Re: Rebalance failed on Distributed Disperse volume based on 3.12.14 version

[Mauro Tridici <mauro.tridici@xxxxxxx>]

Dear Ashish,

thank you very much.

I will wait for Nithya and DHT team opinion.

I think I will follow your suggestion changing the names of the new bricks.

Unfortunately, I think that I can’t change the names of the old ones, doesn’t it?!

Mauro

Il giorno 01 ott 2018, alle ore 12:35, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

Hi Mauro,

My comments are inline.

--

Ashish

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "Gluster Users" <gluster-users@xxxxxxxxxxx>
Sent: Monday, October 1, 2018 3:35:26 PM
Subject: Re: Rebalance failed on Distributed Disperse volume        based on 3.12.14 version

Good morning Ashish,

your explanations are always very useful, thank you very much: I will remember these suggestions for any future needs.

Anyway, during the week-end, the remove-brick procedures ended successfully and we were able to free up all bricks defined on server s04, s05 and 6 bricks of 12 on server s06.

So, we can say that, thanks to your suggestions, we are about to complete this first phase (removing of all bricks defined on s04, s05 and s06 servers).

I really appreciated your support. 

Now I have a last question (I hope): after remove-brick commit I noticed that some data remain on each brick (about 1.2GB of data).

Please, take a look to the “df-h_on_s04_s05_s06.txt”.

The situation is almost the same on all 3 servers mentioned above: a long list of directories names and some files that are still on the brick, but respective size is 0.

Examples:

a lot of empty directories on /gluster/mnt*/brick/.glusterfs

8 /gluster/mnt2/brick/.glusterfs/b7/1b

0 /gluster/mnt2/brick/.glusterfs/b7/ee/b7ee94a5-a77c-4c02-85a5-085992840c83

0 /gluster/mnt2/brick/.glusterfs/b7/ee/b7ee85d4-ce48-43a7-a89a-69c728ee8273

some empty files in directories in /gluster/mnt*/brick/*

[root@s04 ~]# cd /gluster/mnt1/brick/

[root@s04 brick]# ls -l

totale 32

drwxr-xr-x 7 root  root  100 11 set 22.14 archive_calypso

[root@s04 brick]# cd archive_calypso/

[root@s04 archive_calypso]# ll

totale 0

drwxr-x--- 3 root 5200 29 11 set 22.13 ans002

drwxr-x--- 3 5104 5100 32 11 set 22.14 ans004

drwxr-x--- 3 4506 4500 31 11 set 22.14 ans006

drwxr-x--- 3 4515 4500 28 11 set 22.14 ans015

drwxr-x--- 4 4321 4300 54 11 set 22.14 ans021

[root@s04 archive_calypso]# du -a *

0 ans002/archive/ans002/HINDCASTS/RUN_ATMWANG_LANSENS/19810501.0/echam5/echam_sf006_198110.01.gz

0 ans002/archive/ans002/HINDCASTS/RUN_ATMWANG_LANSENS/19810501.0/echam5

0 ans002/archive/ans002/HINDCASTS/RUN_ATMWANG_LANSENS/19810501.0

0 ans002/archive/ans002/HINDCASTS/RUN_ATMWANG_LANSENS/19810501.1/echam5/echam_sf006_198105.01.gz

0 ans002/archive/ans002/HINDCASTS/RUN_ATMWANG_LANSENS/19810501.1/echam5/echam_sf006_198109.01.gz

8 ans002/archive/ans002/HINDCASTS/RUN_ATMWANG_LANSENS/19810501.1/echam5

What we have to do with this data? Should I backup this “empty” dirs and files on a different storage before deleting them?

>>>>> As per my understanding, if remove-bricks was successful then this could be deleted. However, I would like to have thoughts from dht team member on this.

@Nithya,

Could you please check if this can be deleted?

-------------------

As soon as all the bricks will be empty, I plan to re-add the new bricks using the following commands:

gluster peer detach s04

gluster peer detach s05

gluster peer detach s06

gluster peer probe s04

gluster peer probe s05

gluster peer probe s06

gluster volume add-brick tier2 s04-stg:/gluster/mnt1/brick s05-stg:/gluster/mnt1/brick s06-stg:/gluster/mnt1/brick s04-stg:/gluster/mnt2/brick s05-stg:/gluster/mnt2/brick s06-stg:/gluster/mnt2/brick s04-stg:/gluster/mnt3/brick s05-stg:/gluster/mnt3/brick s06-stg:/gluster/mnt3/brick s04-stg:/gluster/mnt4/brick s05-stg:/gluster/mnt4/brick s06-stg:/gluster/mnt4/brick s04-stg:/gluster/mnt5/brick s05-stg:/gluster/mnt5/brick s06-stg:/gluster/mnt5/brick s04-stg:/gluster/mnt6/brick s05-stg:/gluster/mnt6/brick s06-stg:/gluster/mnt6/brick s04-stg:/gluster/mnt7/brick s05-stg:/gluster/mnt7/brick s06-stg:/gluster/mnt7/brick s04-stg:/gluster/mnt8/brick s05-stg:/gluster/mnt8/brick s06-stg:/gluster/mnt8/brick s04-stg:/gluster/mnt9/brick s05-stg:/gluster/mnt9/brick s06-stg:/gluster/mnt9/brick s04-stg:/gluster/mnt10/brick s05-stg:/gluster/mnt10/brick s06-stg:/gluster/mnt10/brick s04-stg:/gluster/mnt11/brick s05-stg:/gluster/mnt11/brick s06-stg:/gluster/mnt11/brick s04-stg:/gluster/mnt12/brick s05-stg:/gluster/mnt12/brick s06-stg:/gluster/mnt12/brick force

>>> This command looks good to me. You have given brick path from s04 to s06 one by one which is right thing to do.

