San Francisco, CA
Joined July 2010
- Tweets11.8K
- Following161
- Followers56.4K
- Likes35.8K
Cindy Sridharan retweeted
Resharing this and urging everyone to read it for several reasons.
1. Everything Cindy writes is fantastic and serious engineering discourse
2. The examples here are concrete and clear and most importantly production services with real world consequences
Cindy Sridharan retweeted
New blog post!
"Lorenz and Little: How Much Does Your Tail Cost?" takes a look at how much tail latency contributes to the concurrency in a system, and how much that contributes to cost.
brooker.co.za/blog/2026/07/2…
Cindy Sridharan retweeted
New blog post, about a great little way to add fairness to distributed systems.
Combining stochastic fairness queuing, best-of-two, and shuffle sharding.
Cindy Sridharan retweeted
Performance Hints
Over the years, my colleague Sanjay Ghemawat and I have done a fair bit of diving into performance tuning of various pieces of code. We wrote an internal Performance Hints document a couple of years ago as a way of identifying some general principles and we've recently published a version of it externally.
We'd love any feedback you might have!
Read the full doc at: abseil.io/fast/hints.html
Cindy Sridharan retweeted
"Mount Mayhem at Netflix: Scaling Containers on Modern CPUs".
Ultimately, the best solution combined hardware awareness with software improvements.
by @NetflixEng
netflixtechblog.medium.com/m…
Cindy Sridharan retweeted
I spoke with @clattner_llvm about AI and software craftsmanship.
"The question is, when things settle out, where do you as a programmer stand? Have you lost years of your own development because you’ve been spending it the wrong way?”
A must read:
fast.ai/posts/2025-10-30-bui…
Cindy Sridharan retweeted
The #1 rule of scalable systems is to avoid congestion collapse.
This is when a system slows down, starts timing out, then gets hammered by retries that also time out, in an infinite loop.
I’ve accidentally broken Dropbox and Convex this way. Here's 7 tips how not to:
Cindy Sridharan retweeted
Recently, I've been discussing throttling with one of our teams. It's a super deep topic, probably deeper than it gets credit in modern systems, so I decided to write some thoughts on the matter: blog.joemag.dev/2025/06/the-…
Cindy Sridharan retweeted
New blog post, about some of my favorite papers from this year's HotOS program. Love Little's law? Hate fork? Think static analysis of shell programs sounds fun? Had enough of the f threshold model? Check it out for some papers to read: brooker.co.za/blog/2025/06/0…
Cindy Sridharan retweeted
I have a brief story I want to tell about the Tech Right, the Trump administration, and immigration.
In June 2024, Trump went on the All In podcast and said we should make it easier for international students who graduate from top US colleges to become citizens.
"It's so sad when we lose people from Harvard" after they graduate, he said. "I think you should get automatically, as part of your diploma, a green card to be able to stay in this country. That is going to end on day one."
This was huge. Day one! Wow. The All In guys ate it up. Chamath goes: "That's fantastic." David Sacks: "That's great." Tech folks proclaimed Trump to be fully high-skill-immigration-pilled.
Well, he's president now. And stapling green cards to diplomas isn't happening.
What's happening instead?
1. Today, the Trump administration announced that it's illegal for Harvard to enroll foreign students and existing students have to transfer or face deportation.
2. The nominee for U.S. Citizenship and Immigration Services director said he wants to end the US's single largest high-skill recruitment program, OPT, which is critical for helping foreign-born students stay in the country.
3. NIH funding YTD is down more than 50%, and more AI scientists are leaving the country than coming in.
Cindy Sridharan retweeted
During the power outage in Spain and Portugal, the local AWS datacentres kept humming thanks to careful planning and preparation. Remember: Everything fails, all the time, so plan for failure and nothing fails.
linkedin.com/posts/kevinmill…
Cindy Sridharan retweeted
The richest and most successful people in tech plotting to coopt Trump thinking they could create massive economic growth but instead becoming responsible for the most smooth brained recession in history would be a really funny plot point if it wasn’t for the suffering.
Here's what this was about: semafor.com/article/04/27/20…
Cindy Sridharan retweeted
It's widely known that sharing a queue across multiple servers, rather than queue-per-server, often helps reduce latency and improve utilization. But when is one queue better? In my new blog post, I look one case where one queue is better than two: different classes of work.
Cindy Sridharan retweeted
New Amazon Builders' Library article: Resilience lessons from the lunch rush. Fantastic overview of techniques to prevent overload in distributed systems, and highly entertaining real-world stories that draw parallels. aws.amazon.com/builders-libr…
Cindy Sridharan retweeted
New post from me: a deep dive on the bitdrift backend - the systems that drive real-time observability at scale. Check it out and enjoy!
blog.bitdrift.io/post/dont-b…
Cindy Sridharan retweeted
I gave a day 1 closing keynote at DistrictCon yesterday. Surprisingly, it was a security talk about memory safety.
Slides are here:
docs.google.com/presentation…
Cindy Sridharan retweeted
Introducing Willow, our new state-of-the-art quantum computing chip with a breakthrough that can reduce errors exponentially as we scale up using more qubits, cracking a 30-year challenge in the field. In benchmark tests, Willow solved a standard computation in <5 mins that would take a leading supercomputer over 10^25 years, far beyond the age of the universe(!).
Cindy Sridharan retweeted
I disagreed with voting for Trump in 16 and 20. But, voting for Trump in 24, after Jan 6, just boggles my mind.
Cindy Sridharan retweeted
New blog post, looking at the great new paper from the Amazon MemoryDB folks: brooker.co.za/blog/2024/04/2… Much of the discussion on distributed systems is about scalability, but this paper shows how availability, durability, cost, and performance are equally important.