nycerrrrrrrrrr

> Sure, more if I'm really into something

I think this is the point of the stimulants - they make you really into whatever you're currently doing.

Wondering how you determined the E2B sandbox is Firecracker and not some other micro VM?

Very cool! I have wanted to build exactly this. Have you thought about supporting scale-to-zero?

Depending on your hardware you may be able to do the CRC validation in the NIC. If you're using Intel you could use DSA also, but then you're still copying the data through DRAM.

Just throwing out some ideas, obviously the best solution is the one that you already have working :)

This might be orthogonal to the TLB miss overhead you found, but have you looked at using P2PDMA to transfer directly from the NVMe SSDs to the NIC? Not sure how the CRC calculation would play into that.

See also https://distro.ibiblio.org/baslinux/, http://www.tinycorelinux.net/

If it's compiled into the kernel it'll occupy memory regardless if it's being used. If it's built as a kernel module then it doesn't occupy memory until loaded.

This idea has been around for a long time. See https://www.usenix.org/conference/hotcloud17/program/present..., also https://www.sigops.org/s/conferences/sosp/2009/papers/anders...

Yes, but when you blue-pill the hypervisor it becomes an attack on VMs. Her demonstrating the blue pill attack on Xen was really the "oh crap, these aren't as safe as we thought" moment.

Since some people seem to not be familiar with Joanna, she is a massively influential security researcher. IMO most famous for her "Blue pill" attacks on Vista and Xen: https://blackhat.com/presentations/bh-usa-06/BH-US-06-Rutkow..., https://invisiblethingslab.com/resources/bh08/part3.pdf. Her work demonstrated that hardware virtualization is not in fact the security panacea we wish it was, but that it too is vulnerable to attack just like any other layer of the stack. This revelation resulted in significant changes in the security world.

She is also famous for the Qubes OS project and coining the term "evil maid attack".

Definitely don't know the system like some people do, but: 102 stations, 60.09 miles, 4:19, 4 boroughs, $3.00 fare: 6 > M > 7 > D > Q > S > C > A.

Fun game :)

Does anyone have recommendations for how to actually print a poster from images like these?

Conflicted. Obviously open access is great, but it's never been that difficult to find most papers either on arxiv or the author's website. And I despise the idea of paying to publish, especially since unlike other fields the "processing" required for CS papers is minimal (e.g., we handle our own formatting). FWIW, USENIX conference papers are both open access and free to publish.

My understanding is that this is at least to some degree in response to the surge of AI generated/assisted papers.

Not sure what city you're in, but this has not been my experience with several NYC libraries.

Also slightly ironic considering United has several planes that are themselves 30+ years old.

Curious why they're using NFSv3 instead of v4?

Not sure what you mean by "US people" - the PC is mostly (but definitely not 90%) US based, but that follows from systems research being largely US based (for now, at least).

Great article, I'll have to try it out next time I'm on the subway.

One correction though - there is no subway line that goes across the Queensboro.