I tested it yesterday on -13, haven't seen -14 on my mirror at that time. Anyway, the test confirmed that the problem still exists in -13.
This time I just did a simple read test of a 600 MB file. The difference between -7 and the newer ones is huge. $ uname -a Linux fafik 2.6.24-7-generic #1 SMP Thu Feb 7 01:29:58 UTC 2008 i686 GNU/Linux $ time dd if=rh73.vdi of=/dev/null 1177609+0 records in 1177609+0 records out 602935808 bytes (603 MB) copied, 14.8931 s, 40.5 MB/s real 0m14.913s user 0m0.632s sys 0m2.236s $ uname -a Linux fafik 2.6.24-11-generic #1 SMP Fri Feb 29 22:08:31 UTC 2008 i686 GNU/Linux $ time dd if=rh73.vdi of=/dev/null 1177609+0 records in 1177609+0 records out 602935808 bytes (603 MB) copied, 105.697 s, 5.7 MB/s real 1m45.703s user 0m3.556s sys 0m33.798s $ uname -a Linux fafik 2.6.24-12-generic #1 SMP Wed Mar 12 23:01:54 UTC 2008 i686 GNU/Linux $ time dd if=rh73.vdi of=/dev/null 1177609+0 records in 1177609+0 records out 602935808 bytes (603 MB) copied, 87.1279 s, 6.9 MB/s real 1m27.135s user 0m3.408s sys 0m32.462s $ uname -a Linux fafik 2.6.24-13-generic #1 SMP Sun Mar 30 23:30:06 UTC 2008 i686 GNU/Linux $ time dd if=rh73.vdi of=/dev/null 1177609+0 records in 1177609+0 records out 602935808 bytes (603 MB) copied, 86.3038 s, 7.0 MB/s real 1m26.323s user 0m2.548s sys 0m17.145s I'll try with -14, but I'm not holding my breath. About building my own kernel -- I think it's possible, though compiling on this laptop will probably take quite some time. Maybe I'll use another, faster machine, though it's running gutsy. Hope it's OK. Could you please also let me know if there is any place with the old binaries of versions -7 to -11? This could also let me narrow down the search. -- [hardy][regression] disk I/O makes the system very slow and unresponsive https://bugs.launchpad.net/bugs/210502 You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
