View Single Post
Posts: 3,328 | Thanked: 4,476 times | Joined on May 2011 @ Poland
#16
Originally Posted by Estel View Post
Then user is wasting space for 2nd swap, without any additional (real) benefits. Additionally, said user doubles loss, due to getting rid of ability to have one physical storage device *without* swap writes to it



Performance of whole device (as usual, with higher CPU speed) - but, it's purely theoretical gain, as you're hardly doing other things while recording. That said, I always use 500-900 limits, so I may be missing some "lagging fun" at lower frequencies.



Yes, but it is related to either slowdowns of writing to storage medium, or what FMG said - in either case, it's not about CPU speed (which, even at 500 mhz, is able to generate writes for much higher speeds, than our flash storage media will ever allow).
---

Theoretically, one could gain better speeds of writing by using real "spinning disks" HDD connected via USB mass storage mode. Hoever, hostmode seems to have max ~4 MB/s write speed (due to some imperfections in hostmode implementation), which makes WiFi our fastest connection with the world (if we skip N900 as USB client + USB networking scenario, which is even faster).

/Estel
1. Is there any way to say swapset to use internal swap for defrag only?
2. So you overclock 250-600 recording seemed to stutter more than 250-805 or 250-900
3. So why does copying 900 MB take so long on N900 and much quicker on desktop Linux? RAM thing?
__________________
If you want to support my work, you can donate by PayPal or Flattr

Projects no longer actively developed: here
 

The Following User Says Thank You to marmistrz For This Useful Post: