Hi,
I tested the lowlatency-2.2.14-B1 patch,
but unfortunately it crashes on both of my testboxes here:
The test was a latencytest session and both boxes crashed (Oops) during the
disk I/O tests:
here the output of my Celeron box: (UP kernel) EIDE IBM harddisk
soundcard Soundblaster Live!
-- Feb 8 17:40:15 smp kernel: Unable to handle kernel NULL pointer dereference at virtual address 0000026c Feb 8 17:40:15 smp kernel: current->tss.cr3 = 00101000, %cr3 = 00101000 Feb 8 17:40:15 smp kernel: *pde = 00000000 Feb 8 17:40:15 smp kernel: Oops: 0000 Feb 8 17:40:15 smp kernel: CPU: 0 ---here the output of my P133 with EIDE IBM HD, soundcard TB Tropez+ --- Feb 8 19:31:12 goblin kernel: Unable to handle kernel NULL pointer dereference at virtual address 00000025 Feb 8 19:31:12 goblin kernel: current->tss.cr3 = 00101000, %cr3 = 00101000 Feb 8 19:31:12 goblin kernel: *pde = 00000000 Feb 8 19:31:12 goblin kernel: Oops: 0000 Feb 8 19:31:12 goblin kernel: CPU: 0 Feb 8 19:31:12 goblin kernel: EIP: 0010:[vmalloc+18/92] Feb 8 19:31:12 goblin kernel: EFLAGS: 00010206 Feb 8 19:31:12 goblin kernel: eax: 00000011 ebx: c0316020 ecx: 00000c18 edx: 00008000 Feb 8 19:31:12 goblin kernel: esi: 00000011 edi: 00000011 ebp: c0316020 esp: c3efffa8 Feb 8 19:31:12 goblin kernel: ds: 0018 es: 0018 ss: 0018 Feb 8 19:31:12 goblin kernel: Process kswapd (pid: 5, process nr: 5, stackpage=c3eff000) Feb 8 19:31:12 goblin kernel: Stack: 000000cf 00000e00 c011cb8a c0316020 0000000b 00000006 00000030 c012196e Feb 8 19:31:13 goblin kernel: 00000006 00000030 c3efe000 c01d198e c3efe1c1 c0121a27 00000030 00000f00 Feb 8 19:31:13 goblin kernel: c3ff9fc0 c0106000 c0107c4b 00000000 00000f00 c0213fd8 Feb 8 19:31:13 goblin kernel: Call Trace: [sys_wait4+602/984] [copy_page_range+354/484] [rs_interrupt+406/1200] [zap_page_range+55/452] [get_options+0/116] [sys_sigaction+103/1044] Feb 8 19:31:13 goblin kernel: Code: 8b 76 14 83 78 20 00 75 06 f6 40 18 46 74 0f 6a 00 e8 6c 01 Feb 8 19:31:36 goblin kernel: Unable to handle kernel NULL pointer dereference at virtual address 00000000 Feb 8 19:31:36 goblin kernel: current->tss.cr3 = 006b7000, %cr3 = 006b7000 Feb 8 19:31:36 goblin kernel: *pde = 00000000 Feb 8 19:31:36 goblin kernel: Oops: 0000 Feb 8 19:31:36 goblin kernel: CPU: 0 Feb 8 19:31:36 goblin kernel: EIP: 0010:[do_acct_process+531/712] -----
any thoughts ?
PS: 2.2.14 feels much faster during the disk I/O tests of latencytest. In fact when you access to the KDE menu bars there is much less "swap-in" of the executable pages than in 2.2.10. New buffer cache algorithm ? (my disk I/O accesses are all sequential)
Benno.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue Feb 15 2000 - 21:00:13 EST