I think it's a very good suggestion, I have faced this issue too.
I think we should it now before we get used to of the current process :)
---
Ashish
- Original Message -
From: "Xavi Hernandez"
To: "gluster-devel"
Sent: Thursday, October 15, 2020 6:16:06 PM
Subject: Re:
1. Can I replace master:slave with primary:secondary everywhere in the
code and the CLI? Are there any suggestions for more appropriate
terminology?
>> Other options could be - Leader : follower
2. Is it okay to target the changes to a major release (release-9) and
*not* provide backward
Hi Mauro,
Yes, it will take time to heal these files and time depends on the number of
file/dir you have created and the amount of data you have written while the
bricks were down.
YOu can just run following command and keep observing that the count is
changing or not -
gluster volume
Hi All,
Today, we had Gluster Community Meeting and the minutes of meeting can be found
on following link -
https://github.com/gluster/community/blob/master/meetings/2019-07-09-Community_meeting.md
---
Ashish
___
Community Meeting Calendar:
@gluster.org
ATTENDEE;CN=Ashish Pandey;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TR
UE:mailto:aspan...@redhat.com
ORGANIZER;CN=Ashish Pandey:mailto:aspan...@redhat.com
DTSTART;TZID="Asia/Kolkata":20190709T113000
DTEND;TZID="Asia/Kolkata":20190709T123000
STATUS:CONFIRMED
CLASS:PU
- Original Message -
From: "Xavi Hernandez"
To: "Ashish Pandey"
Cc: "Amar Tumballi Suryanarayan" , "gluster-devel"
Sent: Thursday, May 30, 2019 2:03:54 PM
Subject: Re: [Gluster-devel] Should we enable features.locks-notify.contention
by
Hi,
While we send a mail on gluster-devel or gluster-user mailing list, following
content gets auto generated and placed at the end of mail.
Gluster-users mailing list
gluster-us...@gluster.org
https://lists.gluster.org/mailman/listinfo/gluster-users
Gluster-devel mailing list
s value and what should be the default value of this
option?
---
Ashish
- Original Message -
From: "Xavi Hernandez"
To: "gluster-devel"
Cc: "Pranith Kumar Karampuri" , "Ashish Pandey"
, "Amar Tumballi"
Sent: Thursday, May 2,
r : Improvements on "heal info" command
Hi ,
This sounds nice. I would like to ask if the order is starting from the local
node's bricks first ? (I am talking about --brick=one)
Best Regards,
Strahil Nikolov
On Mar 5, 2019 10:51, Ashish Pandey wrote:
Hi All,
We have o
Hi All,
We have observed and heard from gluster users about the long time "heal info"
command takes.
Even when we all want to know if a gluster volume is healthy or not, it takes
time to list down all the files from all the bricks after which we can be
sure if the volume is healthy or not.
Following is the patch I am working and targeting -
https://review.gluster.org/#/c/glusterfs/+/21933/
It is under review phase and yet to be merged.
--
Ashish
- Original Message -
From: "RAFI KC"
To: "Shyam Ranganathan" , "GlusterFS Maintainers"
, "Gluster Devel"
Sent:
I downloaded logs of regression runs 1077 and 1073 and tried to investigate it.
In both regression ec/bug-1236065.t is hanging on TEST 70 which is trying to
get the online brick count
I can see that in mount/bricks and glusterd logs it has not move forward after
this test.
glusterd.log -
for that.
---
Ashish
- Original Message -
From: "Ashish Pandey"
To: "Shyam Ranganathan"
Cc: "GlusterFS Maintainers" , "Gluster Devel"
Sent: Monday, August 13, 2018 10:54:16 AM
Subject: Re: [Gluster-devel] Master branch lock down: RCA for tests
(ec-14682
RCA - https://lists.gluster.org/pipermail/gluster-devel/2018-August/055167.html
Patch - https://review.gluster.org/#/c/glusterfs/+/20657/ should also fix this
issue.
Checking if we can put extra test to make sure bricks are connected to shd
before heal begin. Will send a patch for that.
I think the problem with this failure is the same which Shyam suspected for
other EC failure.
Connection to bricks are not being setup after killing bricks and starting
volume using force.
