Re: [Gluster-users] Hot Tier exceeding watermark-hi
4 hours later, no files have been demoted [root@Glus1 ~]# gluster volume status FFPrimary detail Status of volume: FFPrimary Hot Bricks: -- Brick: Brick Glus3:/data/glusterfs/FFPrimary/brick3 TCP Port : 49155 RDMA Port: 0 Online : Y Pid : 24177 File System : xfs Device : /dev/nvme0n1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 24.3GB Total Disk Space : 476.7GB Inode Count : 50877088 Free Inodes : 50874696 -- Brick: Brick Glus2:/data/glusterfs/FFPrimary/brick2 TCP Port : 49155 RDMA Port: 0 Online : Y Pid : 17994 File System : xfs Device : /dev/nvme0n1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 15.5GB Total Disk Space : 476.7GB Inode Count : 32560288 Free Inodes : 32557896 -- Brick: Brick Glus1:/data/glusterfs/FFPrimary/brick1 TCP Port : 49154 RDMA Port: 0 Online : Y Pid : 23573 File System : xfs Device : /dev/nvme0n1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 13.8GB Total Disk Space : 476.7GB Inode Count : 29027000 Free Inodes : 29024515 Cold Bricks: -- Brick: Brick Glus1:/data/glusterfs/FFPrimary/brick5 TCP Port : 49152 RDMA Port: 0 Online : Y Pid : 23442 File System : xfs Device : /dev/sdb1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 2.5TB Total Disk Space : 2.7TB Inode Count : 292971904 Free Inodes : 292969488 -- Brick: Brick Glus2:/data/glusterfs/FFPrimary/brick6 TCP Port : 49153 RDMA Port: 0 Online : Y Pid : 17856 File System : xfs Device : /dev/sdb1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 2.5TB Total Disk Space : 2.7TB Inode Count : 292971904 Free Inodes : 292969489 -- Brick: Brick Glus3:/data/glusterfs/FFPrimary/brick7 TCP Port : 49153 RDMA Port: 0 Online : Y Pid : 24018 File System : xfs Device : /dev/sdb1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 2.5TB Total Disk Space : 2.7TB Inode Count : 292971904 Free Inodes : 292969488 -- Brick: Brick Glus1:/data/glusterfs/FFPrimary/brick8 TCP Port : 49153 RDMA Port: 0 Online : Y Pid : 23518 File System : xfs Device : /dev/sdc1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 2.7TB Total Disk Space : 2.7TB Inode Count : 292971904 Free Inodes : 292969607 -- Brick: Brick Glus2:/data/glusterfs/FFPrimary/brick9 TCP Port : 49154 RDMA Port: 0 Online : Y Pid : 17943 File System : xfs Device : /dev/sdc1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 2.7TB Total Disk Space : 2.7TB Inode Count : 292971904 Free Inodes : 292969607 -- Brick: Brick Glus3:/data/glusterfs/FFPrimary/brick10 TCP Port : 49154 RDMA Port: 0 Online : Y Pid : 24108 File System : xfs Device : /dev/sdc1 Mount Options: rw,seclabel,relatime,attr2,inode64,noquota Inode Size : 512 Disk Space Free : 2.7TB Total Disk Space : 2.7TB Inode Count : 292971904 Free Inodes : 292969604 [root@Glus1 ~]# gluster volume info Volume N
Re: [Gluster-users] Hot Tier exceeding watermark-hi
Thank you Hari, I have set: cluster.tier-promote-frequency: 1800 cluster.tier-demote-frequency: 120 I will let you know if it makes a difference after some time. So far (10 minutes), nothing has changed. I would agree with you, that by looking at the result of 'gluster volume tier FFPrimary status' it would seem that demoting is happening. However, for the last 24hrs, nothing has changed in the tier status report except the time. Could it be stuck? How would I know? Is there a way to restart it without restarting the cluster? On Sat, Sep 29, 2018 at 11:08 AM Hari Gowtham wrote: > Hi, > > I can see that the demotion is happening from the status provided by you. > Do verify it. > I would recommend you to change the cluster.tier-demote-frequency to 120 > and cluster.tier-promote-frequency to 1800 to increase the demotions until > the > hot tier