After I access some really (hundreds of MB) large files in UML, my UML system and even the applications on the host get slower and slower.
I think this comes from the so-called Linux buffer cache. Linux seems to use all free memory pages for buffering disk pages. This is a good idea in a normal Linux system, because if a process requests a lot of memory, the former buffer cache are available for that process immediateley. However, when UML caches disk pages, the memory used for that purpose are allocated to the memory of the UML kernel process from the host's point of view and so they are no longer available on the host and can not be used for other processes on the host. What's the best solution for that problem? -- Manfred Härtel, DB3HM mailto:manfred.haer...@rz-online.de http://rz-home.de/mhaertel ------------------------------------------------------------------------------ Special Offer -- Download ArcSight Logger for FREE! Finally, a world-class log management solution at an even better price-free! And you'll get a free "Love Thy Logs" t-shirt when you download Logger. Secure your free ArcSight Logger TODAY! http://p.sf.net/sfu/arcsisghtdev2dev _______________________________________________ User-mode-linux-user mailing list User-mode-linux-user@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/user-mode-linux-user
