Here is a rewrite of gdlm_plock_callback(). We still need to add the
lock cancel.
Marc.
int gdlm_plock_callback(struct plock_op *op)
{
struct file *file;
struct file_lock *fl;
int (*notify)(void *, void *, int) = NULL;
int rv;
spin_lock(&ops_lock);
if (!list_empty(&op->lis
On Dec 06, 2006 09:42 -0800, Ulrich Drepper wrote:
> Rob Ross wrote:
> >File size is definitely one of the more difficult of the parameters,
> >either because (a) it isn't stored in one place but is instead derived,
> >or (b) because a lock has to be obtained to guarantee consistency of the
> >
On Thu, 2006-12-07 at 12:44 +1100, David Chinner wrote:
> Maybe we should be using EAs for this sort of thing instead of flags
> on the inode? If we keep adding inode flags for generic features
> then we are going to force more than just XFS into inode format
> changes eventually
You do need t
On Wed, Dec 06, 2006 at 07:14:58PM -0800, Nicholas Miell wrote:
> On Thu, 2006-12-07 at 13:49 +1100, David Chinner wrote:
> > On Wed, Dec 06, 2006 at 09:35:30PM -0500, Josef Sipek wrote:
> > > On Thu, Dec 07, 2006 at 12:44:27PM +1100, David Chinner wrote:
> > > > Maybe we should be using EAs for th
On Wed, 2006-12-06 at 20:11 +1100, David Chinner wrote:
> ...
> If all we need to add to XFS is support for those flags, then XFS
> support would be trivial to add.
>
> Oh, damn. I take that back. We're almost out of flag space in the on
> disk inode - these two flags would use the last 2 flag bit
On Thu, 2006-12-07 at 13:49 +1100, David Chinner wrote:
> On Wed, Dec 06, 2006 at 09:35:30PM -0500, Josef Sipek wrote:
> > On Thu, Dec 07, 2006 at 12:44:27PM +1100, David Chinner wrote:
> > > Maybe we should be using EAs for this sort of thing instead of flags
> > > on the inode? If we keep adding
On Wed, Dec 06, 2006 at 09:35:30PM -0500, Josef Sipek wrote:
> On Thu, Dec 07, 2006 at 12:44:27PM +1100, David Chinner wrote:
> > Maybe we should be using EAs for this sort of thing instead of flags
> > on the inode? If we keep adding inode flags for generic features
> > then we are going to force
On Thu, Dec 07, 2006 at 12:44:27PM +1100, David Chinner wrote:
> Maybe we should be using EAs for this sort of thing instead of flags
> on the inode? If we keep adding inode flags for generic features
> then we are going to force more than just XFS into inode format
> changes eventually
Aren't
On Wed, Dec 06, 2006 at 07:56:19PM -0500, Josef Sipek wrote:
> On Wed, Dec 06, 2006 at 08:11:00PM +1100, David Chinner wrote:
> > They are defined but unused in 2.6.19, right? I can't see anywhere
> > in the 2.6.19 ext2/3/4/reiser trees that actually those flags,
> > including setting and retrievin
On Wed, Dec 06, 2006 at 08:11:00PM +1100, David Chinner wrote:
> They are defined but unused in 2.6.19, right? I can't see anywhere
> in the 2.6.19 ext2/3/4/reiser trees that actually those flags,
> including setting and retrieving them from disk. JFS i can see
> sets, clears and retreives them, bu
On Wed, Dec 06, 2006 at 03:09:10PM -0700, Andreas Dilger wrote:
> > While it could do that, I'd be interested to see how you'd construct
> > the handle such that it's immune to a malicious user tampering with it,
> > or saving it across a reboot, or constructing one from scratch.
>
> If the server
On Wed, 2006-12-06 at 18:12 -0500, Latchesar Ionkov wrote:
> On 12/5/06, Christoph Hellwig <[EMAIL PROTECTED]> wrote:
> > On Tue, Dec 05, 2006 at 05:55:14PM +0100, Latchesar Ionkov wrote:
> > > What is your opinion on giving the file system an option to lookup a
> > > file more than one name/direct
On Wed, Dec 06, 2006 at 09:42:47AM -0600, Rob Ross wrote:
> The fh_t is indeed a type of capability. fh_t, properly protected, could
> be passed into user space and validated by the file system when
> presented back to the file system.