However, I would like you to give  more meaningful name to bricks associated to one ec subvolume. This will help you in future to find out which brick belongs to which ec sub volume.

For example:

gluster volume add-brick tier2

 

s04-stg:/gluster/mnt1/brick-13

s05-stg:/gluster/mnt1/brick-13

s06-stg:/gluster/mnt1/brick-13

s04-stg:/gluster/mnt2/brick-13

s05-stg:/gluster/mnt2/brick-13

s06-stg:/gluster/mnt2/brick-13

 

-13 will indicate that these bricks belongs to 13th ec subvol. You can give any other name also.

s04-stg:/gluster/mnt3/brick-14

s05-stg:/gluster/mnt3/brick-14

s06-stg:/gluster/mnt3/brick-14

s04-stg:/gluster/mnt4/brick-14

s05-stg:/gluster/mnt4/brick-14

s06-stg:/gluster/mnt4/brick-14

gluster volume rebalance tier2 fix-layout start

gluster volume rebalance tier2 start

>>> This looks fine.

From your point of view, are they the right commands to close this repairing task?

Thank you very much for your help.

Regards,

Mauro

Il giorno 01 ott 2018, alle ore 09:17, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

Ohh!! It is because brick-multiplexing is "ON" on your setup. Not sure if it is by default ON for 3.12.14  or not.

See "cluster.brick-multiplex: on" in gluster v <volname> info

If brick multiplexing is ON, you will see only one process running for all the bricks on a Node.

So we have to do following step to  kill any one brick on a node.

Steps to kill a brick when multiplex is on  -

Step - 1 

Find unix domain_socket of the process on a node.

Run "ps -aef | grep glusterfsd" on a node. Example :

This is on my machine when I have all the bricks on same machine

[root@apandey glusterfs]# ps -aef | grep glusterfsd | grep -v mnt
root     28311     1  0 11:16 ?        00:00:06 /usr/local/sbin/glusterfsd -s apandey --volfile-id vol.apandey.home-apandey-bricks-gluster-vol-1 -p /var/run/gluster/vols/vol/apandey-home-apandey-bricks-gluster-vol-1.pid -S /var/run/gluster/1259033d2ff4f4e5.socket --brick-name /home/apandey/bricks/gluster/vol-1 -l /var/log/glusterfs/bricks/home-apandey-bricks-gluster-vol-1.log --xlator-option *-posix.glusterd-uuid=61b4524c-ccf3-4219-aaff-b3497ac6dd24 --process-name brick --brick-port 49158 --xlator-option vol-server.listen-port=49158

Here, /var/run/gluster/1259033d2ff4f4e5.socket is the unix domain socket

Step - 2

Run following command to kill a brick on the same node -

gf_attach -d <unix domain_socket> brick_path_on_that_node

Example:

gf_attach -d /var/run/gluster/1259033d2ff4f4e5.socket  /home/apandey/bricks/gluster/vol-6

Status of volume: vol
Gluster process                             TCP Port  RDMA Port  Online  Pid
------------------------------------------------------------------------------
Brick apandey:/home/apandey/bricks/gluster/
vol-1                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-2                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-3                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-4                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-5                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-6                                       49158     0          Y       28311
Self-heal Daemon on localhost               N/A       N/A        Y       29787
 
Task Status of Volume vol
------------------------------------------------------------------------------
There are no active volume tasks
 
[root@apandey glusterfs]#
[root@apandey glusterfs]#
[root@apandey glusterfs]# gf_attach -d /var/run/gluster/1259033d2ff4f4e5.socket /home/apandey/bricks/gluster/vol-6
OK
[root@apandey glusterfs]# gluster v status
Status of volume: vol
Gluster process                             TCP Port  RDMA Port  Online  Pid
------------------------------------------------------------------------------
Brick apandey:/home/apandey/bricks/gluster/
vol-1                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-2                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-3                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-4                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-5                                       49158     0          Y       28311
Brick apandey:/home/apandey/bricks/gluster/
vol-6                                       N/A       N/A        N       N/A  
Self-heal Daemon on localhost               N/A       N/A        Y       29787
 
Task Status of Volume vol
------------------------------------------------------------------------------
There are no active volume tasks

To start a brick we just need to start volume using "force"

gluster v start <volname> force

----

Ashish

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "Gluster Users" <gluster-users@xxxxxxxxxxx>
Sent: Friday, September 28, 2018 9:25:53 PM
Subject: Re: Rebalance failed on Distributed Disperse volume        based on 3.12.14 version

I asked you how to detect the PID of a specific brick because I see that more than one brick has the same PID (also on my virtual env).

If I kill one of them I risk to kill some other brick. Is it normal?

