On 28/04/14 09:31, sf...@users.sourceforge.net wrote: > Hello Justin, > > "Justin (jlec)": >> I also can reproduce the +4k problem with the procedure described here >> http://serverfault.com/q/445445/145512 and linux-3.13.3 + current aufs >> development HEAD. >> >> So, what is the problem now? Is this by design or is this still a bug? > > The answer from me is essentially unchanged. > *Currently* I don't think it a bug nor by design. > You should try these steps. > - check the size and the number of the consumed blocks of XINO files via > debugfs and make sure they are big pressure for tmpfs. > --> In other words, are you sure that XINO files eat up your tmpfs, > or is it a general problem that your filesystem is too small for > your files? > If the XINO trunation feature in aufs doesn't work expectedly, > then it must be a bug.
Hi, I checked debugfs and the number of blocks increases per file creation/deletion cycle by 8 and the free space on the tmpfs reduces by 4k. Space isn't a problem as there are multiple GB free. One interesting observation I made was that very rapid creation/deletion doesn't show this effect, but a repeat rate of 1/10sec or so, does. justin
signature.asc
Description: OpenPGP digital signature
------------------------------------------------------------------------------ "Accelerate Dev Cycles with Automated Cross-Browser Testing - For FREE Instantly run your Selenium tests across 300+ browser/OS combos. Get unparalleled scalability from the best Selenium testing platform available. Simple to use. Nothing to install. Get started now for free." http://p.sf.net/sfu/SauceLabs