Well, there's quite a lot of papers on how to implement prop
On 12/5/06, Rob Ross <[EMAIL PROTECTED]> wrote:
I unfortunately don't have data to show exactly where the time was
spent, but it's a good guess that it is all the network traffic in the
open() case.
Is it hard to repeat the test and check what requests (and how much
time do they take) PVFS serv
On 12/6/06, Rob Ross <[EMAIL PROTECTED]> wrote:
David Chinner wrote:
> On Tue, Dec 05, 2006 at 05:47:16PM +0100, Latchesar Ionkov wrote:
>> On 12/5/06, Rob Ross <[EMAIL PROTECTED]> wrote:
>>> Hi,
>>>
>>> I agree that it is not feasible to add new system calls every time
>>> somebody has a problem
On 12/5/06, Christoph Hellwig <[EMAIL PROTECTED]> wrote:
On Tue, Dec 05, 2006 at 05:55:14PM +0100, Latchesar Ionkov wrote:
> What is your opinion on giving the file system an option to lookup a
> file more than one name/directory at a time? I think that all remote
> file systems can benefit from
On Dec 06, 2006 15:17 -0700, Matthew Wilcox wrote:
> On Wed, Dec 06, 2006 at 03:09:10PM -0700, Andreas Dilger wrote:
> > Considering that filesystems like GFS and OCFS allow clients DIRECT
> > ACCESS to the block device itself (which no amount of authentication
> > will fix, unless it is in the di
On Wed, Dec 06, 2006 at 03:09:10PM -0700, Andreas Dilger wrote:
> Considering that filesystems like GFS and OCFS allow clients DIRECT
> ACCESS to the block device itself (which no amount of authentication
> will fix, unless it is in the disks themselves), the risk of passing a
> file handle around
On Dec 06, 2006 13:50 -0700, Matthew Wilcox wrote:
> On Thu, Dec 07, 2006 at 07:40:05AM +1100, David Chinner wrote:
> > This is an implementation detail - it is possible that file handle,
> > being opaque, could encode a UID/GID of the user that constructed
> > the handle and then allow any proces
On Wed, Dec 06, 2006 at 03:42:31PM -0600, David Teigland wrote:
> Oh yeah, that's painful, I knew it sounded too easy.
Yeah. Well, we could try to teach GFS2 to reliably cancel posix locks.
I think that may turn out to be necessary some day anyway.
Or we could look at why we're timing out and fi
On Wed, Dec 06, 2006 at 04:23:47PM -0500, J. Bruce Fields wrote:
> On Wed, Dec 06, 2006 at 02:58:22PM -0600, David Teigland wrote:
> > On Wed, Dec 06, 2006 at 02:57:22PM -0500, J. Bruce Fields wrote:
> > > The more annoying problem is the need to cancel the GFS lock when
> > > fl_notify fails; is t
On Wed, Dec 06, 2006 at 02:58:22PM -0600, David Teigland wrote:
> On Wed, Dec 06, 2006 at 02:57:22PM -0500, J. Bruce Fields wrote:
> > The more annoying problem is the need to cancel the GFS lock when
> > fl_notify fails; is that something that it's possible for GFS to do?
> >
> > It can fail beca
On Wed, Dec 06, 2006 at 01:50:24PM -0700, Matthew Wilcox wrote:
> On Thu, Dec 07, 2006 at 07:40:05AM +1100, David Chinner wrote:
> > Permission checks are done on the path_to_handle(), so in reality
> > only root or CAP_SYS_ADMIN users can currently use the
> > open_by_handle interface because of t
On Wed, Dec 06, 2006 at 02:50:49PM -0600, Rob Ross wrote:
> David Chinner wrote:
> >On Wed, Dec 06, 2006 at 09:53:39AM -0600, Rob Ross wrote:
> >>David Chinner wrote:
> >>>Does anyone here know about the XFS libhandle API? This has been around
> >>>for
> >>>years and it does _exactly_ what these p
On Wed, Dec 06, 2006 at 02:57:22PM -0500, J. Bruce Fields wrote:
> On Wed, Dec 06, 2006 at 09:49:51AM -0600, David Teigland wrote:
> > The gfs side looks fine to me. Did you forget to call fl_notify from
> > gdlm_plock_callback() or am I missing something?