is emptied to a certain extent. Later you can use the values > existing now. > On Sat, Sep 29, 2018 at 5:39 PM David Brown wrote: > > > > Hey Everyone, > > > > I have a 3 node GlusterFS cluster that uses NVMe hot tier and a HDD cold > tier. > > I recently ran into some problems when the hot tier became full with > df-h showing 100%. > > > > I did not have a watermark-hi set, but it is my understanding that 90% > is the default. In an attempt to get the cluster to demote some files, I > set cluster.watermark-hi: 80 but it is still not demoting. > > > > > > [root@Glus1 ~]# gluster volume info > > > > Volume Name: FFPrimary > > Type: Tier > > Volume ID: 466ec53c-d1ef-4ebc-8414-d7d070dfe61e > > Status: Started > > Snapshot Count: 0 > > Number of Bricks: 9 > > Transport-type: tcp > > Hot Tier : > > Hot Tier Type : Replicate > > Number of Bricks: 1 x 3 = 3 > > Brick1: Glus3:/data/glusterfs/FFPrimary/brick3 > > Brick2: Glus2:/data/glusterfs/FFPrimary/brick2 > > Brick3: Glus1:/data/glusterfs/FFPrimary/brick1 > > Cold Tier: > > Cold Tier Type : Distributed-Replicate > > Number of Bricks: 2 x 3 = 6 > > Brick4: Glus1:/data/glusterfs/FFPrimary/brick5 > > Brick5: Glus2:/data/glusterfs/FFPrimary/brick6 > > Brick6: Glus3:/data/glusterfs/FFPrimary/brick7 > > Brick7: Glus1:/data/glusterfs/FFPrimary/brick8 > > Brick8: Glus2:/data/glusterfs/FFPrimary/brick9 > > Brick9: Glus3:/data/glusterfs/FFPrimary/brick10 > > Options Reconfigured: > > cluster.tier-promote-frequency: 120 > > cluster.tier-demote-frequency: 1800 > > cluster.watermark-low: 60 > > cluster.watermark-hi: 80 > > performance.flush-behind: on > > performance.cache-max-file-size: 128MB > > performance.cache-size: 25GB > > diagnostics.count-fop-hits: off > > diagnostics.latency-measurement: off > > cluster.tier-mode: cache > > features.ctr-enabled: on > > transport.address-family: inet > > nfs.disable: on > > performance.client-io-threads: off > > [root@Glus1 ~]# gluster volume tier FFPrimary status > > Node Promoted files Demoted filesStatus >run time in h:m:s > > --- > -- > > localhost49 0in > progress 5151:30:45 > > Glus2 00in progress > 5151:30:45 > > Glus3 02075 in progress > 5151:30:47 > > Tiering Migration Functionality: FFPrimary: success > > [root@Glus1 ~]# > > > > What can cause GlusterFS to stop demoting files and allow it to > completely fill the Hot Tier? > > > > Thank you! > > > > > > > > ___ > > Gluster-users mailing list > > Gluster-users@gluster.org > > https://lists.gluster.org/mailman/listinfo/gluster-users > > > > -- > Regards, > Hari Gowtham. > ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Hot Tier exceeding watermark-hi
Hi, I can see that the demotion is happening from the status provided by you. Do verify it. I would recommend you to change the cluster.tier-demote-frequency to 120 and cluster.tier-promote-frequency to 1800 to increase the demotions until the hot tier is emptied to a certain extent. Later you can use the values existing now. On Sat, Sep 29, 2018 at 5:39 PM David Brown wrote: > > Hey Everyone, > > I have a 3 node GlusterFS cluster that uses NVMe hot tier and a HDD cold tier. > I recently ran into some problems when the hot tier became full with df-h > showing 100%. > > I did not have a watermark-hi set, but it is my understanding that 90% is the > default. In an attempt to get the cluster to demote some files, I set > cluster.watermark-hi: 80 but it is still not demoting. > > > [root@Glus1 ~]# gluster volume info > > Volume Name: FFPrimary > Type: Tier > Volume ID: 466ec53c-d1ef-4ebc-8414-d7d070dfe61e > Status: Started > Snapshot Count: 0 > Number of Bricks: 9 > Transport-type: tcp > Hot Tier : > Hot Tier Type : Replicate > Number of Bricks: 1 