ObjectiveFS

Performance Optimization Guide

For best performance, we recommend running on ObjectiveFS on servers with at least 2GB of RAM and 2 cpus.

Performance Recommendations

1. Use a larger memory cache

Use >500MB memory cache for best performance when using hpc mode. Larger memory cache gives better performance.
Memory cache can be adjusted using the CACHESIZEenvironment variable.
Reference: Memory Cache User Guide

2. Enable disk cache

Use the local instance store SSD as disk cache.
The disk cache maintains good performance even with a smaller memory cache and reduces the number of S3 operations.
Reference: Disk Cache User Guide, Instance Store Disk Cache Setup Guide

3. Run your servers in the same region as your object store

Running your servers in the same region as your object store (e.g. S3 bucket) gives you lower latency and higher bandwidth.

4. Enable hpc mode

The high performance computing (hpc) mode is a mount option that can be enabled with
-o hpc.
Enabling hpc assumes the server is running in the same region as the object store.
For large sequential reads/writes, we typically see 100+MB/s per mount for larger instance type. If you see less than 100+MB/s, please let us know and we can work with you.
```
$ mount.objectivefs -o hpc <filesystem> <directory> 
```

5. Enable multithreading

Multithreading can lower latency and improve throughput for your workload.
Multithreading is a mount option and can be enabled with -o mt.
```
$ mount.objectivefs -o mt <filesystem> <directory> 
```
You can also configure the number of CPU and IO threads explicitly by using the cputhreadsand iothreadsoptions (see user guide).
Reference: Multithreading User Guide, Mount options

6. Exclude your filesystem from programs that regularly scan directories

If your server runs programs that scan the filesystem, such as mlocate, we recommend excluding your ObjectiveFS directories from the scan for best performance.
Reference: How to exclude your filesystem from mlocate scanning

7. Performance testing considerations

/dev/randomor /dev/urandomcan sometimes become the bottleneck during the filesystem performance testing. We recommend pre-generating the random data in /tmpand copy them to your filesystem for an accurate measurement.
/dev/zerowill be compressed.

Reference

Last updated by ObjectiveFS staff, April 25, 2016
ObjectiveFS is a shared file system for OS X and Linux that automatically scales and gives you scalable cloud storage. If you have questions or article idea suggestions, please email us at お問い合わせはこちら