./tests/basic/ec/ec-1468261.t
-
Failure reported -
23:03:05 ok 34,
It is disappointing to see the limitation being put by Nvidia on low cost GPU
usage on data centers.
https://www.theregister.co.uk/2018/01/03/nvidia_server_gpus/
We thought of providing an option in glusterfs by which we can control if we
want to use GPU or not.
So, the concern of gluster
I have updated the comment.
Thanks!!!
---
Ashish
- Original Message -
From: "Shyam Ranganathan" <srang...@redhat.com>
To: "Ashish Pandey" <aspan...@redhat.com>
Cc: "Gluster Devel" <gluster-devel@gluster.org>
Sent: Thursday, Jan
Hi,
We have been thinking of exploiting GPU capabilities to enhance performance of
glusterfs. We would like to know others thoughts on this.
In EC, we have been doing CPU intensive computations to encode and decode data
before writing and reading. This requires a lot of CPU cycles and we have
gluster.org>, "Xavi Hernandez"
<jaher...@redhat.com>, "Ashish Pandey" <aspan...@redhat.com>
Sent: Monday, November 6, 2017 6:35:24 PM
Subject: Regression failure : /tests/basic/ec/ec-1468261.t
Can someone take a look at this?
The run was aborted (
https://
endra Gowdappa" <rgowd...@redhat.com>
To: "Ashish Pandey" <aspan...@redhat.com>
Cc: "Pranith Kumar Karampuri" <pkara...@redhat.com>, "Xavier Hernandez"
<xhernan...@datalab.es>, "Gluster Devel" <gluster-devel@gluster.org>
Sent:
Hi,
The issue you are seeing is a little complex one but information you have
provided is very less.
- Volume info
- Volume status?
- What kind of IO is going on?
- Any brick is down or not?
- Snapshot of Top command.
- Anything you are seeing in glustershd or mount logs or bricks logs?
Hi Nigel,
As Pranith has already mentioned, we are getting different gfid's in loc and
loc->inode.
It looks like issue with DHT. If a re validate fails for gfid, a fresh look up
should be done.
I don't know if it is related or not but a similar bug was fixed by Pranith
I think it is a good Idea.
May be we can add more enhancement in this xlator to improve things in future.
- Original Message -
From: "Pranith Kumar Karampuri" <pkara...@redhat.com>
To: "Ashish Pandey" <aspan...@redhat.com>
Cc: "Xavier Hernand
Hi,
There are some code changes in EC which is impacting response time of gluster v
heal info
I have sent following patch to initiate the discussion on this and to
understand why this code change was done.
https://review.gluster.org/#/c/17606/1
ec: Increase
Ok,
I will check if this is catching the data corruption or not after modifying the
code in EC.
Initially it was not doing so.
- Original Message -
From: "Atin Mukherjee" <amukh...@redhat.com>
To: "Ashish Pandey" <aspan...@redhat.com>
Cc
are trying to kill a brick and starting it using command line.
I think that is what actually failing.
In multiplexing, can we do it? Or is there some other way of doing the same
thing?
Ashish
- Original Message -
From: "Atin Mukherjee" <amukh...@redhat.com>
To
Please note the bug in fio https://github.com/axboe/fio/issues/376 which is
actually impacting performance in case of EC volume.
I am not sure if this would be relevant in your case but thought to mention it.
Ashish
- Original Message -
From: "Manoj Pillai"
To:
If the data is written on minimum number of brick, heal will take place on
failed brick only.
Data will be read from good bricks, encoding will happen and the fragment on
the failed brick will be written only.
- Original Message -
From: "jayakrishnan mm"
- Original Message -
From: "Atin Mukherjee"
To: "Raghavendra Talur" , gluster-devel@gluster.org,
gluster-us...@gluster.org
Sent: Thursday, March 16, 2017 4:22:41 PM
Subject: Re: [Gluster-devel] [Gluster-users] Proposal to deprecate
Xavi,
shd has been disabled in this test on line number 12 and we have also disabled
client side heal.
So, no body is going to try to heal it.
