Hm, this is tricky. It looks like these patches include:
the addition of the multiblock allocator, already patched in my
kernel (from one of the lustre patches I believe)
the use of EXT3_MOUNT_MBALLOC
ext2_find_next_le_bit and its use
change to the signature of ext3_free_blocks
addition of buddy allocator
I have the feeling the patches for these all exist in the lustre
kernel patches dir, I'm just missing some. Still exploring.
Thanks,
--bob
On Nov 3, 2006, at 5:39 PM, Jean-Marc Saffroy wrote:
On Fri, 3 Nov 2006, Robert Olson wrote:
BUG: soft lockup detected on CPU#1!
Call Trace:
[C000000076991DC0] [C00000000000EBD0] .show_stack+0x68/0x1b0
(unreliable)
[C000000076991E60] [C000000000077484] .softlockup_tick+0xf0/0x13c
[C000000076991F10] [C000000000056114] .run_local_timers+0x1c/0x30
[C000000076991F90] [C00000000001B6C4] .timer_interrupt+0xa4/0x464
[C000000076992070] [C0000000000034EC] decrementer_common+0xec/0x100
--- Exception: 901 at .generic_find_next_zero_le_bit+0xb8/0x21c
LR = .ldiskfs_mb_init_cache+0x590/0x7a4 [ldiskfs]
[C000000076992360] [D0000000009D55D0] .ldiskfs_mb_init_cache
+0x174/0x7a4 [ldiskfs] (unreliable)
[C0000000769924D0] [D0000000009D5DEC] .ldiskfs_mb_load_buddy+0x1ec/
0x358 [ldiskfs]
You may need patches from this bug:
https://bugzilla.lustre.org/show_bug.cgi?id=10634
HTH
--
Jean-Marc Saffroy - [EMAIL PROTECTED]
_______________________________________________
Lustre-discuss mailing list
[email protected]
https://mail.clusterfs.com/mailman/listinfo/lustre-discuss
