On Dec 7, 2007, at 1:57 PM, Sam Lang wrote:
On Dec 7, 2007, at 1:54 PM, Murali Vilayannur wrote:
I'm confused now. Why do we need a dentry cache timeout?
i.e. only if we wish to take advantage of the kernel provided dcache.
Right now, it is as if the timeout is 0, i..e hits in the dcache
On Dec 7, 2007, at 1:54 PM, Murali Vilayannur wrote:
Sam,
I think we try to keep the kmod simple so that its only forwarding
requests to the daemon. Caching fits better in the daemon if that's
the case.
Sure.. Okay.
I'm confused now. Why do we need a dentry cache timeout?
i.e. only if
Sam,
>
> I think we try to keep the kmod simple so that its only forwarding
> requests to the daemon. Caching fits better in the daemon if that's
> the case.
Sure.. Okay.
> I'm confused now. Why do we need a dentry cache timeout?
i.e. only if we wish to take advantage of the kernel provided dca
On Dec 7, 2007, at 1:04 PM, Murali Vilayannur wrote:
Hi Sam,
I can test it on older kernels. :-)
Okay.. sounds good!
We do this with the ncache in the client daemon. Sure, it still
requires invalidating an entry and doing the lookup through the VFS
to
the client daemon, but that seems
Hi Sam,
>
> I can test it on older kernels. :-)
Okay.. sounds good!
> We do this with the ncache in the client daemon. Sure, it still
> requires invalidating an entry and doing the lookup through the VFS to
> the client daemon, but that seems tiny by comparison to the network
> roundtrip.
RIght
On Dec 7, 2007, at 11:45 AM, Murali Vilayannur wrote:
Sam,
d_revalidate is invoked for every hit in the dentry cache.
If a file system believes that all its dentries are valid all the
time, it does not
bother implementing this callback.
if we return > 0, it is intended to mean success and the d
Sam,
d_revalidate is invoked for every hit in the dentry cache.
If a file system believes that all its dentries are valid all the
time, it does not
bother implementing this callback.
if we return > 0, it is intended to mean success and the dentry is valid.
== 0, means we tell vfs to invalidate the
Please ignore the second patch in that email. I need it to return 0
(invalid) for negative dentries, to avoid the inconsistency with
remove/create cases I mentioned.
-sam
On Dec 5, 2007, at 2:35 PM, Sam Lang wrote:
Hi Murali,
I'm trying to figure out a bug in pvfs_revalidate_common. M
