Hey Nithya,

root@PB-WA-AA-00-A:/# glusterfs -V
glusterfs 3.10.1
Repository revision: git://git.gluster.org/glusterfs.git
Copyright (c) 2006-2016 Red Hat, Inc. <https://www.gluster.org/>
GlusterFS comes with ABSOLUTELY NO WARRANTY.
It is licensed to you under your choice of the GNU Lesser
General Public License, version 3 or any later version (LGPLv3
or later), or the GNU General Public License, version 2 (GPLv2),
in all cases as published by the Free Software Foundation.

We have also set the performance.parallel-readdir option to off, based on the 
information provided in the Bugzilla report you included.
We’re currently pending confirmation as to if this has resolved the issue for 
the short term. I’ll update you with this once I’ve received confirmation.

We’re also planning an upgrade to 3.10.2 shortly.

Regards,
[Probax]

Joshua Coyle


P

1300 885 117

E

[email protected]<mailto:[email protected]>

W

probax.io<http://www.probax.io/>


A

QV1 Perth,


Level 33/250 St Georges Tce,


Perth WA 6000



smart safe local cloud




From: Nithya Balachandran [mailto:[email protected]]
Sent: Wednesday, May 31, 2017 6:20 PM
To: Joshua Coyle <[email protected]>
Cc: [email protected]; Gurusiddaiah, Poornima <[email protected]>; 
Raghavendra Gowdappa <[email protected]>; Ravishankar Narayanankutty 
<[email protected]>
Subject: Re: [Gluster-users] FW: ATTN: nbalacha IRC - Gluster - BlackoutWNCT 
requested info for 0byte file issue

CCing Ravi (arbiter) , Poornima and Raghavendra (parallel readdir)

Hi Joshua,

I had a quick look at the files you sent across.  To summarize the issue, you 
see empty linkto files on the mount point.

From the logs I see  that parallel readdir is enabled for this volume:

performance.readdir-ahead: on
performance.parallel-readdir: on

There was a similar issue reported earlier [1] and fixed as part of [2]. Which 
version of gluster are you running? Poornima and Raghavendra, can you take a 
look and see if it is the same issue?



An interesting observation - the value of the  trusted.glusterfs.dht.linkto 
xattr is different on the one of the bricks of the replica set for some of the 
files(Ravi, any idea why ?)

---------T 2 root root 0 May 18 16:49 
/arbiterAA01/gvAA01/brick1/vaultAA01/support-couplers/CPL-SBS01 
(CPL-SBS01)/D_VOL-b002-i1873-cd.md5

root@PB-WA-AA-00-A:/# getfattr -e hex -m . -d 
/arbiterAA01/gvAA01/brick1/vaultAA01/support-couplers/CPL-SBS01\ 
\(CPL-SBS01\)/D_VOL-b002-i1873-cd.md5
getfattr: Removing leading '/' from absolute path names
# file: arbiterAA01/gvAA01/brick1/vaultAA01/support-couplers/CPL-SBS01 
(CPL-SBS01)/D_VOL-b002-i1873-cd.md5
trusted.gfid=0xfc31c380697a4c70b6af1af35822e519
trusted.glusterfs.dht.linkto=0x6776414130312d726561646469722d61686561642d3100

This value is "gvAA01-readdir-ahead-1"



---------T 2 root root 0 May 18 16:49 
/brick1/gvAA01/brick/vaultAA01/support-couplers/CPL-SBS01 
(CPL-SBS01)/D_VOL-b002-i1873-cd.md5

root@PB-WA-AA-01-B:/# getfattr -e hex -m . -d 
/brick1/gvAA01/brick/vaultAA01/support-couplers/CPL-SBS01\ 
\(CPL-SBS01\)/D_VOL-b002-i1873-cd.md5
getfattr: Removing leading '/' from absolute path names
# file: brick1/gvAA01/brick/vaultAA01/support-couplers/CPL-SBS01 
(CPL-SBS01)/D_VOL-b002-i1873-cd.md5
trusted.gfid=0xfc31c380697a4c70b6af1af35822e519
trusted.glusterfs.dht.linkto=0x6776414130312d726561646469722d61686561642d3100

This value is "gvAA01-readdir-ahead-1"



---------T 2 root root 0 May 30 14:25 
/brick1/gvAA01/brick/vaultAA01/support-couplers/CPL-SBS01 
(CPL-SBS01)/D_VOL-b002-i1873-cd.md5

root@PB-WA-AA-02-B:/# getfattr -e hex -m . -d 
/brick1/gvAA01/brick/vaultAA01/support-couplers/CPL-SBS01\ 
\(CPL-SBS01\)/D_VOL-b002-i1873-cd.md5
getfattr: Removing leading '/' from absolute path names
# file: brick1/gvAA01/brick/vaultAA01/support-couplers/CPL-SBS01 
(CPL-SBS01)/D_VOL-b002-i1873-cd.md5
trusted.afr.dirty=0x000000000000000000000000
trusted.bit-rot.version=0x020000000000000058df0ab7000710ee
trusted.gfid=0xfc31c380697a4c70b6af1af35822e519
trusted.glusterfs.dht.linkto=0x6776414130312d7265706c69636174652d3100

This value is "gvAA01-replicate-1"


[1] http://lists.gluster.org/pipermail/gluster-users/2017-March/030254.html
[2] https://bugzilla.redhat.com/show_bug.cgi?id=1435942

On 30 May 2017 at 14:20, Joshua Coyle 
<[email protected]<mailto:[email protected]>> wrote:


[Probax]

Joshua Coyle


P

1300 885 117

E

[email protected]<mailto:[email protected]>

W

probax.io<http://www.probax.io/>


A

QV1 Perth,


Level 33/250 St Georges Tce,


Perth WA 6000



smart safe local cloud




From: Joshua Coyle
Sent: Tuesday, May 30, 2017 3:27 PM
To: '[email protected]<mailto:[email protected]>' 
<[email protected]<mailto:[email protected]>>
Subject: ATTN: nbalacha IRC - Gluster - BlackoutWNCT requested info for 0byte 
file issue

Hey nbalacha,

Please find the requested information attached for the issue being discussed in 
IRC.

If you need any further info, please let me know.

Thanks,

BlackoutWNCT
[Probax]

Joshua Coyle


P

1300 885 117

E

[email protected]<mailto:[email protected]>

W

probax.io<http://www.probax.io/>


A

QV1 Perth,


Level 33/250 St Georges Tce,


Perth WA 6000



smart safe local cloud





_______________________________________________
Gluster-users mailing list
[email protected]<mailto:[email protected]>
http://lists.gluster.org/mailman/listinfo/gluster-users

_______________________________________________
Gluster-users mailing list
[email protected]
http://lists.gluster.org/mailman/listinfo/gluster-users

Reply via email to