Hi! > I would like some clarity on which of the file system tests are doing > most extensive r/w operations. I run these LTP fs tests on an SD card. > For past sometime I face issue where the card gets disconnected with > below errors at times and doesn't get detected again. This mostly > happens on ftest* where sync/fsync is happening:
Most of the filesystem testcases are stress tests. There are a few testcases for file permissions, extended attributes, procfs and so, but the rest just hammers filesystem with various types of load. Especially the aio testcases are all stressing the system with excesive I/O. > > I/O error , DID_NO_CONNECT > > [ 3277.237974] EXT4-fs error (device sdc1): ext4_put_super:861: Couldn't > clean up the journal > > I am suspecting that these tests over a period of time have caused the > card's flash memory life to near end, because when I used a newer card > yesterday the results improved and these errors didn't come. My guess is that the area used for the ext4 journal has died, which is inevitable because the journal gets written over and over (it's a circular log of fs operations). It's better to turn the journal off for SD cards (and even better aling the filesystem to the card erase block size). Have a look at: https://blogofterje.wordpress.com/2012/01/14/optimizing-fs-on-sd-card/ -- Cyril Hrubis chru...@suse.cz ------------------------------------------------------------------------------ Dive into the World of Parallel Programming. The Go Parallel Website, sponsored by Intel and developed in partnership with Slashdot Media, is your hub for all things parallel software development, from weekly thought leadership blogs to news, videos, case studies, tutorials and more. Take a look and join the conversation now. http://goparallel.sourceforge.net/ _______________________________________________ Ltp-list mailing list Ltp-list@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ltp-list
