On Wednesday 17 October 2007 11:13, Eric W. Biederman wrote:Technically, it does change correctness: after BLKFLSBUF, the ramdisk should contain zeroes. I'm assuming it would also cause problems in tight embedded environments if ramdisk ram is supposed to be thrown away but isn't. So maybe not technically a correctness problem, but could be the difference between working and not working. Sure, you could do that, but you still presumably need to support the old behaviour. As a test vehicle for filesystems, I'd much rather it didn't do this of course, because subsequent writes would need to reallocate the page again. -
| Adrian Bunk | Re: Linux 2.6.21 |
| Linus Torvalds | Linux 2.6.21-rc2 |
| WANG Cong | [-mm Patch] UML: fix a building error |
| Roland McGrath | Re: [PATCH 0/5] ftrace: to kill a daemon |
git: | |
| Natalie Protasevich | [BUG] New Kernel Bugs |
| David Miller | Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock(). |
| Patrick McHardy | Re: [PATCH] netfilter: use per-cpu spinlock rather than RCU (v3) |
| Gerrit Renker | [PATCH 27/37] dccp: Integration of dynamic feature activation - part 2 (server side) |
| Theodore Ts'o | Re: cc1 fails silently |
| Michael Nolan | Power routines on notebook cause kernel panic |
| Marc Peters | v 0.11 boot disk problem |
| Dave `geek' Gymer | WARNING (was Re: New afio release) |
