On Mon, 2014-02-24 at 08:34 +0100, Henrik Goldman wrote: > Hello, > > In the last couple of days I saw a series of these errors. Can someone > say what it is and what consequences it has? I assume dataloss is > always the case, right? > > [460976.529867] fd_do_rw() returned -22 for non S_ISBLK > [460977.529895] fd_do_rw() returned -22 for non S_ISBLK > [460978.530471] fd_do_rw() returned -22 for non S_ISBLK > [460979.530994] fd_do_rw() returned -22 for non S_ISBLK > [467598.475214] fd_do_rw() returned -22 for non S_ISBLK > [467599.151055] fd_do_rw() returned -22 for non S_ISBLK > [467600.150796] fd_do_rw() returned -22 for non S_ISBLK > [467601.151342] fd_do_rw() returned -22 for non S_ISBLK > The -EINVAL (-22) failure is occurring during a normal FILEIO vfs_read() operation, which ends up causing SCSI READ commands to return a non GOOD status back to the initiator LUN. AFAICT the error is not occurring during WRITEs operations, so the original blocks on the underlying struct file backend should still be intact. > This is on Ubuntu 13.10 with kernel 3.11.0-14 (customly patched for fileio): > What's the extra patch..? > uname -a > Linux linuxstore-1 3.11.0-14-generic #21 SMP Tue Dec 10 16:54:51 CET > 2013 x86_64 x86_64 x86_64 GNU/Linux > Need more context on what's underneath the FILEIO LUNs to be helpful.. --nab -- To unsubscribe from this list: send the line "unsubscribe target-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
