Live data from Hacker News

The impact of Prince’s death on Wikipedia

blog.wikimedia.org

81–90 of 112 posts

Re: The impact of Prince’s death on Wikipedia

#81
post #39
post #30

Earlier quoted context omitted.

2m refers to concurrent connections, not rate.

Ah, that makes sense. Still, is 2m rps within the realm of possibility for BEAM with a high-end server grade processor and heavy use of actors/concurrency?

The Phoenix framework tests in October got up to 2m concurrent active (well, mostly just awake) connections, without timeouts.

http://www.phoenixframework.org/blog/the-road-to-2-million-w...

Re: The impact of Prince’s death on Wikipedia

#82

Earlier quoted context omitted.

https://grafana.wikimedia.org/dashboard/db/varnish-http-erro... (and grafana.wikimedia.org in general) have more stats. It stated '13.38 Million req/min), which I think is ~230,000 req/s

Ah. So my hunch was that the published number was what is making it through cache, and that's where my estimate comes from too. That sounds about what I'd expect for the cached side. Nice find!

The total number of requests that get through the cache to the application layer can be seen here

https://ganglia.wikimedia.org/latest/stacked.php?m=ap_rps&c=...

which you can see is not showing any substantial increase due to the passing of Prince. The big hole of two days that ends just before the news broke is due to wikimedia switching traffic to a second datacenter for two days, see http://blog.wikimedia.org/2016/04/18/wikimedia-server-switch...

Re: The impact of Prince’s death on Wikipedia

#83

Earlier quoted context omitted.

Well, I wasn't really responding to the Bill Gates part in particular. Gates was a bit of a megalomaniac with MS. But he's doing awesome stuff with the money now. As person I'm not aware of him ever being a jerk.

So if you gain lots of money via semi nefarious means what fraction do you have to dedicate to good works before the earlier wrong is cancelled? I know that he didn't gas 6 million people but letting people buy their way out of moral debt with a fraction of the money they gained still seems horribly repugnant.

Hey, Hitler might have been responsible for killing a lot of people, including ones of Jewish faith, but he also killed Hitler. I think that makes him strictly a better person than Bill Gates. How many of us can say that we ended a world war?

Re: The impact of Prince’s death on Wikipedia

#84
post #38

Earlier quoted context omitted.

Downvotes aren't punishment. Up/down votes indicate "this comment ought to be more/less prominent on the page". The sentence was somewhat ambiguous and your misunderstanding is understandable. But your comment is not useful to the discussion because most people understood and in any case it's tangential.

Okay honestly am I the only one who reads "in front of a hundred million people" and thinks it actually means he was in front of a hundred million people? I don't see it as an ambiguity, it's simply a wrong statement. I'm okay with people being uninterested in (and even downvoting) a correction, but I'm baffled that anyone could read the sentence as anything other than incorrect. I mean, they even describe the weathe…

I've reworded the sentence in the post—does it work better that way? Many thanks for the feedback, everyone. :-)

Re: The impact of Prince’s death on Wikipedia

#85
post #47

For others who were left scratching their heads at what exactly this pop-sci-explained PoolCounter mechanism actually is: https://wikitech.wikimedia.org/wiki/PoolCounter TL;DR: It's a limiter on how many workers start rendering the new page version when the old page version in cache has been invalidated.

Yeah, I am the engineer mentioned in the article, and I agree the explanation doesn't really work. The pieces of the explanation that ended up in the article itself don't add up to a coherent explanation. The fault for that is mostly mine. In hindsight, my original explanation was too long and too elaborate to be helpful. It's a good reminder that it is easy to go to far with an analogy and end up complicating the th…

There is a stochastic approach that can be adapted to address this problem, I think I first saw it at IMVU in 2009 but conveniently Wikipedia has a good reference now: https://en.wikipedia.org/wiki/Cache_stampede#Probabilistic_e...

The advantage is less coordination is necessary and you should be able to get down to a single concurrent rerender per page.

Re: The impact of Prince’s death on Wikipedia

#86
post #50
post #47

Earlier quoted context omitted.

Yeah, I am the engineer mentioned in the article, and I agree the explanation doesn't really work. The pieces of the explanation that ended up in the article itself don't add up to a coherent explanation. The fault for that is mostly mine. In hindsight, my original explanation was too long and too elaborate to be helpful. It's a good reminder that it is easy to go to far with an analogy and end up complicating the th…

Basically a page view checks the cache and rebuilds if necessary. Thousands of page hits in the same second before the build is over starts thousands of parallel rebuilds.

Why isn't it a possibility to rebuild and invalidate the cache only when the rebuild is finished?

Re: The impact of Prince’s death on Wikipedia

#87
How are Wikipedia articles kept consistent with each other? Say someone like Prince dies. His page will instantly change, seemingly while his portrait is still in the sky and the cannon fires.

But with certain people there's a variety of connected items that need referential integrity. For instance, I can imagine Prince being on one of those lists (eg highest grossing) that has bold text for still living artist. For office holders, they need to be moved from "incumbent" to a box with dates and the new incumbent needs to be updated. And then there's text snippets that are in present tense ("Prince and David Bowie are among the greatest living artists").

And then there's the corresponding pages in other languages.

How's it done?

Re: The impact of Prince’s death on Wikipedia

#88
post #29

For others who were left scratching their heads at what exactly this pop-sci-explained PoolCounter mechanism actually is: https://wikitech.wikimedia.org/wiki/PoolCounter TL;DR: It's a limiter on how many workers start rendering the new page version when the old page version in cache has been invalidated.

+1 for whoever named it the "Michael Jackson problem". I'm going to start using that if I ever encounter the same issue myself.

American Idol caused widespread rearchitecting of SMSGW/SMSC. Fun times; voting was a very distributed DoS.

Re: The impact of Prince’s death on Wikipedia

#89

How are Wikipedia articles kept consistent with each other? Say someone like Prince dies. His page will instantly change, seemingly while his portrait is still in the sky and the cannon fires. But with certain people there's a variety of connected items that need referential integrity. For instance, I can imagine Prince being on one of those lists (eg highest grossing) that has bold text for still living artist. For…

Some material like that is generated by templates, so updating the templates updates it in many places.

A lot, however, is just done manually by the armies of volunteers that contribute to the site. More than a few people specialize in updating bits of minutia like that.

Re: The impact of Prince’s death on Wikipedia

#90
post #47

Earlier quoted context omitted.

Yeah, I am the engineer mentioned in the article, and I agree the explanation doesn't really work. The pieces of the explanation that ended up in the article itself don't add up to a coherent explanation. The fault for that is mostly mine. In hindsight, my original explanation was too long and too elaborate to be helpful. It's a good reminder that it is easy to go to far with an analogy and end up complicating the th…

There is a stochastic approach that can be adapted to address this problem, I think I first saw it at IMVU in 2009 but conveniently Wikipedia has a good reference now: https://en.wikipedia.org/wiki/Cache_stampede#Probabilistic_e... The advantage is less coordination is necessary and you should be able to get down to a single concurrent rerender per page.

Wow, fascinating -- thank you for the pointer!
Post reply on HN