TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

5M Bid request/s, 2ms max response time – The Road to Damascus

157 点作者 sanjayts将近 6 年前

10 条评论

mej10将近 6 年前
Interested to know what Rust was missing. I built an ad exchange last year and it has been great. I have been using nightly builds, mostly for access to async&#x2F;await, and it has been very fast and stable.<p>I have had to submit a few pull requests to various projects along the way, but didn&#x27;t find the ecosystem prohibitively lacking.
评论 #20007385 未加载
sebastienros将近 6 年前
TechEmpower&#x27;s Plaintext scenario is currently limited at 7M RPS due to network limits, though it uses a 10Gb NIC. Knowing that the Plaintext scenario is a very simple HTTP request (standard headers) that returns &quot;Hello World!&quot;, how close to network saturation are you with 5M in this case with only &quot;2 Gigabit Ethernet cards&quot;?
nullwasamistake将近 6 年前
Did you consider Vert.X? it&#x27;s built on Netty and has it&#x27;s own Linux epoll driver, async, and fiber support. It&#x27;s impossible to know if it would be faster, but likely comparable and way less work than rolling your own.<p>In techempower benchmarks it exceeds 2 million http requests&#x2F;second and it&#x27;s a full REST framework.<p>And if you use the fiber support through Quasar you can pretend most things are normal blocking code.<p>Have to tried it or is this a case of NIH?
reilly3000将近 6 年前
I spent a few cycles in media buying and later in sell-side ad tech. Please do say what you will about advertising and its effects on the web, but I will say this: it is a world of fascinating tech. As a buyer I experienced janky pacing all of the time across various platforms, because this is a HARD problem. We had to manually adjust campaigns on a daily basis to ensure pacing worked properly. It was common to stop a campaign and overspend by hundreds of dollars while all of the caching spun down.<p>I&#x27;m fascinated to see they are running that all on a single node. Its a massive amount of state aggregated from billions of events that needs to be served at extremely low latency, but couldn&#x27;t it be partitioned somehow??? Google Fi&#x2F;Spanner and BigTable have certainly been developed to support these issues. I&#x27;ve been trying to dig up what infrastructure powers Google AdX, but I haven&#x27;t found anything. AdWords seems to be tied to Spanner, but AdX is&#x2F;was an entirely different beast. In any case I&#x27;m quite certain that it isn&#x27;t running pacing on a single, gigantic node.
评论 #20007965 未加载
评论 #20009394 未加载
评论 #20007734 未加载
ggregoire将近 6 年前
Glad to see this kind of stuff written with a strongly typed language instead of Python.
评论 #20006839 未加载
w3clan将近 6 年前
Is this complete note? You didn&#x27;t mention what you end up using.<p>Is it golang or pony or F$? CoreFX mention in the end confused me more.
评论 #20004957 未加载
评论 #20004696 未加载
评论 #20007702 未加载
评论 #20006150 未加载
csdreamer7将近 6 年前
Curious if there are numbers for other languages in high performance applications.<p>I am learning Clojure so I would like to know if anyone knows of the highest performant applications written in it.
eliasson将近 6 年前
&gt; (scala? That&#x27;s another story for another day)<p>This makes me curious - was it the language or the runtime characteristics?
Nextgrid将近 6 年前
It’s kind of sad that all this engineering effort was spent to essentially make the internet a worse place for everyone and waste users’ time and attention.<p>Imagine if a crime syndicate would brag about their efforts to make their worldwide criminal activities more efficient.
评论 #20006341 未加载
评论 #20005417 未加载
评论 #20005401 未加载
评论 #20007301 未加载
评论 #20006091 未加载
llamataboot将近 6 年前
The Best Minds of My Generation Are Thinking About How To Make People Click Ads (or serve them efficently)
评论 #20005699 未加载
评论 #20006652 未加载