| |||||||||||||
|
| |||||||||||||
Async I/OAsync I/OPosted Apr 8, 2009 8:30 UTC (Wed) by jamesh (subscriber, #1159)In reply to: Async I/O by bojan Parent article: Linux Storage and Filesystem workshop, day 1
With this proposal, you're now in a situation where every reader of the file needs to participate in the crash recovery, rather than having the writer ensure that the file is written correctly.
Also, readers would need to differentiate between the case of "foo~" existing because the system crashed and "foo~" existing because some other process is in the process of replacing "foo" and waiting on the fsync.
(Log in to post comments)
Async I/O Posted Apr 8, 2009 11:02 UTC (Wed) by bojan (subscriber, #14302) [Link]
As I said, this will work for one process only. With Gnome, at least, this is the case.
|
|
||||||||||||