Hi, I`m not reporting a bug, just an experience.
My server UPS died today and I can`t get a replacement because the highway is closed because of heavy heavy snowfall. :-) Of cause, a power failure is preprogrammed under this conditions. So in my paranoia, I disabled write caching for my harddrives (cheap sata ones) with hdparm. The host took it fine, write performance dropped but it was still in the >10MB/s area (raid1), so not really a problem for a few ???days??? BUT the guests dropped their write performance to somewhere around 200kB/s of raw throughput (journalling inclusive) and this was bad. A simple apt-get update took ages. My uml guests mount LVM2 volumes as ubdas and ext3 with data=journal and noatime. Turning the write cache back on brought all to normal. I still do not understand, why the guests became that much slow. Could somebody explain me why? cheers, juraj ------------------------------------------------------- This SF.net email is sponsored by: Splunk Inc. Do you grep through log files for problems? Stop! Download the new AJAX search engine that makes searching your log files as easy as surfing the web. DOWNLOAD SPLUNK! http://ads.osdn.com/?ad_id=7637&alloc_id=16865&op=click _______________________________________________ User-mode-linux-user mailing list User-mode-linux-user@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/user-mode-linux-user
