Revision 7ce9d5d1f3c8736511daa413c64985a05b2feee3 authored by Eric Sandeen on 04 March 2009, 23:38:18 UTC, committed by Theodore Ts'o on 04 March 2009, 23:38:18 UTC
I was seeing fsck errors on inode bitmaps after a 4 thread dbench run on a 4 cpu machine: Inode bitmap differences: -50736 -(50752--50753) etc... I believe that this is because ext4_free_inode() uses atomic bitops, and although ext4_new_inode() *used* to also use atomic bitops for synchronization, commit 393418676a7602e1d7d3f6e560159c65c8cbd50e changed this to use the sb_bgl_lock, so that we could also synchronize against read_inode_bitmap and initialization of uninit inode tables. However, that change left ext4_free_inode using atomic bitops, which I think leaves no synchronization between setting & unsetting bits in the inode table. The below patch fixes it for me, although I wonder if we're getting at all heavy-handed with this spinlock... Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
1 parent fec6c6f
File | Mode | Size |
---|---|---|
mpi.h | -rw-r--r-- | 34.2 KB |
mpi_cnfg.h | -rw-r--r-- | 157.2 KB |
mpi_fc.h | -rw-r--r-- | 17.5 KB |
mpi_history.txt | -rw-r--r-- | 53.1 KB |
mpi_init.h | -rw-r--r-- | 28.6 KB |
mpi_ioc.h | -rw-r--r-- | 59.3 KB |
mpi_lan.h | -rw-r--r-- | 9.6 KB |
mpi_log_fc.h | -rw-r--r-- | 5.9 KB |
mpi_log_sas.h | -rw-r--r-- | 22.6 KB |
mpi_raid.h | -rw-r--r-- | 11.5 KB |
mpi_sas.h | -rw-r--r-- | 12.8 KB |
mpi_targ.h | -rw-r--r-- | 33.5 KB |
mpi_tool.h | -rw-r--r-- | 17.5 KB |
mpi_type.h | -rw-r--r-- | 2.2 KB |
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...