[root@s01 ~]# gluster vol status

Status of volume: tier2

Gluster process                             TCP Port  RDMA Port  Online  Pid

------------------------------------------------------------------------------

Brick s01-stg:/gluster/mnt1/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt1/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt1/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt2/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt2/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt2/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt3/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt3/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt3/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt4/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt4/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt4/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt5/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt5/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt5/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt6/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt6/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt6/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt7/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt7/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt7/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt8/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt8/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt8/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt9/brick           49153     0          Y       3956 

Brick s02-stg:/gluster/mnt9/brick           49153     0          Y       3956 

Brick s03-stg:/gluster/mnt9/brick           49153     0          Y       3953 

Brick s01-stg:/gluster/mnt10/brick          49153     0          Y       3956 

Brick s02-stg:/gluster/mnt10/brick          49153     0          Y       3956 

Brick s03-stg:/gluster/mnt10/brick          49153     0          Y       3953 

Brick s01-stg:/gluster/mnt11/brick          49153     0          Y       3956 

Brick s02-stg:/gluster/mnt11/brick          49153     0          Y       3956 

Brick s03-stg:/gluster/mnt11/brick          49153     0          Y       3953 

Brick s01-stg:/gluster/mnt12/brick          49153     0          Y       3956 

Brick s02-stg:/gluster/mnt12/brick          49153     0          Y       3956 

Brick s03-stg:/gluster/mnt12/brick          49153     0          Y       3953 

Brick s04-stg:/gluster/mnt1/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt2/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt3/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt4/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt5/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt6/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt7/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt8/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt9/brick           49153     0          Y       3433 

Brick s04-stg:/gluster/mnt10/brick          49153     0          Y       3433 

Brick s04-stg:/gluster/mnt11/brick          49153     0          Y       3433 

Brick s04-stg:/gluster/mnt12/brick          49153     0          Y       3433 

Brick s05-stg:/gluster/mnt1/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt2/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt3/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt4/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt5/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt6/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt7/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt8/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt9/brick           49153     0          Y       3709 

Brick s05-stg:/gluster/mnt10/brick          49153     0          Y       3709 

Brick s05-stg:/gluster/mnt11/brick          49153     0          Y       3709 

Brick s05-stg:/gluster/mnt12/brick          49153     0          Y       3709 

Brick s06-stg:/gluster/mnt1/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt2/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt3/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt4/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt5/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt6/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt7/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt8/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt9/brick           49153     0          Y       3644 

Brick s06-stg:/gluster/mnt10/brick          49153     0          Y       3644 

Brick s06-stg:/gluster/mnt11/brick          49153     0          Y       3644 

Brick s06-stg:/gluster/mnt12/brick          49153     0          Y       3644 

Self-heal Daemon on localhost               N/A       N/A        Y       79376

Quota Daemon on localhost                   N/A       N/A        Y       79472

Bitrot Daemon on localhost                  N/A       N/A        Y       79485

Scrubber Daemon on localhost                N/A       N/A        Y       79505

Self-heal Daemon on s03-stg                 N/A       N/A        Y       77073

Quota Daemon on s03-stg                     N/A       N/A        Y       77148

Bitrot Daemon on s03-stg                    N/A       N/A        Y       77160

Scrubber Daemon on s03-stg                  N/A       N/A        Y       77191

Self-heal Daemon on s02-stg                 N/A       N/A        Y       80150

Quota Daemon on s02-stg                     N/A       N/A        Y       80226

Bitrot Daemon on s02-stg                    N/A       N/A        Y       80238

Scrubber Daemon on s02-stg                  N/A       N/A        Y       80269

Self-heal Daemon on s04-stg                 N/A       N/A        Y       106815

Quota Daemon on s04-stg                     N/A       N/A        Y       106866

Bitrot Daemon on s04-stg                    N/A       N/A        Y       106878

Scrubber Daemon on s04-stg                  N/A       N/A        Y       106897

Self-heal Daemon on s05-stg                 N/A       N/A        Y       130807

Quota Daemon on s05-stg                     N/A       N/A        Y       130884

Bitrot Daemon on s05-stg                    N/A       N/A        Y       130896

Scrubber Daemon on s05-stg                  N/A       N/A        Y       130927

Self-heal Daemon on s06-stg                 N/A       N/A        Y       157146

Quota Daemon on s06-stg                     N/A       N/A        Y       157239

Bitrot Daemon on s06-stg                    N/A       N/A        Y       157252

Scrubber Daemon on s06-stg                  N/A       N/A        Y       157288

 

Task Status of Volume tier2

------------------------------------------------------------------------------

Task                 : Remove brick        

ID                   : 06ec63bb-a441-4b85-b3cf-ac8e9df4830f

Removed bricks:     

s04-stg:/gluster/mnt1/brick

s04-stg:/gluster/mnt2/brick

s04-stg:/gluster/mnt3/brick

s04-stg:/gluster/mnt4/brick

s04-stg:/gluster/mnt5/brick

s04-stg:/gluster/mnt6/brick

Status               : in progress   

[root@s01 ~]# ps -ef|grep glusterfs

root       3956      1 79 set25 ?        2-14:33:57 /usr/sbin/glusterfsd -s s01-stg --volfile-id tier2.s01-stg.gluster-mnt1-brick -p /var/run/gluster/vols/tier2/s01-stg-gluster-mnt1-brick.pid -S /var/run/gluster/a889b8a21ac2afcbfa0563b9dd4db265.socket --brick-name /gluster/mnt1/brick -l /var/log/glusterfs/bricks/gluster-mnt1-brick.log --xlator-option *-posix.glusterd-uuid=b734b083-4630-4523-9402-05d03565efee --brick-port 49153 --xlator-option tier2-server.listen-port=49153