Ashish
- Original Message -
From: "Atin Mukherjee" <amukh...@redhat.com>
To: "Ashish Pandey" <aspan
ppa" <rgowd...@redhat.com>
To: "Nithya Balachandran" <nbala...@redhat.com>
Cc: "Gluster Devel" <gluster-devel@gluster.org>, "Pranith Kumar Karampuri"
<pkara...@redhat.com>, "Ashish Pandey" <aspan...@redhat.com>
Sent:
That means ec is not getting correct trusted.ec.config xattr from minimum
number of bricks.
1 - Did you see any error on client side while accessing any file?
2 - If yes, check the file xattr's from all the bricks for such files.
It is too less information to find out the cause. If [1] is
Hi All,
We have been seeing an issue where re balancing symbolic links leads to an
assertion failure in EC volume.
The root cause of this is that while migrating symbolic links to other sub
volume, it creates a link file (with attributes .T) .
This file is a regular file.
Now,
Hi All,
On EC volume, we have been seeing an interesting bug caused by fine race
between rmdir and inodelk which leads to EIO error.
Pranith, Xavi and I had a discussion on this and have some possible solution.
Your inputs are required on this bug and its possible solution.
1 - Consider
Hi,
Please review the following patch for EC-
http://review.gluster.org/#/c/13733/
Ashish
___
Gluster-devel mailing list
Gluster-devel@gluster.org
http://www.gluster.org/mailman/listinfo/gluster-devel
As Susant and Atin suggested, I cleaned everything and did installation from
scratch and it is working now.
- Original Message -
From: "Nigel Babu" <nig...@redhat.com>
To: "Ashish Pandey" <aspan...@redhat.com>
Cc: "Manikandan Selvaganesh&q
Hi,
I am trying to build latest code on my laptop and it is giving compilation
error -
CC cli-rl.o
CC cli-cmd-global.o
CC cli-cmd-volume.o
cli-cmd-volume.c: In function ‘cli_cmd_quota_cbk’:
cli-cmd-volume.c:1712:35: error: ‘EVENT_QUOTA_ENABLE’ undeclared (first use in
this function)
Hi All,
I have modified the code for volume file generation to support decompounder
translator.
Please review this patch and provide me your comments/suggestion.
http://review.gluster.org/#/c/13968/
Ashish
___
Gluster-devel mailing list
Hi Jeff,
Where can we find the core dump?
---
Ashish
- Original Message -
From: "Pranith Kumar Karampuri" <pkara...@redhat.com>
To: "Jeff Darcy" <jda...@redhat.com>
Cc: "Gluster Devel" <gluster-devel@gluster.org>, "Ashish Pan
force" will do the same.
Regards,
Ashish
- Original Message -
From: "Serkan Çoban" <cobanser...@gmail.com>
To: "Ashish Pandey" <aspan...@redhat.com>
Cc: "Gluster Users" <gluster-us...@gluster.org>, "Gluster Devel"
&
d to
send statedump of all the bricks..
- Original Message -
From: "Serkan Çoban" <cobanser...@gmail.com>
To: "Ashish Pandey" <aspan...@redhat.com>
Cc: "Gluster Users" <gluster-us...@gluster.org>, "Gluster Devel"
<gluster-d
Hi Serkan,
Could you also provide us the statedump of all the brick processes and clients?
Commands to generate statedumps for brick processes/nfs server/quotad
For bricks: gluster volume statedump
For nfs server: gluster volume statedump nfs
We can find the directory where statedump
/statedump.md
Ashish
- Original Message -
From: "Serkan Çoban" <cobanser...@gmail.com>
To: "Ashish Pandey" <aspan...@redhat.com>
Cc: "Gluster Users" <gluster-us...@gluster.org>, "Gluster Devel"
<gluster-devel@gluster.org>
I think this is the statesump of only one brick.
We would required statedump from all the bricks and client process in case of
fuse or nfs process if it is mounted through nfs.
Ashish
- Original Message -
From: "Serkan Çoban" <cobanser...@gmail.com>
To
Hi Xavi,
I think for Systematic erasure coded volume you are going to take fragment size
of 512 Bytes.
Will there be any CLI option to configure this block size?
We were having a discussion and Manoj was suggesting to have this option which
might improve performance for some workload.
For
45 matches
Mail list logo