Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

7 Years Of YouTube Scalability Lessons In 30 Minutes

highscalability.com

Post reply on HN
Print view View original

41–50 of 77 posts

Re: 7 Years Of YouTube Scalability Lessons In 30 Minutes

#41

Post by colmmacc »

ajross wrote: post #20

Most of this is relatively straightforward and unsurprising. But the one part that grabbed me is about "jittering". They insert random delays into timed events (the example given is cache expiration) to prevent a thundering herd problem when all the parts of the distributed system see the event at the same time (and for popular content, presumably repopulate the cache from the backend simulteously). This is simple en…

A related technique is to use distinct prime numbers for periodicities in the first place:

http://www.stdlib.net/~colmmacc/2009/11/26/period-pain-3/

(http://www.stdlib.net/~colmmacc/2009/09/27/period-pain-part-... http://www.stdlib.net/~colmmacc/2009/09/14/period-pain/ for the background material).

The reasons primes are optimal should be obvious :)

Re: 7 Years Of YouTube Scalability Lessons In 30 Minutes

#42

Post by makmanalp »

ajross wrote: post #20

Most of this is relatively straightforward and unsurprising. But the one part that grabbed me is about "jittering". They insert random delays into timed events (the example given is cache expiration) to prevent a thundering herd problem when all the parts of the distributed system see the event at the same time (and for popular content, presumably repopulate the cache from the backend simulteously). This is simple en…

Same in multicast DNS which is used in zeroconf:

http://files.multicastdns.org/draft-cheshire-dnsext-multicas...

Search for "random". Cool spec written by Stuart Cheshire of Apple.

Re: 7 Years Of YouTube Scalability Lessons In 30 Minutes

#43

Post by joering2 »

orlandu63 wrote: post #7
blhack wrote: post #3

What's this? Python? Apache? MySQL? But I thought you had to be running beta-release key value stores, esoteric web servers, and experimental programming languages if you wanted to scale! /s

Nope, you just need lots of cash.

speaking of - are they profitable yet?

Re: 7 Years Of YouTube Scalability Lessons In 30 Minutes

#45

Post by toddh »

ajross wrote: post #20

Most of this is relatively straightforward and unsurprising. But the one part that grabbed me is about "jittering". They insert random delays into timed events (the example given is cache expiration) to prevent a thundering herd problem when all the parts of the distributed system see the event at the same time (and for popular content, presumably repopulate the cache from the backend simulteously). This is simple en…

As an interesting counter point, Jeff Dean at Google says they prefer to have a known hit every once in a while, so they will have all the cron jobs go off at the same time versus introducing jitter. It perhaps has to do with their emphasis on reducing variability to control the size of the long tail distribution.

Re: 7 Years Of YouTube Scalability Lessons In 30 Minutes

#49

Post by cpeterso »

ajross wrote: post #20

Most of this is relatively straightforward and unsurprising. But the one part that grabbed me is about "jittering". They insert random delays into timed events (the example given is cache expiration) to prevent a thundering herd problem when all the parts of the distributed system see the event at the same time (and for popular content, presumably repopulate the cache from the backend simulteously). This is simple en…

The Adblock Plus blog details the thundering herd problems they faced. Their ad blocking lists checked for updates every 5 days. Eventually, many users' update schedules would converge on Mondays because office computers did not run over the weekend. Updates that had been scheduled for Saturday or Sunday would spill over to Monday.

https://adblockplus.org/blog/downloading-a-file-regularly-ho...

Re: 7 Years Of YouTube Scalability Lessons In 30 Minutes

#50

Post by leeskye »

cwbrandsma wrote: post #2

I love the part on faking data. I take the viewpoint that only software testers care that the comment count is exactly correct in the majority of system. Users don't care.

The publisher who uploaded the video might care. Especially so, if they are selling to advertisers. Comments, ratings, and favorites are three variables we calculate to reflect how engaging a video is.
Post reply on HN