[Gluster-devel] [Gluster-users] remove_me files building up

Strahil Nikolov hunter86_bg at yahoo.com
Wed Jul 5 10:59:14 UTC 2023


Adding Gluster Devel list.
Best Regards,Strahil Nikolov 


Sent from Yahoo Mail for iPhone


On Wednesday, July 5, 2023, 12:41 PM, Liam Smith <liam.smith at ek.co> wrote:

 #yiv4442503694 P {margin-top:0;margin-bottom:0;}Hi Strahil,
This is the output from the commands:
root at uk3-prod-gfs-arb-01:~# du -h -x -d 1 /data/glusterfs/gv1/brick1/brick2.2G    /data/glusterfs/gv1/brick1/brick/.glusterfs24M     /data/glusterfs/gv1/brick1/brick/scalelite-recordings16K     /data/glusterfs/gv1/brick1/brick/mytute18M     /data/glusterfs/gv1/brick1/brick/.shard0       /data/glusterfs/gv1/brick1/brick/.glusterfs-anonymous-inode-d3d1fdec-7df9-4f71-b9fc-660d12c2a0462.3G    /data/glusterfs/gv1/brick1/brick

root at uk3-prod-gfs-arb-01:~# du -h -x -d 1 /data/glusterfs/gv1/brick3/brick11G     /data/glusterfs/gv1/brick3/brick/.glusterfs15M     /data/glusterfs/gv1/brick3/brick/scalelite-recordings460K    /data/glusterfs/gv1/brick3/brick/mytute151M    /data/glusterfs/gv1/brick3/brick/.shard0       /data/glusterfs/gv1/brick3/brick/.glusterfs-anonymous-inode-d3d1fdec-7df9-4f71-b9fc-660d12c2a04611G     /data/glusterfs/gv1/brick3/brick

root at uk3-prod-gfs-arb-01:~# du -h -x -d 1 /data/glusterfs/gv1/brick2/brick12G     /data/glusterfs/gv1/brick2/brick/.glusterfs110M    /data/glusterfs/gv1/brick2/brick/scalelite-recordings3.1M    /data/glusterfs/gv1/brick2/brick/mytute169M    /data/glusterfs/gv1/brick2/brick/.shard0       /data/glusterfs/gv1/brick2/brick/.glusterfs-anonymous-inode-d3d1fdec-7df9-4f71-b9fc-660d12c2a04612G     /data/glusterfs/gv1/brick2/brick
Also, this is the du -sh output for the specific directory that appears to be taking up space on brick 3:
root at uk3-prod-gfs-arb-01:~# du -sh /data/glusterfs/gv1/brick3/brick/.shard/.remove_me/10G     /data/glusterfs/gv1/brick3/brick/.shard/.remove_me/

The gluster package version on all the servers is 11.0, and I believe they were upgraded from 7.2>8.6>11.0; the op.version was only changed after the 11.0 upgrade.
The archival job deletes the files, files shouldn't be overwritten at any point as it's new, unique files being generated everyday.
Thanks,
| 
|   |
| 
| 
| 
| Liam Smith​​​​ |
| Linux Systems Support Engineer, Scholar |

 |

 |

 |   |
| 
|  |

 |

 |

From: Strahil Nikolov <hunter86_bg at yahoo.com>
Sent: 04 July 2023 17:47
To: Liam Smith <liam.smith at ek.co>; gluster-users at gluster.org <gluster-users at gluster.org>
Subject: Re: [Gluster-users] remove_me files building up 
| 
CAUTION: This e-mail originates from outside of Ekco. Do not click links or attachments unless you recognise the sender. 
 |


Thanks for the clarification.
That behaviour is quite weird as arbiter bricks should hold only metadata.
What does the following show on host uk3-prod-gfs-arb-01:
du -h -x -d 1 /data/glusterfs/gv1/brick1/brickdu -h -x -d 1 /data/glusterfs/gv1/brick3/brickdu -h -x -d 1 /data/glusterfs/gv1/brick2/brick

