Lightnews — Scholar-powered news

Reposted by Alex P

Qian Li @qianli.dev · 22d

The South Bay Systems talk series is back on Oct 2nd.

@codedrift.social will talk about the history and novel use cases of WebAssembly. Perfect timing too: Wasm 3.0 just released, and it is turning 10 this year.

Huge thanks to @yugabytedb.bsky.social for hosting!

Register here: luma.com/p3mibf27

South Bay Systems: WebAssembly Is Cool! (finally!) · Luma

Welcome to another edition of South Bay Systems! This time we'll have Jakob Heuser delivering an expanded version of his QCon 2024 lightning talk "WebAssembly…

luma.com

6 9

Reposted by Alex P

Apache Cassandra® @cassandra.apache.org · 28d

Abe Ratnofsky presenting "What's New in CEP-45: Mutation Tracking and Reconciliation"

More info about this CEP here: cwiki.apache.org/confluence/d...

1 2 5

Reposted by Alex P

Apache Cassandra® @cassandra.apache.org · 27d

Ariel Weisberg presenting "Living with Accord"

1 1 1

Reposted by Alex P

Apache Cassandra® @cassandra.apache.org · 27d

@taco.cat presenting
"Witness Replicas: Reducing Storage Costs in Apache Cassandra"

Saving 1/3 on storage, cpu and IO, is some serious spare change.

1 2 1

Alex P @ifesdjeen.bsky.social · 25d

Heading back home from Community over Code. So much new stuff this year in Cassandra: Mutation Tracking, Witness Replicas, Auto Repair, a bunch of new Analytics related work, and, of course, Accord!

3 9

Alex P @ifesdjeen.bsky.social · Jul 20

All day, every day. That’s what making it fun!

3

Alex P @ifesdjeen.bsky.social · Jul 18

Cassandra Team at Apple is searching for a fresh grad / person early in their career to join our ranks in SF/Bay Area!

Come work on super interesting problems with world class team. Help us build better Cassandra!

Ping me if you’re interested!

jobs.apple.com/en-us/detail...

Software Engineer, ASE Cassandra Storage - Jobs - Careers at Apple

Apply for a Software Engineer, ASE Cassandra Storage job at Apple. Read about the role and find out if it’s right for you.

jobs.apple.com

10 15

Alex P @ifesdjeen.bsky.social · Apr 7

Systems empire growth!

2 1

Alex P @ifesdjeen.bsky.social · Apr 6

Reading Sunk Works after reading the Qualcomm Equation, and can’t help but wonder what happened to engineering. I can think of 2 companies in the entire industry (which will remain unnamed) that are delivering projects of immense complexity with tiny resources, while others are lost in processes.

3 13

Alex P @ifesdjeen.bsky.social · Jan 30

Folks on database internals discord are voting for the next book. It’s a perfect time to join. This will be the third book we will be reading together, after Transaction Processing, and DDIA. discord.gg/GmchY45BbS

1 12

Alex P @ifesdjeen.bsky.social · Dec 24

If you’re ever in the vicinity of Munich and are fancy for a hike, give me a holler, I can show you some of my favourites.

1 1

Alex P @ifesdjeen.bsky.social · Dec 24

Indeed

1 2

Alex P @ifesdjeen.bsky.social · Dec 24

Looks awesome! Is this from your thesis / publication? Any chance it is public?

Also, if you’re available after the holidays I may reach out after I’m done with the initial mapping of literature.

Thank you for help!

2 1

Alex P @ifesdjeen.bsky.social · Dec 24

Checked out a couple of top ones, looks like right up my lane. Thank you for the pointer!

1

Alex P @ifesdjeen.bsky.social · Dec 23

Also, I'm trying to solve multiple problems, such as noisy neighbour, read/write starvation, workload prioritization, etc. But mostly, I wanted to get a good overview: most ideas I had and seen so far were more or less obvious, so was searching for harder-to-reach fruit.

3 1

Alex P @ifesdjeen.bsky.social · Dec 23

Thank you for all the pointers! My current list of papers looks something like this (attached).

Among other things, I am trying to understand whether multiple queues, or a single queue with priorities can be a better approach (also, whether one is reducible to the other).

1 1

Alex P @ifesdjeen.bsky.social · Dec 23

Never too late to recommend a paper! Thank you)

Alex P @ifesdjeen.bsky.social · Dec 22

I haven’t but I will now; thank you!

1

Alex P @ifesdjeen.bsky.social · Dec 22

I’ll take anything. Databases or client/server applications can be an example. I believe learnings are highly transferable. If you can point me to _literature_ I’d be grateful. Papers/algorithms are also pretty useful.

1

Reposted by Alex P

taco.cat @taco.cat · Dec 17

This bears out in practice, yep.

But it may be more attributable to compaction strategies that limit the number of SSTables that may contain a key (e.g. leveled) and keeping up with compaction backlog.

Most Cassandra deployments using LCS and default blooms maintain an SSTable-per-read count of 1.

3 3

Reposted by Alex P

JauntyWunderKind @jauntywk.bsky.social · Dec 16

I don't know how they have come to be regarded but I remember Google's Maglev and Meta's Katran & I remember enjoying the papers surrounding them.
github.com/facebookincu...

GitHub - facebookincubator/katran: A high performance layer 4 load balancer

A high performance layer 4 load balancer. Contribute to facebookincubator/katran development by creating an account on GitHub.

github.com