root      79376      1  0 09:16 ?        00:04:16 /usr/sbin/glusterfs -s localhost --volfile-id gluster/glustershd -p /var/run/gluster/glustershd/glustershd.pid -l /var/log/glusterfs/glustershd.log -S /var/run/gluster/4fab1a27e6ee700b3b9a3b3393ab7445.socket --xlator-option *replicate*.node-uuid=b734b083-4630-4523-9402-05d03565efee

root      79472      1  0 09:16 ?        00:00:42 /usr/sbin/glusterfs -s localhost --volfile-id gluster/quotad -p /var/run/gluster/quotad/quotad.pid -l /var/log/glusterfs/quotad.log -S /var/run/gluster/958ab34799fc58f4dfe20e5732eea70b.socket --xlator-option *replicate*.data-self-heal=off --xlator-option *replicate*.metadata-self-heal=off --xlator-option *replicate*.entry-self-heal=off

root      79485      1  7 09:16 ?        00:40:43 /usr/sbin/glusterfs -s localhost --volfile-id gluster/bitd -p /var/run/gluster/bitd/bitd.pid -l /var/log/glusterfs/bitd.log -S /var/run/gluster/b2ea9da593fae1bc4d94e65aefdbdda9.socket --global-timer-wheel

root      79505      1  0 09:16 ?        00:00:01 /usr/sbin/glusterfs -s localhost --volfile-id gluster/scrub -p /var/run/gluster/scrub/scrub.pid -l /var/logglusterfs/scrub.log -S /var/run/gluster/ee7886cbcf8d2adf261084b608c905d5.socket --global-timer-wheel

root     137362 137225  0 17:53 pts/0    00:00:00 grep --color=auto glusterfs

Il giorno 28 set 2018, alle ore 17:47, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "Gluster Users" <gluster-users@xxxxxxxxxxx>
Sent: Friday, September 28, 2018 9:08:52 PM
Subject: Re: Rebalance failed on Distributed Disperse volume based on 3.12.14 version

Thank you, Ashish.

I will study and try your solution on my virtual env.

How I can detect the process of a brick on gluster server?

Many Thanks,

Mauro

gluster v status <volname> will give you the list of bricks and the respective process id.

Also, you can use "ps aux | grep glusterfs" to see all the processes on a node but I think the above step also do the same.

---

Ashish

Il ven 28 set 2018 16:39 Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "gluster-users" <gluster-users@xxxxxxxxxxx>
Sent: Friday, September 28, 2018 7:08:41 PM
Subject: Re: Rebalance failed on Distributed Disperse volume        based on 3.12.14 version

Dear Ashish,

please excuse me, I'm very sorry for misunderstanding.

Before contacting you during last days, we checked all network devices (switch 10GbE, cables, NICs, servers ports, and so on), operating systems version and settings, network bonding configuration, gluster packages versions, tuning profiles, etc. but everything seems to be ok. The first 3 servers (and volume) operated without problem for one year. After we added the new 3 servers we noticed something wrong.

Fortunately, yesterday you gave me an hand to understand where is (or could be) the problem. 

At this moment, after we re-launched the remove-brick command, it seems that the rebalance is going ahead without errors, but it is only scanning the files.

May be that during the future data movement some errors could appear.

For this reason, it could be useful to know how to proceed in case of a new failure: insist with approach n.1 or change the strategy?

We are thinking to try to complete the running remove-brick procedure and  make a decision based on the outcome.

Question: could we start approach n.2 also after having successfully removed the V1 subvolume?!

>>> Yes, we can do that. My idea is to use replace-brick command.

We will kill "ONLY" one brick process on s06. We will format this brick. Then use replace-brick command to replace brick of a volume on s05 with this formatted brick.

heal will be triggered and data of the respective volume will be placed on this brick.

Now, we can format the brick which got freed up on s05 and replace the brick which we killed on s06 to s05.

During this process, we have to make sure heal completed before trying any other replace/kill brick.

It is tricky but looks doable. Think about it and try to perform it on your virtual environment first before trying on production.

-------

If it is still possible, could you please illustrate the approach n.2 even if I dont have free disks?

I would like to start thinking about it and test it on a virtual environment.

Thank you in advance for your help and patience.

Regards,

Mauro

Il giorno 28 set 2018, alle ore 14:36, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

We could have taken approach -2 even if you did not have free disks. You should have told me why are you
opting Approach-1 or perhaps I should have asked.
I was wondering for approach 1 because sometimes re-balance takes time depending upon the data size.

Anyway, I hope whole setup is stable, I mean it is not in the middle of something which we can not stop.
If free disks are the only concern I will give you some more steps to deal with it and follow the approach 2.

Let me know once you think everything is fine with the system and there is nothing to heal.

---
Ashish

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "gluster-users" <gluster-users@xxxxxxxxxxx>
Sent: Friday, September 28, 2018 4:21:03 PM
Subject: Re: Rebalance failed on Distributed Disperse volume based on 3.12.14 version

Hi Ashish,

as I said in my previous message, we adopted the first approach you suggested (setting network.ping-timeout option to 0).

This choice was due to the absence of empty brick to be used as indicated in the second approach.