If indeed the shards are taking space - that is a really strange situation.From which version did you upgrade and which one is now ? I assume all gluster TSP members (the servers) have the same version, but it’s nice to double check.
Does the archival job actually deletes the original files after being processed or the workload keeps overriding the existing files ?
Best Regards,Strahil Nikolov 




Sent from Yahoo Mail for iPhone


On Tuesday, July 4, 2023, 6:50 PM, Liam Smith <liam.smith at ek.co> wrote:
 
 
  
 The contents of this email message and any attachments are intended solely for the addressee(s) and may contain confidential and/or privileged information and may be legally protected from disclosure. 
 
 
 
<!--#yiv4442503694 #yiv4442503694x_yiv0069265236 p {margin-top:0;margin-bottom:0;}-->Hi Strahil,
We're using gluster to act as a share for an application to temporarily process and store files, before they're then archived off over night.
The issue we're seeing isn't with the inodes running out of space, but the actual disk space on the arb server running low.
This is the df -h​ output for the bricks on the arb server:/dev/sdd1              15G   12G  3.3G  79% /data/glusterfs/gv1/brick3/dev/sdc1              15G  2.8G   13G  19% /data/glusterfs/gv1/brick1/dev/sde1              15G   14G  1.6G  90% /data/glusterfs/gv1/brick2
And this is the df -hi​ output for the bricks on the arb server:/dev/sdd1              7.5M  2.7M  4.9M   35% /data/glusterfs/gv1/brick3/dev/sdc1              7.5M  643K  6.9M    9% /data/glusterfs/gv1/brick1/dev/sde1              6.1M  3.0M  3.1M   49% /data/glusterfs/gv1/brick2
So the inode usage appears to be fine, but we're seeing that the actual disk usage keeps increasing on the bricks despite it being the arbiter.
The actual issue appears to be that files under /data/glusterfs/gv1/brick3/brick/.shard/.remove_me/​ and/data/glusterfs/gv1/brick2/brick/.shard/.remove_me/​ are being retained, even when the original files are deleted from the data nodes.
For reference, I've attached disk usage graphs for brick 3 over the past two weeks; one is a graph from a data node, the other from the arb.
As you can see, the disk usage of the data node builds throughout the day, but then an archival job clears space down. However, on the arb, we see the disk space increasing in the same sort of trend, but it's never cleared down like the data node.
Hopefully this clarifies the issue, we're a bit confused as to why this is occurring and whether this is actually intended behaviour or potentially a bug, so any advice is greatly appreciated.
Thanks,
| 
|   |
| 
| 
| 
| Liam Smith​​​​ |
| Linux Systems Support Engineer, Scholar |

 |

 |

 |   |
| 


The contents of this email message and any attachments are intended solely for the addressee(s) and may contain confidential and/or privileged information and may be legally protected from disclosure.



|  |

 |

 |

From: Strahil Nikolov <hunter86_bg at yahoo.com>
Sent: 04 July 2023 15:51
To: Liam Smith <liam.smith at ek.co>; gluster-users at gluster.org <gluster-users at gluster.org>
Subject: Re: [Gluster-users] remove_me files building up 
| 
CAUTION: This e-mail originates from outside of Ekco. Do not click links or attachments unless you recognise the sender. 
 |


Hi Liam,
I saw that your XFS uses ‘imaxpct=25’ which for an arbiter brick is a little bit low.
If you have free space on the bricks, increase the maxpct to a bigger value, like:xfs_growfs -m 80 /path/to/brickThat will set 80% of the Filesystem for inodes, which you can verify with df -i /brick/path (compare before and after). This way you won’t run out of inodes in the future.
Of course, always test that on non Prod first.
Are you using the volume for VM disk storage domain ? What is your main workload ?
Best Regards,Strahil Nikolov 




On Tuesday, July 4, 2023, 2:12 PM, Liam Smith <liam.smith at ek.co> wrote:

