XFS: Recent and Future Adventures in Filesystem Scalability - Dave Chinner
Linux.conf.au 2012 -- Ballarat, Australia2 HN recommenders · recommended in 2 months, 2012-2023
29K views · 14 years ago · talk · dated
Dave Chinner's linux.conf.au 2012 talk on XFS scalability, covering pain points with large numbers of files and complex metadata, and the work to fix XFS metadata performance.
HN recommends it as the definitive explanation of XFS metadata performance fixes and how XFS was developed and made robust on Linux.
46:00Scaling ZFS for NVMe - Allan Jude - EuroBSDcon 2022
EuroBSDCon
14K views • 4 years ago
15:39introducing copyparty, the FOSS file server
tripflag
613K views • 1 year ago
35:31June 2021 FreeBSD Developer Summit: Raid-Z Expansion
FreeBSD
4K views • 5 years ago
42:39Bloat: How and Why UNIX Grew Up (and Out) - Rusty Russell,Matt Evans
Linux.conf.au 2012 -- Ballarat, Australia
21K views • 14 years ago
35:16Filesystem in Rust - Kent Overstreet
The Linux Foundation
124K views • 2 years ago
1:25:25OpenZFS Office Hours with Matt Ahrens
OpenZFS
0 views • 13 years ago
45:35[Linux.conf.au 2013] - The real story behind Wayland and X
HackersOnBoard
35K views • 13 years ago
56:53A Brief History of the BSD Fast Filesystem by Marshall Kirk McKusick
EuroBSDCon
878 views • 6 years ago
53:11EFI and Linux: the future is here, and it's awful - Matthew Garrett
Linux.conf.au 2012 -- Ballarat, Australia
77K views • 14 years ago
52:54Rust at speed — building a fast concurrent database
Jon Gjengset
225K views • 7 years ago
45:35The real story behind Wayland and X
Linux.conf.au 2013 -- Canberra, Australia
46K views • 11 years ago
52:41Seattle Conference on Scalability: YouTube Scalability
Google TechTalks
30K views • 19 years ago
48:04"NTFS really isn't that bad" - Robert Collins (LCA 2020)
linux.conf.au
161K views • 6 years ago
49:43ZFS Native Encryption by Tom Caputi
OpenZFS
14K views • 10 years ago
1:11:44DebConf 14: QA with Linus Torvalds
Adnan Hodzic
737K views • 12 years ago
1:00:31BetrFS: A Right-Optimized Write-Optimized File System
Microsoft Research
3K views • 10 years ago
45:35The Real Story Behind Wayland and X - Daniel Stone (linux.conf.au 2013)
Mladen Mijatov
104K views • 13 years ago
56:55AWS re:Invent 2017: How Netflix Tunes Amazon EC2 Instances for Performance (CMP325)
Amazon Web Services
18K views • 8 years ago
48:13RIP Windows: Linux GPU Gaming Benchmarks on Bazzite
Gamers Nexus
1.1M views • 11 months ago
1:08:17How We've Scaled Dropbox
Stanford
372K views • 14 years ago
3 comments from Hacker News
> XFS is probably the best bet on Linux Yes, agree. However, I also lost files on it (had files overwritten with 0s, as other people already commented here). Also, it's your best bet of you don't need the extra features provided by ZFS. Thanks to its checksum validation, I detected bad SATA cables three times already (on different systems), instead of getting corrupted data. >it was beautifully designed and implemented by SGI back in the day. Hopefully the ChatGPT generation don't start modifying that code too much. Except it's not what happened. Please check this talk from Dave Chinner, where he explains how XFS was developed and ported to Linux and then made robust and stable by him and other contributors. The disk format has changed many times, now it's robust and resilient against metadata corruption. XFS Development talk by Dave Chinner ▶ this video History of Linux FS, also by Dave Chinner: link
I wonder if you know about Dave Chinner's talk, which addresses the metadata performance issue. (they fixed it) ▶ this video
> A while ago, I read somewhere that XFS is good for a small number of large files, whereas ReiserFS is good for a large number of small files. I don't know whether that's true anymore if it ever was It used to be true. XFS has for a long time been the very fastest real filesystem available when it comes to moving data, and one of the slowest ones in real-world use when it comes to changing metadata. Untarring a kernel tarball a second time (on top of the first) is pretty much the canonical benchmark for metadata operations, and the one where XFS used to be at it's absolute worst. XFS is in the news right now exactly because they have fixed that deficiency. It's still faster than ext*, zfs and btrfs in pretty much everything else, but now it's comparable to them when modifying metadata. So this is exactly the right benchmark to use, because it's the one where there has been recent change. Video of Dave Chinner presenting this at linux.conf.au: ▶ this video