So, we launched remove-brick command on the first subvolume (V1, bricks 1,2,3,4,5,6 on server s04).

Rebalance started moving the data across the other bricks, but, after about 3TB of moved data, rebalance speed slowed down and some transfer errors appeared in the rebalance.log of server s04.

At this point, since remaining 1,8TB need to be moved in order to complete the step, we decided to stop the remove-brick execution and start it again (I hope it doesn’t stop again before complete the rebalance)

Now rebalance is not moving data, it’s only scanning files (please, take a look to the following output)

[root@s01 ~]# gluster volume remove-brick tier2 s04-stg:/gluster/mnt1/brick s04-stg:/gluster/mnt2/brick s04-stg:/gluster/mnt3/brick s04-stg:/gluster/mnt4/brick s04-stg:/gluster/mnt5/brick s04-stg:/gluster/mnt6/brick status

                                    Node Rebalanced-files          size       scanned      failures       skipped               status  run time in h:m:s

                               ---------      -----------   -----------   -----------   -----------   -----------         ------------     --------------

                                 s04-stg                0        0Bytes        182008             0             0          in progress        3:08:09

Estimated time left for rebalance to complete :      442:45:06

If I’m not wrong, remove-brick rebalances entire cluster each time it start.

Is there a way to speed up this procedure? Do you have some other suggestion that, in this particular case, could be useful to reduce errors (I know that they are related to the current volume configuration) and improve rebalance performance avoiding to rebalance the entire cluster?

Thank you in advance,

Mauro

Il giorno 27 set 2018, alle ore 13:14, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

Yes, you can.

If not me others may also reply.

---

Ashish

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "gluster-users" <gluster-users@xxxxxxxxxxx>
Sent: Thursday, September 27, 2018 4:24:12 PM
Subject: Re: Rebalance failed on Distributed Disperse volume        based on 3.12.14 version

Dear Ashish,

I can not thank you enough!

Your procedure and description is very detailed.

I think to follow the first approach after setting network.ping-timeout option to 0 (If I’m not wrong “0" means “infinite”...I noticed that this value reduced rebalance errors).

After the fix I will set network.ping-timeout option to default value.

Could I contact you again if I need some kind of suggestion?

Thank you very much again.

Have a good day,

Mauro

Il giorno 27 set 2018, alle ore 12:38, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

Hi Mauro,

We can divide the 36 newly added bricks into 6 set of 6 bricks each starting from brick37.

That means, there are 6 ec subvolumes and we have to deal with one sub volume at a time.

I have named it V1 to V6.

Problem:

Take the case of V1.

The best configuration/setup would be to have all the 6 bricks of V1 on 6 different nodes.

However, in your case you have added 3 new nodes. So, at least we should have 2 bricks on 3 different newly added nodes.

This way, in 4+2 EC configuration, even if one node goes down you will have 4 other bricks of that volume and the data on that volume would be accessible.

In current setup if s04-stg goes down, you will loose all the data on V1 and V2 as all the bricks will be down. We want to avoid and correct it.

Now, we can have two approach to correct/modify this setup.

Approach 1

We have to remove all the newly added bricks in a set of 6 bricks. This will trigger re- balance and move whole data to other sub volumes.

Repeat the above step and then once all the bricks are removed, add those bricks again in a set of 6 bricks, this time have 2 bricks from each of the 3 newly added Nodes.

While this is a valid and working approach, I personally think that this will take long time and also require lot of movement of data.

Approach 2

In this approach we can use the heal process. We have to deal with all the volumes (V1 to V6) one by one. Following are the steps for V1-

Step 1 -

Use replace-brick command to move following bricks on s05-stg node one by one (heal should be completed after every replace brick command)

Brick39: s04-stg:/gluster/mnt3/brick to s05-stg/<brick which is free>

Brick40: s04-stg:/gluster/mnt4/brick to s05-stg/<other brick which is free>

Command :

gluster v replace-brick <volname>  s04-stg:/gluster/mnt3/brick     s05-stg:/<brick which is free>    commit force

Try to give names to the bricks so that you can identify which 6 bricks belongs to same ec subvolume

Use replace-brick command to move following bricks on s06-stg node one by one

Brick41: s04-stg:/gluster/mnt5/brick to  s06-stg/<brick which is free>

Brick42: s04-stg:/gluster/mnt6/brick to  s06-stg/<other brick which is free>

Step 2 - After, every replace-brick command, you have to wait for heal to be completed.

check "gluster v heal <volname> info " if it shows any entry you have to wait for it to be completed.

After successful step 1 and step 2, setup for sub volume V1 will be fixed. The same steps you have to perform for other volumes. Only thing is that

the nodes would be different on which you have to move the bricks.