x 3 = 3 > Brick1: Glus3:/data/glusterfs/FFPrimary/brick3 > Brick2: Glus2:/data/glusterfs/FFPrimary/brick2 > Brick3: Glus1:/data/glusterfs/FFPrimary/brick1 > Cold Tier: > Cold Tier Type : Distributed-Replicate > Number of Bricks: 2 x 3 = 6 > Brick4: Glus1:/data/glusterfs/FFPrimary/brick5 > Brick5: Glus2:/data/glusterfs/FFPrimary/brick6 > Brick6: Glus3:/data/glusterfs/FFPrimary/brick7 > Brick7: Glus1:/data/glusterfs/FFPrimary/brick8 > Brick8: Glus2:/data/glusterfs/FFPrimary/brick9 > Brick9: Glus3:/data/glusterfs/FFPrimary/brick10 > Options Reconfigured: > cluster.tier-promote-frequency: 120 > cluster.tier-demote-frequency: 1800 > cluster.watermark-low: 60 > cluster.watermark-hi: 80 > performance.flush-behind: on > performance.cache-max-file-size: 128MB > performance.cache-size: 25GB > diagnostics.count-fop-hits: off > diagnostics.latency-measurement: off > cluster.tier-mode: cache > features.ctr-enabled: on > transport.address-family: inet > nfs.disable: on > performance.client-io-threads: off > [root@Glus1 ~]# gluster volume tier FFPrimary status > Node Promoted files Demoted filesStatus > run time in h:m:s > ---- > - > localhost49 0in progress > 5151:30:45 > Glus2 00in progress > 5151:30:45 > Glus3 02075 in progress > 5151:30:47 > Tiering Migration Functionality: FFPrimary: success > [root@Glus1 ~]# > > What can cause GlusterFS to stop demoting files and allow it to completely > fill the Hot Tier? > > Thank you! > > > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > https://lists.gluster.org/mailman/listinfo/gluster-users -- Regards, Hari Gowtham. ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Hot Tier exceeding watermark-hi
Hey Everyone, I have a 3 node GlusterFS cluster that uses NVMe hot tier and a HDD cold tier. I recently ran into some problems when the hot tier became full with df-h showing 100%. I did not have a watermark-hi set, but it is my understanding that 90% is the default. In an attempt to get the cluster to demote some files, I set cluster.watermark-hi: 80 but it is still not demoting. [root@Glus1 ~]# gluster volume info Volume Name: FFPrimary Type: Tier Volume ID: 466ec53c-d1ef-4ebc-8414-d7d070dfe61e Status: Started Snapshot Count: 0 Number of Bricks: 9 Transport-type: tcp Hot Tier : Hot Tier Type : Replicate Number of Bricks: 1 x 3 = 3 Brick1: Glus3:/data/glusterfs/FFPrimary/brick3 Brick2: Glus2:/data/glusterfs/FFPrimary/brick2 Brick3: Glus1:/data/glusterfs/FFPrimary/brick1 Cold Tier: Cold Tier Type : Distributed-Replicate Number of Bricks: 2 x 3 = 6 Brick4: Glus1:/data/glusterfs/FFPrimary/brick5 Brick5: Glus2:/data/glusterfs/FFPrimary/brick6 Brick6: Glus3:/data/glusterfs/FFPrimary/brick7 Brick7: Glus1:/data/glusterfs/FFPrimary/brick8 Brick8: Glus2:/data/glusterfs/FFPrimary/brick9 Brick9: Glus3:/data/glusterfs/FFPrimary/brick10 Options Reconfigured: cluster.tier-promote-frequency: 120 cluster.tier-demote-frequency: 1800 cluster.watermark-low: 60 cluster.watermark-hi: 80 performance.flush-behind: on performance.cache-max-file-size: 128MB performance.cache-size: 25GB diagnostics.count-fop-hits: off diagnostics.latency-measurement: off cluster.tier-mode: cache features.ctr-enabled: on transport.address-family: inet nfs.disable: on performance.client-io-threads: off [root@Glus1 ~]# gluster volume tier FFPrimary status Node Promoted files Demoted filesStatus run time in h:m:s ---- - localhost49 0in progress 5151:30:45 Glus2 00in progress 5151:30:45 Glus3 02075 in progress 5151:30:47 Tiering Migration Functionality: FFPrimary: success [root@Glus1 ~]# What can cause GlusterFS to stop demoting files and allow it to completely fill the Hot Tier? Thank you! ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
