is there any aggregator for official docs such as this for db/systems/distributed arch at scale?
Asynchronous I/O in DuckDB: Work, Thread, Work
11–20 of 36 posts
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#12Using 512gb of ram for a 22gb remote file does feel a bit weird for a benchmark but maybe they couldn’t get a large number of cores without lots of memory?
Even so you could use cgroups to cap the memory for the process (including its caches).
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#13Does having the worker pool hold as many threads as cores work well alongside the async pool? It is basically oversubscribed by design. I built a system once which had (this is Rust) a Rayon worker thread pool of 4 threads and a Tokio async pool of 2 (multithreaded runtime). On a system of 6 vCPU. This ended up working fine. Tokio was not starved so handled network requests at low latency. One difference is DuckDB is…
As long as you're scheduled by the kernel and not something like Kubernetes with a CPU limit, you can generally oversubscribe I/O threads without much of a problem. They're mostly parked waiting for syscalls anyway. Heck, even if they're mostly doing CPU work, the scheduler generally deals with it pretty gracefully.
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#14Using 512gb of ram for a 22gb remote file does feel a bit weird for a benchmark but maybe they couldn’t get a large number of cores without lots of memory?
The main reason I decided to use a beefier machine is that it gives me flexibility when benchmarking, without the need to set up different environments. The CSV data, for example, is >80 GB. We can also “scale down the machine” for experiments where we want to stress-test lower-memory scenarios or use fewer threads by configuring DuckDB’s settings (e.g., SET memory_limit = '10GB'; or SET threads TO 1;).
(Disclaimer: I’m the author of the blog post.)
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#15Does having the worker pool hold as many threads as cores work well alongside the async pool? It is basically oversubscribed by design. I built a system once which had (this is Rust) a Rayon worker thread pool of 4 threads and a Tokio async pool of 2 (multithreaded runtime). On a system of 6 vCPU. This ended up working fine. Tokio was not starved so handled network requests at low latency. One difference is DuckDB is…
I've run quite a few benchmarks on that as well, on a few different machines, and oversubscribing ASYNC threads demonstrated very little performance downside. In the end, the memory governor also keeps these threads "in check" while still allowing full utilization when possible.
There is still something to gain from tuning it further (as you can see in the async I/O tuned benchmark), but having that network saturation by default is still a work in progress.
(Disclaimer: I'm the author of the blogpost)
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#16Do the CSV files allow quoted newlines? If yes, what's the trick to avoid checking the whole file too find out whether a newline is quoted or a record separator when reading it from the middle in an async thread?
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#17[flagged]
I can't say it's 'deep' in any way, e.g. what type of queue is that? Another part - utmost importance to keep async threads fully busy - that doesn't address what kind of disk subsystem is and how it deals with random reads.
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#18Do the CSV files allow quoted newlines? If yes, what's the trick to avoid checking the whole file too find out whether a newline is quoted or a record separator when reading it from the middle in an async thread?
most likely - they read large chunks and decode them
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#19Do the CSV files allow quoted newlines? If yes, what's the trick to avoid checking the whole file too find out whether a newline is quoted or a record separator when reading it from the middle in an async thread?
DuckDB uses a speculative parallel CSV parsing technique. The basic idea is that the parser speculates about the state the CSV parser is in at a random byte (e.g., whether it is inside a quoted field) and tries to figure out where the next row starts based on that.There are validation steps during finalization as well, to ensure the parser did not got anything wrong in its speculation.
I've never gotten around to writing a blog post about it, but I go quite in-depth on the technique in this presentation: https://www.youtube.com/watch?v=YrqSp8m7fmk
(Disclaimer: I'm the author of the blog post and also the developer who implemented the entire CSV parser in DuckDB.)
Re: Asynchronous I/O in DuckDB: Work, Thread, Work
#20Do the CSV files allow quoted newlines? If yes, what's the trick to avoid checking the whole file too find out whether a newline is quoted or a record separator when reading it from the middle in an async thread?
DuckDB uses a speculative parallel CSV parsing technique. The basic idea is that the parser speculates about the state the CSV parser is in at a random byte (e.g., whether it is inside a quoted field) and tries to figure out where the next row starts based on that.There are validation steps during finalization as well, to ensure the parser did not got anything wrong in its speculation. I've never gotten around to wri…
Thank you so much. I love DuckDB!