>
> Yes, looks like we missed something,
David Chinner wrote:
On Wed, Dec 06, 2006 at 09:53:39AM -0600, Rob Ross wrote:
David Chinner wrote:
On Tue, Dec 05, 2006 at 05:47:16PM +0100, Latchesar Ionkov wrote:
On 12/5/06, Rob Ross <[EMAIL PROTECTED]> wrote:
Hi,
I agree that it is not feasible to add new system calls every time
somebod
On Wed, Dec 06, 2006 at 10:20:23AM -0600, Rob Ross wrote:
> Matthew Wilcox wrote:
> >On Wed, Dec 06, 2006 at 09:53:39AM -0600, Rob Ross wrote:
> >>David Chinner wrote:
> >>>Does anyone here know about the XFS libhandle API? This has been
> >>>around for years and it does _exactly_ what these propos
On Thu, Dec 07, 2006 at 07:40:05AM +1100, David Chinner wrote:
> Permission checks are done on the path_to_handle(), so in reality
> only root or CAP_SYS_ADMIN users can currently use the
> open_by_handle interface because of this lack of checking. Given
> that our current users of this interface n
On Wed, Dec 06, 2006 at 09:53:39AM -0600, Rob Ross wrote:
> David Chinner wrote:
> >On Tue, Dec 05, 2006 at 05:47:16PM +0100, Latchesar Ionkov wrote:
> >>On 12/5/06, Rob Ross <[EMAIL PROTECTED]> wrote:
> >>>Hi,
> >>>
> >>>I agree that it is not feasible to add new system calls every time
> >>>someb
On Wed, Dec 06, 2006 at 02:57:22PM -0500, J. Bruce Fields wrote:
> On Wed, Dec 06, 2006 at 09:49:51AM -0600, David Teigland wrote:
> > The gfs side looks fine to me. Did you forget to call fl_notify from
> > gdlm_plock_callback() or am I missing something?
>
> Yes, looks like we missed something,
On Wed, Dec 06, 2006 at 09:49:51AM -0600, David Teigland wrote:
> The gfs side looks fine to me. Did you forget to call fl_notify from
> gdlm_plock_callback() or am I missing something?
Yes, looks like we missed something, thanks. This code's an rfc (not
even tested), so don't apply it yet! Wha
On Dec 6 2006 12:32, Josef Sipek wrote:
>> > >+int __init init_sioq(void)
>> >
>> > Although it's just me, I'd prefer sioq_init(), sioq_exit(),
>> > sioq_run(), etc. to go in hand with what most drivers use as naming
>> > (i.e. "_" ).
>>
>> That makes sense.
>
>Hrm. Looking at the code, I noti
Ragnar Kjørstad wrote:
I guess the code needs to be checked, but I would think that:
* ls
* find
* rm -r
* chown -R
* chmod -R
* rsync
* various backup software
* imap servers
Then somebody do the analysis. And please an analysis which takes into
account that some programs might need to be ad
On Wed, Dec 06, 2006 at 09:42:55AM -0800, Ulrich Drepper wrote:
> >I can't speak for everyone, but "ls" is the #1 consumer as far as I am
> >concerned.
>
> So a syscall for ls alone?
I guess the code needs to be checked, but I would think that:
* ls
* find
* rm -r
* chown -R
* chmod -R
* rsync
*
Rob Ross wrote:
File size is definitely one of the more difficult of the parameters,
either because (a) it isn't stored in one place but is instead derived,
or (b) because a lock has to be obtained to guarantee consistency of the
returned value.
OK, and looking at the man page again, it is al
On Tue, Dec 05, 2006 at 02:50:13PM -0500, Josef Sipek wrote:
> On Tue, Dec 05, 2006 at 08:27:51PM +0100, Jan Engelhardt wrote:
> >
> > On Dec 4 2006 07:30, Josef 'Jeff' Sipek wrote:
> > >+#include "union.h"
> > >+
> > >+struct workqueue_struct *sioq;
> > >+
> > >+int __init init_sioq(void)
> >
>
Ulrich Drepper wrote:
Andreas Dilger wrote:
Does this mean you are against the statlite() API entirely, or only
against
the document's use of the flag as a vague "accuracy" value instead of a
hard "valid" value?