V1

 

Brick37: s04-stg:/gluster/mnt1/brick

Brick38: s04-stg:/gluster/mnt2/brick

Brick39: s04-stg:/gluster/mnt3/brick

Brick40: s04-stg:/gluster/mnt4/brick

Brick41: s04-stg:/gluster/mnt5/brick

Brick42: s04-stg:/gluster/mnt6/brick

 

V2

Brick43: s04-stg:/gluster/mnt7/brick

Brick44: s04-stg:/gluster/mnt8/brick

Brick45: s04-stg:/gluster/mnt9/brick

Brick46: s04-stg:/gluster/mnt10/brick

Brick47: s04-stg:/gluster/mnt11/brick

Brick48: s04-stg:/gluster/mnt12/brick

 

V3

Brick49: s05-stg:/gluster/mnt1/brick

Brick50: s05-stg:/gluster/mnt2/brick

Brick51: s05-stg:/gluster/mnt3/brick

Brick52: s05-stg:/gluster/mnt4/brick

Brick53: s05-stg:/gluster/mnt5/brick

Brick54: s05-stg:/gluster/mnt6/brick

 

V4

Brick55: s05-stg:/gluster/mnt7/brick

Brick56: s05-stg:/gluster/mnt8/brick

Brick57: s05-stg:/gluster/mnt9/brick

Brick58: s05-stg:/gluster/mnt10/brick

Brick59: s05-stg:/gluster/mnt11/brick

Brick60: s05-stg:/gluster/mnt12/brick

 

V5

Brick61: s06-stg:/gluster/mnt1/brick

Brick62: s06-stg:/gluster/mnt2/brick

Brick63: s06-stg:/gluster/mnt3/brick

Brick64: s06-stg:/gluster/mnt4/brick

Brick65: s06-stg:/gluster/mnt5/brick

Brick66: s06-stg:/gluster/mnt6/brick

 

V6

Brick67: s06-stg:/gluster/mnt7/brick

Brick68: s06-stg:/gluster/mnt8/brick

Brick69: s06-stg:/gluster/mnt9/brick

Brick70: s06-stg:/gluster/mnt10/brick

Brick71: s06-stg:/gluster/mnt11/brick

Brick72: s06-stg:/gluster/mnt12/brick

 

Just a note that these steps need movement of data.

Be careful while performing these steps and do one replace brick at a time and only after heal completion go to next.

Let me know if you have any issues.

---

Ashish

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "gluster-users" <gluster-users@xxxxxxxxxxx>
Sent: Thursday, September 27, 2018 4:03:04 PM
Subject: Re: Rebalance failed on Distributed Disperse volume        based on 3.12.14 version

Dear Ashish,

I hope I don’t disturb you so much, but I would like to ask you if you had some time to dedicate to our problem.

Please, forgive my insistence.

Thank you in advance,

Mauro

Il giorno 26 set 2018, alle ore 19:56, Mauro Tridici <mauro.tridici@xxxxxxx> ha scritto:

Hi Ashish,

sure, no problem! We are a little bit worried, but we can wait  :-)

Thank you very much for your support and your availability.

Regards,

Mauro

Il giorno 26 set 2018, alle ore 19:33, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

Hi Mauro,

Yes, I can provide you step by step procedure to correct it.

Is it fine If i provide you the steps tomorrow as it is quite late over here and I don't want to miss anything in hurry?

---

Ashish

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "gluster-users" <gluster-users@xxxxxxxxxxx>
Sent: Wednesday, September 26, 2018 6:54:19 PM
Subject: Re: Rebalance failed on Distributed Disperse volume        based on 3.12.14 version

Hi Ashish,

in attachment you can find the rebalance log file and the last updated brick log file (the other files in /var/log/glusterfs/bricks directory seem to be too old).

I just stopped the running rebalance (as you can see at the bottom of the rebalance log file).

So, if exists a safe procedure to correct the problem I would like execute it.

I don’t know if I can ask you it, but, if it is possible, could you please describe me step by step the right procedure to remove the newly added bricks without losing the data that have been already rebalanced?

The following outputs show the result of “df -h” command executed on one of the first 3 nodes (s01, s02, s03) already existing  and on one of the last 3 nodes (s04, s05, s06) added recently.