<!--#yiv4442503694 #yiv4442503694x_yiv0069265236 #yiv4442503694x_yiv0069265236x_yiv8784601153 p {margin-top:0;margin-bottom:0;}-->Hi,
Thanks for your response, please find the xfs_info for each brick on the arbiter below:
root at uk3-prod-gfs-arb-01:~# xfs_info /data/glusterfs/gv1/brick1meta-data=/dev/sdc1              isize=512    agcount=31, agsize=131007 blks         =                       sectsz=512   attr=2, projid32bit=1         =                       crc=1        finobt=1, sparse=1, rmapbt=0         =                       reflink=1data     =                       bsize=4096   blocks=3931899, imaxpct=25         =                       sunit=0      swidth=0 blksnaming   =version 2              bsize=4096   ascii-ci=0, ftype=1log      =internal log           bsize=4096   blocks=2560, version=2         =                       sectsz=512   sunit=0 blks, lazy-count=1realtime =none                   extsz=4096   blocks=0, rtextents=0

root at uk3-prod-gfs-arb-01:~# xfs_info /data/glusterfs/gv1/brick2meta-data=/dev/sde1              isize=512    agcount=13, agsize=327616 blks         =                       sectsz=512   attr=2, projid32bit=1         =                       crc=1        finobt=1, sparse=1, rmapbt=0         =                       reflink=1data     =                       bsize=4096   blocks=3931899, imaxpct=25         =                       sunit=0      swidth=0 blksnaming   =version 2              bsize=4096   ascii-ci=0, ftype=1log      =internal log           bsize=4096   blocks=2560, version=2         =                       sectsz=512   sunit=0 blks, lazy-count=1realtime =none                   extsz=4096   blocks=0, rtextents=0

root at uk3-prod-gfs-arb-01:~# xfs_info /data/glusterfs/gv1/brick3meta-data=/dev/sdd1              isize=512    agcount=13, agsize=327616 blks         =                       sectsz=512   attr=2, projid32bit=1         =                       crc=1        finobt=1, sparse=1, rmapbt=0         =                       reflink=1data     =                       bsize=4096   blocks=3931899, imaxpct=25         =                       sunit=0      swidth=0 blksnaming   =version 2              bsize=4096   ascii-ci=0, ftype=1log      =internal log           bsize=4096   blocks=2560, version=2         =                       sectsz=512   sunit=0 blks, lazy-count=1realtime =none                   extsz=4096   blocks=0, rtextents=0

I've also copied below some df output from the arb server:
root at uk3-prod-gfs-arb-01:~# df -hiFilesystem           Inodes IUsed IFree IUse% Mounted onudev                   992K   473  991K    1% /devtmpfs                  995K   788  994K    1% /run/dev/sda1              768K  105K  664K   14% /tmpfs                  995K     3  995K    1% /dev/shmtmpfs                  995K     4  995K    1% /run/locktmpfs                  995K    18  995K    1% /sys/fs/cgroup/dev/sdb1              128K   113  128K    1% /var/lib/glusterd/dev/sdd1              7.5M  2.6M  5.0M   35% /data/glusterfs/gv1/brick3/dev/sdc1              7.5M  600K  7.0M    8% /data/glusterfs/gv1/brick1/dev/sde1              6.4M  2.9M  3.5M   46% /data/glusterfs/gv1/brick2uk1-prod-gfs-01:/gv1   150M  6.5M  144M    5% /mnt/gfstmpfs                  995K    21  995K    1% /run/user/1004

root at uk3-prod-gfs-arb-01:~# df -hFilesystem            Size  Used Avail Use% Mounted onudev                  3.9G     0  3.9G   0% /devtmpfs                 796M  916K  795M   1% /run/dev/sda1              12G  3.9G  7.3G  35% /tmpfs                 3.9G  8.0K  3.9G   1% /dev/shmtmpfs                 5.0M     0  5.0M   0% /run/locktmpfs                 3.9G     0  3.9G   0% /sys/fs/cgroup/dev/sdb1             2.0G  456K  1.9G   1% /var/lib/glusterd/dev/sdd1              15G   12G  3.5G  78% /data/glusterfs/gv1/brick3/dev/sdc1              15G  2.6G   13G  18% /data/glusterfs/gv1/brick1/dev/sde1              15G   14G  1.8G  89% /data/glusterfs/gv1/brick2uk1-prod-gfs-01:/gv1  300G  139G  162G  47% /mnt/gfstmpfs                 796M     0  796M   0% /run/user/1004

