I've no idea whether this problem is actually LFS related or I was just hitting 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 worth to try LFS. So we dumped the database, set up an LFS partition on a development server and fed the dump into mysql. First, everything went as expected (mysqld being CPU bound). Then, as most of the database seems to have been 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 also hung). We experienced another problem during RAID parity rebuild, but that will go into its own message.

As there's rumor about LFS problems with the partition running full, I then restarted the experiment with a larger LFS partition. Possibly a coincedence, but everything went fine. Only, shortly before reading the dump finished, I observed ioflush occupying some 60% or 80% CPU time. All the time, the process was CPU bound as we hoped.