[root@s06 bricks]# df -h

File system                          Dim. Usati Dispon. Uso% Montato su

/dev/mapper/cl_s06-root              100G  2,1G     98G   3% /

devtmpfs                              32G     0     32G   0% /dev

tmpfs                                 32G  4,0K     32G   1% /dev/shm

tmpfs                                 32G   26M     32G   1% /run

tmpfs                                 32G     0     32G   0% /sys/fs/cgroup

/dev/mapper/cl_s06-var               100G  2,0G     99G   2% /var

/dev/mapper/cl_s06-gluster           100G   33M    100G   1% /gluster

/dev/sda1                           1014M  152M    863M  15% /boot

/dev/mapper/gluster_vgd-gluster_lvd  9,0T  807G    8,3T   9% /gluster/mnt3

/dev/mapper/gluster_vgg-gluster_lvg  9,0T  807G    8,3T   9% /gluster/mnt6

/dev/mapper/gluster_vgc-gluster_lvc  9,0T  807G    8,3T   9% /gluster/mnt2

/dev/mapper/gluster_vge-gluster_lve  9,0T  807G    8,3T   9% /gluster/mnt4

/dev/mapper/gluster_vgj-gluster_lvj  9,0T  887G    8,2T  10% /gluster/mnt9

/dev/mapper/gluster_vgb-gluster_lvb  9,0T  807G    8,3T   9% /gluster/mnt1

/dev/mapper/gluster_vgh-gluster_lvh  9,0T  887G    8,2T  10% /gluster/mnt7

/dev/mapper/gluster_vgf-gluster_lvf  9,0T  807G    8,3T   9% /gluster/mnt5

/dev/mapper/gluster_vgi-gluster_lvi  9,0T  887G    8,2T  10% /gluster/mnt8

/dev/mapper/gluster_vgl-gluster_lvl  9,0T  887G    8,2T  10% /gluster/mnt11

/dev/mapper/gluster_vgk-gluster_lvk  9,0T  887G    8,2T  10% /gluster/mnt10

/dev/mapper/gluster_vgm-gluster_lvm  9,0T  887G    8,2T  10% /gluster/mnt12

tmpfs                                6,3G     0    6,3G   0% /run/user/0

[root@s01 ~]# df -h

File system                          Dim. Usati Dispon. Uso% Montato su

/dev/mapper/cl_s01-root              100G  5,3G     95G   6% /

devtmpfs                              32G     0     32G   0% /dev

tmpfs                                 32G   39M     32G   1% /dev/shm

tmpfs                                 32G   26M     32G   1% /run

tmpfs                                 32G     0     32G   0% /sys/fs/cgroup

/dev/mapper/cl_s01-var               100G   11G     90G  11% /var

/dev/md127                          1015M  151M    865M  15% /boot

/dev/mapper/cl_s01-gluster           100G   33M    100G   1% /gluster

/dev/mapper/gluster_vgi-gluster_lvi  9,0T  5,5T    3,6T  61% /gluster/mnt7

/dev/mapper/gluster_vgm-gluster_lvm  9,0T  5,4T    3,6T  61% /gluster/mnt11

/dev/mapper/gluster_vgf-gluster_lvf  9,0T  5,7T    3,4T  63% /gluster/mnt4

/dev/mapper/gluster_vgl-gluster_lvl  9,0T  5,8T    3,3T  64% /gluster/mnt10

/dev/mapper/gluster_vgj-gluster_lvj  9,0T  5,5T    3,6T  61% /gluster/mnt8

/dev/mapper/gluster_vgn-gluster_lvn  9,0T  5,4T    3,6T  61% /gluster/mnt12

/dev/mapper/gluster_vgk-gluster_lvk  9,0T  5,8T    3,3T  64% /gluster/mnt9

/dev/mapper/gluster_vgh-gluster_lvh  9,0T  5,6T    3,5T  63% /gluster/mnt6

/dev/mapper/gluster_vgg-gluster_lvg  9,0T  5,6T    3,5T  63% /gluster/mnt5

/dev/mapper/gluster_vge-gluster_lve  9,0T  5,7T    3,4T  63% /gluster/mnt3

/dev/mapper/gluster_vgc-gluster_lvc  9,0T  5,6T    3,5T  62% /gluster/mnt1

/dev/mapper/gluster_vgd-gluster_lvd  9,0T  5,6T    3,5T  62% /gluster/mnt2

tmpfs                                6,3G     0    6,3G   0% /run/user/0

s01-stg:tier2                        420T  159T    262T  38% /tier2

As you can see, used space value of each brick of the last servers is about 800GB.

Thank you,

Mauro

Il giorno 26 set 2018, alle ore 14:51, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

Hi Mauro,

rebalance and brick logs should be the first thing we should go through.

There is a procedure to correct the configuration/setup but the situation you are in is difficult to follow that procedure.

You should have added the bricks hosted on s04-stg, s05-stg and s06-stg the same way you had the previous configuration.

That means 2 bricks on each node for one subvolume.

The procedure will require a lot of replace bricks which will again need healing and all. In addition to that we have to wait for re-balance to complete.

I would suggest that if whole data has not been rebalanced and if you can stop the rebalance and remove these newly added bricks properly then you should remove these newly added bricks.

After that, add these bricks so that you have 2 bricks of each volume on 3 newly added nodes.

Yes, it is like undoing whole effort but it is better to do it now then facing issues in future when it will be almost impossible to correct these things if you have lots of data.

---

Ashish

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "Ashish Pandey" <aspandey@xxxxxxxxxx>
Cc: "gluster-users" <gluster-users@xxxxxxxxxxx>
Sent: Wednesday, September 26, 2018 5:55:02 PM
Subject: Re: Rebalance failed on Distributed Disperse volume        based on 3.12.14 version

Dear Ashish,

thank you for you answer.

I could provide you the entire log file related to glusterd, glusterfsd and rebalance.

Please, could you indicate which one you need first?

Yes, we added the last 36 bricks after creating vol. Is there a procedure to correct this error? Is it still possible to do it?

Many thanks,

Mauro

Il giorno 26 set 2018, alle ore 14:13, Ashish Pandey <aspandey@xxxxxxxxxx> ha scritto:

I think we don't have enough logs to debug this so I would suggest you to provide more logs/info.

I have also observed that the configuration and setup of your volume is not very efficient.

For example:

Brick37: s04-stg:/gluster/mnt1/brick

Brick38: s04-stg:/gluster/mnt2/brick

Brick39: s04-stg:/gluster/mnt3/brick

Brick40: s04-stg:/gluster/mnt4/brick

Brick41: s04-stg:/gluster/mnt5/brick

Brick42: s04-stg:/gluster/mnt6/brick

Brick43: s04-stg:/gluster/mnt7/brick

Brick44: s04-stg:/gluster/mnt8/brick

Brick45: s04-stg:/gluster/mnt9/brick

Brick46: s04-stg:/gluster/mnt10/brick

Brick47: s04-stg:/gluster/mnt11/brick

Brick48: s04-stg:/gluster/mnt12/brick

These 12 bricks are on same node and the sub volume made up of these bricks will be of same subvolume, which is not good. Same is true for the bricks hosted on s05-stg and s06-stg

I think you have added these bricks after creating vol. The probability of disruption in connection of these bricks will be higher in this case.

