Issue iSCSI disk in stopping state.
Pages: 1 2
karad
12 Posts
August 28, 2023, 1:43 pmQuote from karad on August 28, 2023, 1:43 pmAre the disks loaded ?
From the disk % util chart, are they very busy ?
Not really, the disks are around 25% of Util on average, Sporadically I see two or three disks at 75%-80% for a couple of minutes.
From OSD latency chart, what is max latencies you see ?
The OSDs have 30ms of applied latency on average. If I change the time range to 1 day I see that two OSD had 1 pike of 400ms each one
From the cluster iops charts, what is the value of cluster iops ?
write iops:~2500
read iops:~1000.
I decided to reboot the storage node 03 and after that, the iSCSI Disks were started properly again. The only ones that I could capture during the reboot via the console were the following messages (check screenshot)
Are the disks loaded ?
From the disk % util chart, are they very busy ?
Not really, the disks are around 25% of Util on average, Sporadically I see two or three disks at 75%-80% for a couple of minutes.
From OSD latency chart, what is max latencies you see ?
The OSDs have 30ms of applied latency on average. If I change the time range to 1 day I see that two OSD had 1 pike of 400ms each one
From the cluster iops charts, what is the value of cluster iops ?
write iops:~2500
read iops:~1000.
I decided to reboot the storage node 03 and after that, the iSCSI Disks were started properly again. The only ones that I could capture during the reboot via the console were the following messages (check screenshot)
Pages: 1 2
Issue iSCSI disk in stopping state.
karad
12 Posts
Quote from karad on August 28, 2023, 1:43 pmAre the disks loaded ?
From the disk % util chart, are they very busy ?
Not really, the disks are around 25% of Util on average, Sporadically I see two or three disks at 75%-80% for a couple of minutes.
From OSD latency chart, what is max latencies you see ?
The OSDs have 30ms of applied latency on average. If I change the time range to 1 day I see that two OSD had 1 pike of 400ms each one
From the cluster iops charts, what is the value of cluster iops ?
write iops:~2500
read iops:~1000.
I decided to reboot the storage node 03 and after that, the iSCSI Disks were started properly again. The only ones that I could capture during the reboot via the console were the following messages (check screenshot)
Are the disks loaded ?
From the disk % util chart, are they very busy ?
Not really, the disks are around 25% of Util on average, Sporadically I see two or three disks at 75%-80% for a couple of minutes.
From OSD latency chart, what is max latencies you see ?
The OSDs have 30ms of applied latency on average. If I change the time range to 1 day I see that two OSD had 1 pike of 400ms each one
From the cluster iops charts, what is the value of cluster iops ?
write iops:~2500
read iops:~1000.
I decided to reboot the storage node 03 and after that, the iSCSI Disks were started properly again. The only ones that I could capture during the reboot via the console were the following messages (check screenshot)