Hi Edgar,

i'm experiencing similar problems at the moment.
I've upgraded to 4.99.14 yesterday and my system starts to slowly lock
up after find is hanging in vnlock state.
"find" is executed for example by running daily cronjobs at 3 o'clock.
Although I could trigger it by running "locate.update".
The odd thing is that running find and locate update immediately after
a reboot works just fine.
I've had no problems until 4.99.12. I'm using LFS since 3.99.21
I doubt it's a LFS bug.

Zafer.



2007/3/1, Edgar Fu=DF <efnbl06@maus.maus.net>:
> I've no idea whether this problem is actually LFS related or I was just h=
itting a coincidence.
>
> We have performance problems on our mySQL server. As analysis showed that=
 disk I/O, in particular seeks, were the problem, I thought it might be wor=
th to try LFS. So we dumped the database, set up an LFS partition on a deve=
lopment server and fed the dump into mysql. First, everything went as expec=
ted (mysqld being CPU bound). Then, as most of the database seems to have b=
een written, we observed ioflush consuming 100% CPU load. From then on, any=
 attempt to access the LFS partition (ls, du) locked up in vnlock state.
>
> After a few minutes, we rebooted the machine (via reset as the shutdown a=
lso hung). We experienced another problem during RAID parity rebuild, but t=
hat will go into its own message.
>
> As there's rumor about LFS problems with the partition running full, I th=
en restarted the experiment with a larger LFS partition. Possibly a coinced=
ence, but everything went fine. Only, shortly before reading the dump finis=
hed, I observed ioflush occupying some 60% or 80% CPU time. All the time, t=
he process was CPU bound as we hoped.
>