I'm against fuzzy values. I've no problems with a bitmap specifying
that certai
Andreas Dilger wrote:
Does this mean you are against the statlite() API entirely, or only against
the document's use of the flag as a vague "accuracy" value instead of a
hard "valid" value?
I'm against fuzzy values. I've no problems with a bitmap specifying
that certain members are not wanted
Trond Myklebust wrote:
On Tue, 2006-12-05 at 16:11 -0600, Rob Ross wrote:
Trond Myklebust wrote:
b) quite unnatural to impose caching semantics on all the
directory _entries_ using a syscall that refers to the directory
itself (see the explanations by both myself and Pet
Matthew Wilcox wrote:
On Wed, Dec 06, 2006 at 09:53:39AM -0600, Rob Ross wrote:
David Chinner wrote:
Does anyone here know about the XFS libhandle API? This has been
around for years and it does _exactly_ what these proposed syscalls
are supposed to do (and more).
Thanks for pointing these out
Matthew Wilcox wrote:
On Wed, Dec 06, 2006 at 09:04:00AM -0600, Rob Ross wrote:
The openg() solution has the following advantages to what you propose.
First, it places the burden of the communication of the file handle on
the application process, not the file system. That means less work for
t
On Wed, Dec 06, 2006 at 09:53:39AM -0600, Rob Ross wrote:
> David Chinner wrote:
> >Does anyone here know about the XFS libhandle API? This has been
> >around for years and it does _exactly_ what these proposed syscalls
> >are supposed to do (and more).
>
> Thanks for pointing these out Dave. Thes
On Wed, Dec 06, 2006 at 12:34:20AM -0500, J. Bruce Fields wrote:
> +int gdlm_plock_callback(struct plock_op *op)
> +{
> + struct file *file;
> + struct file_lock *fl;
> + int rv;
> +
> + spin_lock(&ops_lock);
> + if (!list_empty(&op->list)) {
> + printk(KERN_INFO "pl
David Chinner wrote:
On Tue, Dec 05, 2006 at 05:47:16PM +0100, Latchesar Ionkov wrote:
On 12/5/06, Rob Ross <[EMAIL PROTECTED]> wrote:
Hi,
I agree that it is not feasible to add new system calls every time
somebody has a problem, and we don't take adding system calls lightly.
However, in this
Sage Weil wrote:
On Mon, 4 Dec 2006, Peter Staubach wrote:
I think that there are several points which are missing here.
First, readdirplus(), without any sort of caching, is going to be _very_
expensive, performance-wise, for _any_ size directory. You can see this
by instrumenting any NFS ser
On Wed, Dec 06, 2006 at 09:04:00AM -0600, Rob Ross wrote:
> The openg() solution has the following advantages to what you propose.
> First, it places the burden of the communication of the file handle on
> the application process, not the file system. That means less work for
> the file system.
Christoph Hellwig wrote:
On Tue, Dec 05, 2006 at 03:44:31PM -0600, Rob Ross wrote:
The openg() really just does the lookup and permission checking). The
openfh() creates the file descriptor and starts that context if the
particular FS tracks that sort of thing.
...
Well you've caught me. I d
On Wed, 2006-12-06 at 11:01 +, Christoph Hellwig wrote:
> Say you want to lookup a path /foo/bar/baz, then the access permission
> is based on the following things:
>
> - the credentials of the user. let's only take traditional uid/gid
>for this example although credentials are much more
On Wed, 2006-12-06 at 13:22 +0100, Ragnar Kjørstad wrote:
> On Tue, Dec 05, 2006 at 09:55:16AM -0500, Trond Myklebust wrote:
> > > The again statlite and
> > > readdirplus really are the most sane bits of these proposals as they
> > > fit nicely into the existing set of APIs. The filehandle idiocy
On Wed, 2006-12-06 at 03:28 -0700, Andreas Dilger wrote:
> On Dec 05, 2006 10:23 -0500, Trond Myklebust wrote:
> > On Tue, 2006-12-05 at 03:26 -0700, Andreas Dilger wrote:
> > > I think the "barrier semantics" are something that have just crept
> > > into this discussion and is confusing the issue
Matthew Wilcox wrote:
On Tue, Dec 05, 2006 at 10:07:48AM +, Christoph Hellwig wrote:
The filehandle idiocy on the other hand is way of into crackpipe land.