Something I forgot to mention in my initial message is that the opversion was upgraded from 70200 to 100000, which seems as though it could have been a trigger for the issue as well.
Thanks,
| 
|   |
| 
| 
| 
| Liam Smith​​​​ |
| Linux Systems Support Engineer, Scholar |

 |

 |

 |   |
| 
|  |

 |

 |

From: Strahil Nikolov <hunter86_bg at yahoo.com>
Sent: 03 July 2023 18:28
To: Liam Smith <liam.smith at ek.co>; gluster-users at gluster.org <gluster-users at gluster.org>
Subject: Re: [Gluster-users] remove_me files building up 
| 
CAUTION: This e-mail originates from outside of Ekco. Do not click links or attachments unless you recognise the sender. 
 |


Hi,
you mentioned that the arbiter bricks run out of inodes.Are you using XFS ?Can you provide the xfs_info of each brick ?
Best Regards,Strahil Nikolov 



The contents of this email message and any attachments are intended solely for the addressee(s) and may contain confidential and/or privileged information and may be legally protected from disclosure.




On Sat, Jul 1, 2023 at 19:41, Liam Smith<liam.smith at ek.co> wrote:Hi,
We're running a cluster with two data nodes and one arbiter, and have sharding enabled.
We had an issue a while back where one of the server's crashed, we got the server back up and running and ensured that all healing entries cleared, and also increased the server spec (CPU/Mem) as this seemed to be the potential cause.
Since then however, we've seen some strange behaviour, whereby a lot of 'remove_me' files are building up under `/data/glusterfs/gv1/brick2/brick/.shard/.remove_me/` and `/data/glusterfs/gv1/brick3/brick/.shard/.remove_me/`. This is causing the arbiter to run out of space on brick2 and brick3, as the remove_me files are constantly increasing.
brick1 appears to be fine, the disk usage increases throughout the day and drops down in line with the trend of the brick on the data nodes. We see the disk usage increase and drop throughout the day on the data nodes for brick2 and brick3 as well, but while the arbiter follows the same trend of the disk usage increasing, it doesn't drop at any point.
This is the output of some gluster commands, occasional heal entries come and go:


root at uk3-prod-gfs-arb-01:~# gluster volume info gv1
Volume Name: gv1Type: Distributed-ReplicateVolume ID: d3d1fdec-7df9-4f71-b9fc-660d12c2a046Status: StartedSnapshot Count: 0Number of Bricks: 3 x (2 + 1) = 9Transport-type: tcpBricks:Brick1: uk1-prod-gfs-01:/data/glusterfs/gv1/brick1/brickBrick2: uk2-prod-gfs-01:/data/glusterfs/gv1/brick1/brickBrick3: uk3-prod-gfs-arb-01:/data/glusterfs/gv1/brick1/brick (arbiter)Brick4: uk1-prod-gfs-01:/data/glusterfs/gv1/brick3/brickBrick5: uk2-prod-gfs-01:/data/glusterfs/gv1/brick3/brickBrick6: uk3-prod-gfs-arb-01:/data/glusterfs/gv1/brick3/brick (arbiter)Brick7: uk1-prod-gfs-01:/data/glusterfs/gv1/brick2/brickBrick8: uk2-prod-gfs-01:/data/glusterfs/gv1/brick2/brickBrick9: uk3-prod-gfs-arb-01:/data/glusterfs/gv1/brick2/brick (arbiter)Options Reconfigured:cluster.entry-self-heal: oncluster.metadata-self-heal: oncluster.data-self-heal: onperformance.client-io-threads: offstorage.fips-mode-rchecksum: ontransport.address-family: inetcluster.lookup-optimize: offperformance.readdir-ahead: offcluster.readdir-optimize: offcluster.self-heal-daemon: enablefeatures.shard: enablefeatures.shard-block-size: 512MBcluster.min-free-disk: 10%cluster.use-anonymous-inode: yes


