Building Blobd: Single-Machine Object Store with Sub-Ms Reads and 15 Gb/s Upload
Postedabout 2 months agoActiveabout 2 months ago
blog.wilsonl.inTechstory
calmmixed
Debate
60/100
Object StoragePerformance OptimizationCloud Storage
Key topics
Object Storage
Performance Optimization
Cloud Storage
The post discusses building 'blobd', a single-machine object store with high performance, and the comments debate its design choices and trade-offs compared to existing solutions like S3 and file systems.
Snapshot generated from the HN discussion
Discussion Activity
Light discussionFirst comment
16h
Peak period
5
24-26h
Avg / period
1.9
Comment distribution15 data points
Loading chart...
Based on 15 loaded comments
Key moments
- 01Story posted
Nov 4, 2025 at 6:09 AM EST
about 2 months ago
Step 01 - 02First comment
Nov 4, 2025 at 9:42 PM EST
16h after posting
Step 02 - 03Peak activity
5 comments in 24-26h
Hottest window of the conversation
Step 03 - 04Latest activity
Nov 5, 2025 at 1:22 PM EST
about 2 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 45809644Type: storyLast synced: 11/20/2025, 12:29:33 PM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
Also for the descried issue of small images for a frontend, nobody would serve directly from S3 without a caching layer on top.
It's a interesting read for fun, but I am not sure what it solves in the end.
Not true, you still need fsync in direct I/O to ensure durability in power loss situations. Some drives have write caches that means acknowledged writes live in non-volatile memory. So maybe the perf is wildly better because you’re sacrificing durability?
https://github.com/wilsonzlin/blobd/blob/master/libblobd-dir...
200ms seems fairly reasonable to me once we factor in all of the other aspects of S3. A lot of machines would have to die at Amazon for your data to become at risk.