, let's not confuse the model of experience with experience.

Extending that analogy I cannot argue that my life experience is similar, equivalent, or exchangeable with African Americans because I haven't lived their experience under, say, American police. Still I am concerned that if this analogy is taken too far, there will arise an insuperable gap that will work against binding each party into the whole we seek or ought to be seeking.

Our -- or THE - American Constitution sets forth equality among us all regardless of creed, color, sex, or religion, but when some of us go to the restaurant we aren't served or, worse, there's no food and no kitchen for us. America is not living up to the goal despite having fine goals. I recall Cornel West saying civil rights was due not because the Blacks wanted a piece of the pie -- a backhanded reference to government handouts for undeserving people -- but because preferential treatment based on color was never part of the deal. There's no white guilt at play here anymore than there's handouts going on.

So, let's be clear: violating civil rights is morally, ethically wrong. And all the more when it's perpetrated by sections of society that have greater power, money, and institutional agency. And all the more when cops are supposed to hold the line on justice. Justice is the good line: if you're on the wrong side, you should have to pay in the criminal or civil penalty. And if you're on the right side then all to the good. Either way, then, there's no room to take offense.

As I understand it the cop with the knee on the throat of a handcuffed black man was finally charged. Well, big deal: it took them long enough to get to the stunningly obvious. I am hoping the FED charges will follow. And then civil charges. There's also the issue of the other officers on the scene and whatever games were played by the DA and its affiliates.

Hackernews is primarily about technology, tech corporations, and business. However, let's over master the lesson so that we realize the ultimate money lesson with plenty of banked savings to boot: money is not the measurement of all things. We can and must insist there's equality under the law for each and everyone of us. Let's all work to make sure there's enforceable norms which is also, beyond income, an important piece of security for us and our families.

I have kids; I know why their skin color is like mine. They had no choice in the matter. And for those parents, sisters, or brothers of African Americans who fell into this society, we cannot be using and abusing and violating their rights. Standing by in a dismissive stance --- a Canadian guy who works as a FTE at my/our American company said we Americans need to get our ____ together like it wasn't his problem too --- is not help.

Maybe I cannot eat the menu. But I am not helpless, nor am I apart from this problem. I also have agency. Let's not lost in silos here.

All day long true - good point