root at uk3-prod-gfs-arb-01:~# gluster peer status
Number of Peers: 2
Hostname: uk2-prod-gfs-01Uuid: 2fdfa4a2-195d-4cc5-937c-f48466e76149State: Peer in Cluster (Connected)
Hostname: uk1-prod-gfs-01Uuid: 43ec93d1-ad83-4103-aea3-80ded0903d88State: Peer in Cluster (Connected)


root at uk3-prod-gfs-arb-01:~# gluster volume heal gv1 info
Brick uk1-prod-gfs-01:/data/glusterfs/gv1/brick1/brick<gfid:5b57e1f6-3e3d-4334-a0db-b2560adae6d1>Status: ConnectedNumber of entries: 1
Brick uk2-prod-gfs-01:/data/glusterfs/gv1/brick1/brickStatus: ConnectedNumber of entries: 0
Brick uk3-prod-gfs-arb-01:/data/glusterfs/gv1/brick1/brickStatus: ConnectedNumber of entries: 0
Brick uk1-prod-gfs-01:/data/glusterfs/gv1/brick3/brickStatus: ConnectedNumber of entries: 0
Brick uk2-prod-gfs-01:/data/glusterfs/gv1/brick3/brickStatus: ConnectedNumber of entries: 0
Brick uk3-prod-gfs-arb-01:/data/glusterfs/gv1/brick3/brickStatus: ConnectedNumber of entries: 0
Brick uk1-prod-gfs-01:/data/glusterfs/gv1/brick2/brickStatus: ConnectedNumber of entries: 0
Brick uk2-prod-gfs-01:/data/glusterfs/gv1/brick2/brick<gfid:6ba9c472-9232-4b45-b12f-a1232d6f4627>/.shard/.remove_me<gfid:0f042518-248d-426a-93f4-cfaa92b6ef3e>Status: ConnectedNumber of entries: 3
Brick uk3-prod-gfs-arb-01:/data/glusterfs/gv1/brick2/brick<gfid:6ba9c472-9232-4b45-b12f-a1232d6f4627>/.shard/.remove_me<gfid:0f042518-248d-426a-93f4-cfaa92b6ef3e>Status: ConnectedNumber of entries: 3


root at uk3-prod-gfs-arb-01:~# gluster volume get all cluster.op-versionOption                                   Value------                                   -----cluster.op-version                       100000

We're not sure if this is a potential bug or if something's corrupted that we don't have visibility of, so any pointers/suggestions about how to approach this would be appreciated. 
Thanks,Liam
| 
 |




The contents of this email message and any attachments are intended solely for the addressee(s) and may contain confidential and/or privileged information and may be legally protected from disclosure.


________



Community Meeting Calendar:

Schedule -
Every 2nd and 4th Tuesday at 14:30 IST / 09:00 UTC
Bridge: https://meet.google.com/cpu-eiue-hvk
Gluster-users mailing list
Gluster-users at gluster.org
https://lists.gluster.org/mailman/listinfo/gluster-users







 


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-devel/attachments/20230705/b288d668/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image357893.png
Type: image/png
Size: 24762 bytes
Desc: not available
URL: <http://lists.gluster.org/pipermail/gluster-devel/attachments/20230705/b288d668/attachment-0003.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image782979.png
Type: image/png
Size: 24762 bytes
Desc: not available
URL: <http://lists.gluster.org/pipermail/gluster-devel/attachments/20230705/b288d668/attachment-0004.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image135755.png
Type: image/png
Size: 24762 bytes
Desc: not available
URL: <http://lists.gluster.org/pipermail/gluster-devel/attachments/20230705/b288d668/attachment-0005.png>


More information about the Gluster-devel mailing list