ZeroFS vs AWS Mountpoint-s3 Benchmarks

Performance comparison conducted on Azure D48lds v6 (48 vCPUs, 96 GiB RAM) with Cloudflare R2 backend.

Test Setup

• VM: Azure Standard D48lds v6, West Europe (Zone 1)
• Storage: Cloudflare R2 (S3-compatible)
• Benchmark suite: github.com/Barre/ZeroFS/bench
• Operations per test: 100 (reduced from 10,000 due to Mountpoint-s3's performance characteristics)

Architecture Differences

ZeroFS: Direct S3-only architecture with full POSIX semantics. No additional infrastructure required.

AWS Mountpoint-s3: Amazon's official S3 FUSE mount (github.com/awslabs/mountpoint-s3) designed to provide a 1:1 mapping between S3 objects and files/folders. This design philosophy prioritizes direct object mapping over performance and POSIX compliance, resulting in limited file system capabilities.

Benchmark Results

Synthetic Benchmarks

Test	ZeroFS	AWS Mountpoint-s3	Difference
Sequential Writes
Operations/sec	663.87	0.70	948x
Mean latency	1.42ms	1,435.81ms	1,011x
Success rate	100%	100%	-
Data Modifications
Operations/sec	695.53	N/A	-
Mean latency	1.30ms	N/A	-
Success rate	100%	0%	Not supported
Single File Append
Operations/sec	769.50	N/A	-
Mean latency	1.22ms	N/A	-
Success rate	100%	0%	Not supported
Empty Files
Operations/sec	888.66	0.09	9,874x
Mean latency	0.86ms	605.61ms	704x
Success rate	100%	2%	-
Empty Directories
Operations/sec	985.98	2.08	474x
Mean latency	0.98ms	479.80ms	490x
Success rate	100%	100%	-
Random Reads
Operations/sec	1,000.84	3.20	313x
Mean latency	0.90ms	312.13ms	347x
Success rate	100%	100%	-

Real-World Operations

Operation	ZeroFS	AWS Mountpoint-s3	Notes
Git clone	3.1s	Failed	Configuration file operations not supported
tar -xf (ZFS source)	13.5s	~2h (est.)	Extrapolated from 10% completion at 12m 27s

Key Observations

ZeroFS

• Consistent sub-millisecond latencies for file operations
• 100% success rate across all benchmarks
• Full POSIX compliance
• Completed all real-world tests

AWS Mountpoint-s3

• Designed for read-heavy workloads with direct S3 object mapping
• Does not support file modification or append operations by design
• Limited POSIX semantics (no utime, chmod, chown support)
• Performance optimized for different use cases than general file system operations

Technical Details

Sequential Writes

Creates files in sequence. Tests metadata performance and write throughput.

ZeroFS: 100 files in 150ms
Mountpoint-s3: 100 files in 143 seconds (948x slower)

Data Modifications

Random writes to existing files. Tests consistency and update capability.

ZeroFS: All operations succeeded
Mountpoint-s3: Not supported in current implementation

Single File Append

Appends to a single file. Tests sequential write patterns.

ZeroFS: All operations succeeded
Mountpoint-s3: Not supported in current implementation

Empty File Creation

Pure metadata operations without data writes.

ZeroFS: 100 files in 112ms
Mountpoint-s3: Only 2 out of 100 succeeded due to implementation constraints

Empty Directory Creation

Tests directory metadata operations.

ZeroFS: 100 directories in 101ms
Mountpoint-s3: 100 directories in 48 seconds (474x slower)

Random Reads

Tests read performance from various file positions.

ZeroFS: 1,000+ ops/sec
Mountpoint-s3: 3.2 ops/sec (313x slower)

Git Clone

Tests mixed read/write patterns with metadata operations.

ZeroFS: Completed in 3.1 seconds
Mountpoint-s3: Unable to complete due to lack of config file modification support

Archive Extraction

Extracting ZFS 2.3.3 source tarball. Tests file creation with permissions and timestamps.

ZeroFS: 13.5 seconds for complete extraction
Mountpoint-s3: 12 minutes 27 seconds for 10% (432 of 4,280 files)

• Extrapolated ~2 hours for complete extraction
• Permission operations not fully supported

Storage Efficiency

S3 Operations Comparison

Metric	ZeroFS	AWS Mountpoint-s3	Notes
Class A Operations	578	8,770	15.2x more
Class B Operations	61	5,870	96.2x more

Note: Mountpoint-s3 numbers exclude operations for the remaining 90% of tar extraction.

The higher API call count reflects Mountpoint-s3's design focus on maintaining direct S3 object correspondence rather than optimizing for operation efficiency.

Design Philosophy Differences

AWS Mountpoint-s3 prioritizes:

• Direct S3 object mapping - 1:1 correspondence between S3 objects and files
• Read-optimized access - Designed primarily for reading existing S3 data
• S3 consistency model - Maintains S3's eventual consistency semantics

ZeroFS prioritizes:

• Full POSIX compliance - Complete file system semantics
• Performance optimization - Sub-millisecond operations
• General-purpose usage - Suitable for development and production workloads

Summary

The benchmarks reveal fundamental architectural differences between ZeroFS and AWS Mountpoint-s3. While Mountpoint-s3's design prioritizes maintaining a direct mapping between S3 objects and the file system, this approach results in significant performance trade-offs and limited POSIX support.

ZeroFS demonstrates that it's possible to achieve both high performance (300-10,000x faster operations) and full POSIX compliance while using S3 as the sole storage backend. The choice between the two systems ultimately depends on whether your use case prioritizes direct S3 object mapping or requires a full-featured, high-performance file system.