---

Ashish

---

From: "Mauro Tridici" <mauro.tridici@xxxxxxx>
To: "gluster-users" <gluster-users@xxxxxxxxxxx>
Sent: Wednesday, September 26, 2018 3:38:35 PM
Subject: Rebalance failed on Distributed Disperse volume        based on 3.12.14 version

Dear All, Dear Nithya,

after upgrading from 3.10.5 version to 3.12.14, I tried to start a rebalance process to distribute data across the bricks, but something goes wrong.

Rebalance failed on different nodes and the time value needed to complete the procedure seems to be very high.

[root@s01 ~]# gluster volume rebalance tier2 status

                                    Node Rebalanced-files          size       scanned      failures       skipped               status  run time in h:m:s

                               ---------      -----------   -----------   -----------   -----------   -----------         ------------     --------------

                               localhost               19       161.6GB           537             2             2          in progress        0:32:23

                                 s02-stg               25       212.7GB           526             5             2          in progress        0:32:25

                                 s03-stg                4        69.1GB           511             0             0          in progress        0:32:25

                                 s04-stg                4      484Bytes         12283             0             3          in progress        0:32:25

                                 s05-stg               23      484Bytes         11049             0            10          in progress        0:32:25

                                 s06-stg                3         1.2GB          8032            11             3               failed        0:17:57

Estimated time left for rebalance to complete :     3601:05:41

volume rebalance: tier2: success

When rebalance processes fail, I can see the following kind of errors in /var/log/glusterfs/tier2-rebalance.log

Error type 1)

[2018-09-26 08:50:19.872575] W [MSGID: 122053] [ec-common.c:269:ec_check_status] 0-tier2-disperse-10: Operation failed on 2 of 6 subvolumes.(up=111111, mask=100111, remaining=

000000, good=100111, bad=011000)

[2018-09-26 08:50:19.901792] W [MSGID: 122053] [ec-common.c:269:ec_check_status] 0-tier2-disperse-11: Operation failed on 1 of 6 subvolumes.(up=111111, mask=111101, remaining=

000000, good=111101, bad=000010)

Error type 2)

[2018-09-26 08:53:31.566836] W [socket.c:600:__socket_rwv] 0-tier2-client-53: readv on 192.168.0.55:49153 failed (Connection reset by peer)

Error type 3)

[2018-09-26 08:57:37.852590] W [MSGID: 122035] [ec-common.c:571:ec_child_select] 0-tier2-disperse-9: Executing operation with some subvolumes unavailable (10)

[2018-09-26 08:57:39.282306] W [MSGID: 122035] [ec-common.c:571:ec_child_select] 0-tier2-disperse-9: Executing operation with some subvolumes unavailable (10)

[2018-09-26 09:02:04.928408] W [MSGID: 109023] [dht-rebalance.c:1013:__dht_check_free_space] 0-tier2-dht: data movement of file {blocks:0 name:(/OPA/archive/historical/dts/MRE

A/Observations/Observations/MREA14/Cs-1/CMCC/raw/CS013.ext)} would result in dst node (tier2-disperse-5:2440190848) having lower disk space than the source node (tier2-dispers

e-11:71373083776).Skipping file.

Error type 4)

W [rpc-clnt-ping.c:223:rpc_clnt_ping_cbk] 0-tier2-client-7: socket disconnected

Error type 5)

[2018-09-26 09:07:42.333720] W [glusterfsd.c:1375:cleanup_and_exit] (-->/lib64/libpthread.so.0(+0x7e25) [0x7f0417e0ee25] -->/usr/sbin/glusterfs(glusterfs_sigwaiter+0xe5) [0x55

90086004b5] -->/usr/sbin/glusterfs(cleanup_and_exit+0x6b) [0x55900860032b] ) 0-: received signum (15), shutting down

Error type 6)

[2018-09-25 08:09:18.340658] C [rpc-clnt-ping.c:166:rpc_clnt_ping_timer_expired] 0-tier2-client-4: server 192.168.0.52:49153 has not responded in the last 42 seconds, disconnecting.

It seems that there are some network or timeout problems, but the network usage/traffic values are not so high.

Do you think that, in my volume configuration, I have to modify some volume options related to thread and/or network parameters?

Could you, please, help me to understand the cause of the problems above?

You can find below our volume info:

(volume is implemented on 6 servers; each server configuration:  2 cpu 10-cores, 64GB RAM, 1 SSD dedicated to the OS, 12 x 10TB HD)

[root@s04 ~]# gluster vol info

 

<div style="margin: 0px; line-height: nor

_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
https://lists.gluster.org/mailman/listinfo/gluster-users

_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
https://lists.gluster.org/mailman/listinfo/gluster-users

-------------------------

Mauro Tridici

Fondazione CMCC

CMCC Supercomputing Center

presso Complesso Ecotekne - Università del Salento -

Strada Prov.le Lecce - Monteroni sn

73100 Lecce  IT

http://www.cmcc.it

mobile: (+39) 327 5630841

email: mauro.tridici@xxxxxxx

https://it.linkedin.com/in/mauro-tridici-5977238b

_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
https://lists.gluster.org/mailman/listinfo/gluster-users