I'm not sure if this is related but worth taking note of: write-behind when
sees a shorter write, it chooses to ignore ENOSPC or EDQUOT that it received
from the brick and will return a generic EIO sometimes.
https://bugzilla.redhat.com/show_bug.cgi?id=986812
Regards,
-Prashanth Pai
- Orig
On Tue, Oct 14, 2014 at 9:18 AM, Emmanuel Dreyfus wrote:
> Vijay Bellur wrote:
>
> > You would need to set features.soft-timeout and features.hard-timeout
> > values to 0 when testing with lower values of directory quota.
>
> It works more like expected this way, but there are still oddities: fo
J. Bruce Fields wrote:
> Is the result on non-Linux really to fail any readdir using an offset
> not returned from the current open?
Yes, but thatnon-Linux behabvior is POSIX compliant. Linux just happens
to do more than the standard here.
> I can't see how NFS READDIR will work on non-Linux pl
Edward Shishkin wrote:
> Thanks for the report,
> I am still not sure that symlinks are the culprit.
Um, you link on a symlink? That could be the answer: Linux links on the
symlink while BSD links on the target (both behavior are POSIX
compliant): Here is BSD hehavior:
# ls -l a b
-rw-r--r-- 1
FYI. :)
- Forwarded Message -
> On Tue, 2014-10-14 at 16:01 -0400, Justin Clift wrote:
> > How'd this go? :)
> >
> > + Justin
> >
> > - Original Message -
> > > Yes definitely! I'll have a look and digest, test and update over the
> > > weekend.
> > >
> > > Thanks
> > >
> > >
> > - New changes coming in should adhere to that.
> > - Old changes if they are there and let them be.
>
>
> Maybe the first change we should make is to prevent
> the script from flagging errors in the surrounding
> context (i.e. code which was already there).
OK, scratch that part. It alread
- Original Message -
> Without taking sides: the last grep is including else without either { or }.
>
> [~/work/glusterfs]
> sh$ git grep '} else {' | wc -l
> 1331
> [~/work/glusterfs]
> sh$ git grep 'else {' | grep -v '}' | wc -l
> 142
>
> So going by just numbers, "} else {" is
- Original Message -
> Hello everyone,
>
> I have cloned and built today's GlusterFS.
> The test tests/basic/uss.t fails.
> The console log and /var/log/glusterfs/mnt-glusterfs-0 attached.
> Any ideas?
As a sanity thought, does this happen consistently?
With the regression tests we run i
> - New changes coming in should adhere to that.
> - Old changes if they are there and let them be.
Maybe the first change we should make is to prevent
the script from flagging errors in the surrounding
context (i.e. code which was already there).
___
G
> are objectively less error-prone than alternatives. "Brace around
> single statement" would have been the perfect example, except that I
> already fixed it with http://review.gluster.org/#/c/8813/. Thus,
> developers could be faced with page after page of style errors because
> they *copied the
On Sun, Oct 12, 2014 at 10:09:01AM +0200, Emmanuel Dreyfus wrote:
> When quota xlator is enabled, bricks get this:
>
> [2014-10-12 07:56:03.090516] E [posix.c:4874:posix_fill_readdir]
> 0-patchy-posix: seekdir(-1154801456) failed on dir=0xb99cb250: Invalid
> argument (offset reused from another DI
Hello Emmanuel,
Thanks for the report,
I am still not sure that symlinks are the culprit.
Could you please try the attached version of crypt.t and report results?
Thank you,
Edward.
On Fri, 10 Oct 2014 20:10:08 +0200
m...@netbsd.org (Emmanuel Dreyfus) wrote:
> Edward Shishkin wrote:
>
> > Co
- Original Message -
> That's a computer's job. Perahps it could be done automaticaly?
Whitespace yeah. Different people have different settings for their
tabs though (eg 2, 4, or 8 spaces), so prob best done by hand. Before
submitting. ;)
+ Justin
--
GlusterFS - http://www.gluster.or
On 10/14/2014 08:23 AM, Jeff Darcy wrote:
We should try comparing performance of multi-thread-epoll to
own-thread, shouldn't be hard to hack own-thread into non-SSL-socket
case.
Own-thread has always been available on non-SSL sockets, from the day it
was first implemented as part of HekaFS.
HO
On Tue, Oct 14, 2014 at 11:55:31AM -0400, Justin Clift wrote:
> Would you be ok to fix the embedded tabs and trailing whitespace in that? :)
That's a computer's job. Perahps it could be done automaticaly?
--
Emmanuel Dreyfus
m...@netbsd.org
___
Gluster
- Original Message -
> You would need to set features.soft-timeout and features.hard-timeout
> values to 0 when testing with lower values of directory quota.
>
> I have a WIP patch describing these options at [1].
Would you be ok to fix the embedded tabs and trailing whitespace in that? :
Recently there has been some controversy about the coding style being
enforced by checkpatch.pl since some weeks ago. Instead of pointing
fingers, I thought it might be useful to get some objective information
that can help us make the situation better. Accordingly, I ran
checkpatch.pl over our e
> We should try comparing performance of multi-thread-epoll to
> own-thread, shouldn't be hard to hack own-thread into non-SSL-socket
> case.
Own-thread has always been available on non-SSL sockets, from the day it
was first implemented as part of HekaFS.
> HOWEVER, if "own-thread" implies a thre
- Original Message -
> This e-mail is specifically about use of multi-thread-epoll optimization
> (originally prototyped by Anand Avati) to solve a Gluster performance
> problem: single-threaded reception of protocol messages (for non-SSL
> sockets), and consequent inability to fully utiliz
This e-mail is specifically about use of multi-thread-epoll optimization
(originally prototyped by Anand Avati) to solve a Gluster performance problem:
single-threaded reception of protocol messages (for non-SSL sockets), and
consequent inability to fully utilize available CPU on server. A disc
On Tue, Oct 14, 2014 at 07:42:54AM -0400, Kaleb KEITHLEY wrote:
>
> >
> >[~/work/glusterfs]
> >sh$ git grep '} else {' | wc -l
> > 1331
> >[~/work/glusterfs]
> >sh$ git grep 'else {' | grep -v '}' | wc -l
> > 142
> >
> >So going by just numbers, "} else {" is 10x more common than "}\n els
On Mon, Oct 13, 2014 at 10:07:51AM -0700, Dave McAllister wrote:
> Good day, all
>
> Just a reminder that we will be having a GlusterFS bug prioritization
> meeting Tuesday 14-Oct-2014, 12:00 UTC.
>
> More information available at :
> http://blog.gluster.org/2014/10/whats-that-bug-to-you-gluster
On Mon, Oct 13, 2014 at 10:04:33AM +, Emmanuel Dreyfus wrote:
> Here it is:
> http://review.gluster.org/8926
It passed regression, please review.
Linux behavior is unaltered.
--
Emmanuel Dreyfus
m...@netbsd.org
___
Gluster-devel mailing list
Gluste
[~/work/glusterfs]
sh$ git grep '} else {' | wc -l
1331
[~/work/glusterfs]
sh$ git grep 'else {' | grep -v '}' | wc -l
142
So going by just numbers, "} else {" is 10x more common than "}\n else
{". I also find that believable based on familiarity of seeing this
pattern in the code.
So I was able to compile gluster 3.3.2. on Solaris 11 and have it running a
volume now! Which is great, I couldn't be more excited.
What this brings to mind, however, is I am missing out on the newer
features and management commands I was used to in version 3.4, when I
started with gluster, and wh
25 matches
Mail list logo