Top all-time · #14010
FractalBits
Company blog · fractalbits.com/blogsystemsdata
FractalBits is the company blog at fractalbits.com, writing about systems and data. Since 2025, 5 different Hacker News readers have linked it 16 times, most often “We built another object storage”. No feed was found, so read it on the site itself.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link FractalBits' post "Why We Built Another Object Storage" for its design choices, especially how it handles metadata, strong consistency and atomic rename, beyond raw IOPS benchmarks.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
High-Performance S3-Compatible Object Storage. Over 1.3 Million Object/s with P99 latency ~3ms.
Most-linked posts?
- We built another object storage2 people · 6 mentions · first linked 2025-12-05
- A new metadata engine for high performance Object Storage (not LSM, not B+ tree)2 people · 3 mentions · first linked 2026-05-09
What Hacker News says?
I'm more interested in the design philosophy behind these projects than which benchmarks top the charts... A lot of the high performance S3 alternatives trumpet crazy IOPS numbers, but the devil is in how they handle metadata and consistency. FractalBits says it offers strong consistency and atomic rename ([Why We Built Another Object Storage (And Why It's Different)]( https://fractalbits.com/blog/why-we-built-anoth…
Comment linking /blog/why-we-built-another-object-storage/
on “We built another object storage”Submitted We built another object storage as a story · 133 points
HN discussionWe wrote a blog explaining why we built another object storage and why it is different: https://fractalbits.com/blog/why-we-built-another-object-sto... . Welcome any useful feedback!
Comment linking /blog/why-we-built-another-object-storage/
on “Show HN: S3 compatible store with 1M IOPS(4K-R,p99~5ms), BYOC in 5min with rust”Submitted A new metadata engine for high performance Object Storage (not LSM, not B+ tree) as a story · 6 points
HN discussionThanks for the analysis. Interestingly when we first released our low latency s3-compatible storage (1M IOPS, p99 ~5ms)[1], a lot of people asking the same questions why we tried to bring file system semantics (atomic object/folder rename) to s3. We also got some feedback from people who really need FS sematics, and added POSIX FS support then. aws S3FS is using normal FUSE interface, which would be super heavy due…
Comment linking /blog/why-we-built-another-object-storage/
on “S3 Files and the changing face of S3”Submitted Removing fsync from our local storage engine as a story · 6 points
HN discussionThanks for the feedback, since I have relied in other thread related to O_DSYNC which a lot of folks have already suggested, and I will not repeat it here. For the benchmark results, and they were mainly due to metadata management. We have implemented our own KV store, see internal here [1], which is more efficient than ext4 namespace management, even after doing very aggressive fs tuning for that [2] (plus 65536 sh…
Comment linking /blog/metadata-engine-for-our-object-storage-from-lsm-tree-to-fractal-art/
on “Removing fsync from our local storage engine”Submitted Bootstrapping a Storage Cluster with S3 Based Workflow and Barriers as a story · 5 points
HN discussionThanks for the encouragement! Another author here. Yes, if you are interested you can check our another blog [1] for the internal storage engine. Yes, we are limiting the delimeter to "/", to better support posix FS semantics. I have just finished the fs feature branch which has passed all posix fstests [2]. [1] https://fractalbits.com/blog/metadata-engine-for-our-object-... [2] https://github.com/pjd/pjdfstest
Comment linking /blog/metadata-engine-for-our-object-storage-from-lsm-tree-to-fractal-art/
on “Removing fsync from our local storage engine”Submitted We Moved Object Storage Metadata Off LSM Trees as a story · 5 points
HN discussionCongrats to the TigerBeetle team's new feature! and it looks like TB has already moved from shared nothing to partially shared disk (object storage) architecture. We are always a big fan of the tigerbeetle engineering and is actually using TB's excellent io_uring runtime [1] to build a new object storage, and this connection feels amazing to me. [1] https://codeberg.org/thomas-fractalbits/iofthetiger [2] https://fra…
Comment linking /blog/why-we-built-another-object-storage/
on “TigerBeetle: A Trillion Transactions [video]”Submitted We Built Another Object Storage (and Why It's Different) as a story · 4 points
HN discussionA lot of good insights here. I am also wandering if they can just simply put different jobs (unclaimed, in-progress, deleted/done) into different directory/prefix, and rely on atomic object rename primitive [1][2][3] to solve the problem more gracefully (group commit can still be used if needed). [1] https://docs.cloud.google.com/storage/docs/samples/storage-m... [2] https://docs.aws.amazon.com/AmazonS3/latest/API/A…
Comment linking /blog/why-we-built-another-object-storage/
on “A distributed queue in a single JSON file on object storage”Submitted Benchmark object storage in objects/s, not GB/s as a story · 3 points
HN discussionSubmitted We Moved Object Storage Metadata Off LSM Trees as a story · 3 points
HN discussionSubmitted To fsync or not, that is a question as a story · 1 points
HN discussion