LWN.net Logo

No-I/O dirty throttling

No-I/O dirty throttling

Posted Sep 7, 2011 10:01 UTC (Wed) by zmi (guest, #4829)
In reply to: No-I/O dirty throttling by DiegoCG
Parent article: No-I/O dirty throttling

That patch sounds nice, but has to be tested a lot to confirm it does what it should in every situation. It especially needs testing on lots of different systems with different storages, from USB sticks to big irons. I like the description of how everything is calculated, seems like the Right Approach.


(Log in to post comments)

No-I/O dirty throttling

Posted Sep 18, 2011 10:17 UTC (Sun) by oak (subscriber, #2786) [Link]

Compressed RAM swap could also be an interesting test-case.

The differences to normal swap devices are:
- swapping causes CPU load, not IO load
- smaller than the amount of RAM instead of larger

Copyright © 2013, Eklektix, Inc.
Comments and public postings are copyrighted by their creators.
Linux is a registered trademark of Linus Torvalds