I am studying the way PVFS2 takes to keep its filesystem consistency.
For example, pvfs2-guide tell us the steps for PVFS2 to create a file
on webpage http://www.pvfs.org/pvfs2-guide.html#SECTION00036000000000000000

Here is some sentences cited from that page:

"Here are the steps necessary to create a new file in PVFS2:

create a directory entry for the new file
create a metadata object for the new file
point the directory entry to the metadata object
create a set of data objects to hold data for the new file
point the metadata at the data objects

Performing those steps in that particular order results in file system
states where a directory entry exists for a file that is not really
ready to be accessed. If we carefully order the operations:

1. create the data objects to hold data for the new file
2. create a metadata object for the new file
3. point the metadata at the data objects
4. create a directory entry for the new file pointing to the metadata object

we create a sequence of states that always leave the file system
directory hierarchy in a consistent state. The file is either there
(and ready to be accessed) or it isn't. All PVFS2 operations are
performed in this manner."

Can anybody tell me the steps PVFS2 takes for other operations like
file/dir deletion, file renaming, free space/block allocation/release.

Thanks,
Peng
_______________________________________________
Pvfs2-developers mailing list
[email protected]
http://www.beowulf-underground.org/mailman/listinfo/pvfs2-developers

Reply via email to