Right, and it needs to be discarded. Of course, there was a real
problem that it addressed, so we need to come up with an acceptable
Wendy Cheng wrote:
J. Bruce Fields wrote:
From: J. Bruce Fields <[EMAIL PROTECTED]>
From: Marc Eshel <[EMAIL PROTECTED]>
Add NFS lock support to GFS2. (Untested.)
Untested ? Trying to keep us busy ?
Sorry, forgot this is on external mailing lists
Nice piece of work ! T
>
> > if (inode->i_sb->s_flags & MS_NOATIME)
> > return;
> So that that one can be deleted.
Hi,
I would mostly expect the compiler to be relatively smart about this and
group a bunch of these tests together... so I rather see readable code
than optimized code for something the
On Tue, Dec 05, 2006 at 09:55:16AM -0500, Trond Myklebust wrote:
> > The again statlite and
> > readdirplus really are the most sane bits of these proposals as they
> > fit nicely into the existing set of APIs. The filehandle idiocy on
> > the other hand is way of into crackpipe land.
>
> ...
>
Hi,
This looks good to me, and I'm copying in Dave & Wendy who have both
done previous work in this area for further comment. Provided we can get
this tested, I'd be happy to accept the patch in its current form.
Steve.
On Wed, 2006-12-06 at 00:34 -0500, J. Bruce Fields wrote:
> From: J. Bruce F
On Tue, Dec 05, 2006 at 03:44:31PM -0600, Rob Ross wrote:
> The openg() really just does the lookup and permission checking). The
> openfh() creates the file descriptor and starts that context if the
> particular FS tracks that sort of thing.
...
> Well you've caught me. I don't want to cache t
On Dec 05, 2006 10:23 -0500, Trond Myklebust wrote:
> On Tue, 2006-12-05 at 03:26 -0700, Andreas Dilger wrote:
> > I think the "barrier semantics" are something that have just crept
> > into this discussion and is confusing the issue.
>
> It is the _only_ concept that is of interest for something
On Dec 05, 2006 15:55 -0800, Ulrich Drepper wrote:
> I don't think an accuracy flag is useful at all. Programs don't want to
> use fuzzy information. If you want a fast 'ls -l' then add a mode which
> doesn't print the fields which are not provided. Don't provide outdated
> information. Sim
On Tue, Dec 05, 2006 at 05:47:16PM +0100, Latchesar Ionkov wrote:
> On 12/5/06, Rob Ross <[EMAIL PROTECTED]> wrote:
> >Hi,
> >
> >I agree that it is not feasible to add new system calls every time
> >somebody has a problem, and we don't take adding system calls lightly.
> >However, in this case we'
On Wednesday 06 December 2006 05:58, Andrew Morton wrote:
> > On Mon, 4 Dec 2006 16:36:20 -0800 Valerie Henson
> > <[EMAIL PROTECTED]> wrote: Add "relatime" (relative atime)
> > support. Relative atime only updates the atime if the previous atime is
> > older than the mtime or ctime. Like noatime,
On Tue, Dec 05, 2006 at 11:41:28AM -0500, Nikolai Joukov wrote:
> > > As we promised on the linux-ext4 list on October 31, here is the patch
> > > that adds secure deletion via a trash-bin functionality for ext4. It is a
> > > compromise solution that combines secure deletion with the trash-bin
>
On Tue, Dec 05, 2006 at 08:58:02PM -0800, Andrew Morton wrote:
> > On Mon, 4 Dec 2006 16:36:20 -0800 Valerie Henson <[EMAIL PROTECTED]> wrote:
> > Add "relatime" (relative atime) support. Relative atime only updates
> > the atime if the previous atime is older than the mtime or ctime.
> > Like noa
62 matches
Mail list logo