IOPS benchmark is very low
Pages: 1 2
Abhishek Kumar Singh
18 Posts
October 28, 2020, 7:16 amQuote from Abhishek Kumar Singh on October 28, 2020, 7:16 amHi Team,
We have created 4 nodes PetaSAN cluster .
We have tested on 3 nodes IOPS benchmark.
4K IOPS rados benchmark
pool: rdb
Threads/Client: 256
Duration : 5 min
Cluster IOPS
Write
Read
1171
2721
Can you please suggest how we can improve performance . We are looking to implement PetaSAN as a production environment.
Thanks in advance,
Abhishek
Hi Team,
We have created 4 nodes PetaSAN cluster .
We have tested on 3 nodes IOPS benchmark.
4K IOPS rados benchmark
pool: rdb
Threads/Client: 256
Duration : 5 min
Cluster IOPS
Write
Read
1171
2721
Can you please suggest how we can improve performance . We are looking to implement PetaSAN as a production environment.
Thanks in advance,
Abhishek
Last edited on October 28, 2020, 7:44 am by Abhishek Kumar Singh · #1
admin
2,930 Posts
October 28, 2020, 9:39 amQuote from admin on October 28, 2020, 9:39 amhow many OSDs do you have ?
are they spinning hdds ?
after 5 min test, look at chart for disk %utilzation, is it high ?
if you have a spare empty disk (non OSD) , can you run the raw disk performance test from blue console menu ?
how many OSDs do you have ?
are they spinning hdds ?
after 5 min test, look at chart for disk %utilzation, is it high ?
if you have a spare empty disk (non OSD) , can you run the raw disk performance test from blue console menu ?
Abhishek Kumar Singh
18 Posts
October 28, 2020, 10:32 amQuote from Abhishek Kumar Singh on October 28, 2020, 10:32 amWe have total 8 OSDs UP & IN.
No, They are not spinning HDDs.. We are using SSD.
After 5 min test disk %utilzation is very low...less then 10%
Please find attached below raw disk performance test from blue console menu
We have total 8 OSDs UP & IN.
No, They are not spinning HDDs.. We are using SSD.
After 5 min test disk %utilzation is very low...less then 10%
Please find attached below raw disk performance test from blue console menu
admin
2,930 Posts
October 28, 2020, 10:58 amQuote from admin on October 28, 2020, 10:58 amThe random read disk test is very low.
The random read disk test is very low.
Abhishek Kumar Singh
18 Posts
October 28, 2020, 11:16 amQuote from Abhishek Kumar Singh on October 28, 2020, 11:16 amOur random read disk test is very low means there is issue with our disks or any thing else & please suggest what we can do for best performance.
Our random read disk test is very low means there is issue with our disks or any thing else & please suggest what we can do for best performance.
admin
2,930 Posts
October 28, 2020, 12:14 pmQuote from admin on October 28, 2020, 12:14 pmcould be many things: the type of disks itself, controller, firmware...
what is the model of SSD you are using ?
the command we run for random disk iops is
fio --name=xx --filename=/dev/sdXX --iodepth=1 --rw=randread --bs=4k --direct=1 --runtime=10 --time_based --numjobs=8 --group_reporting
replace /dev/sdXX with correct name and numjobs=8 with desired threads
could be many things: the type of disks itself, controller, firmware...
what is the model of SSD you are using ?
the command we run for random disk iops is
fio --name=xx --filename=/dev/sdXX --iodepth=1 --rw=randread --bs=4k --direct=1 --runtime=10 --time_based --numjobs=8 --group_reporting
replace /dev/sdXX with correct name and numjobs=8 with desired threads
Abhishek Kumar Singh
18 Posts
November 2, 2020, 6:23 pmQuote from Abhishek Kumar Singh on November 2, 2020, 6:23 pmHi Team,
I used ceph rbd in my project(create rbd and map in client by mounting it as data partition ,use like a local disk), will the PetaSAN have this similar feature?
Hi Team,
I used ceph rbd in my project(create rbd and map in client by mounting it as data partition ,use like a local disk), will the PetaSAN have this similar feature?
admin
2,930 Posts
November 2, 2020, 9:57 pmQuote from admin on November 2, 2020, 9:57 pmNot sure i understand the question, but PetaSAN includes Ceph, so anything you did before with Ceph you can do, open a shell and just type Ceph commands, create rbd images...etc. Then from a Linux client, you can map the disk and mount it.
Not sure i understand the question, but PetaSAN includes Ceph, so anything you did before with Ceph you can do, open a shell and just type Ceph commands, create rbd images...etc. Then from a Linux client, you can map the disk and mount it.
Abhishek Kumar Singh
18 Posts
November 5, 2020, 5:40 amQuote from Abhishek Kumar Singh on November 5, 2020, 5:40 amWeather we can implement bond ip for PetaSAN setup ?
Please confirm & how we can implement?
Weather we can implement bond ip for PetaSAN setup ?
Please confirm & how we can implement?
admin
2,930 Posts
November 5, 2020, 8:13 amQuote from admin on November 5, 2020, 8:13 amYou can configure network including bonds via ui when you first setup the cluster, during deployment of first node "Create New Cluster'.
After you deploy, you can change the configuration on a running cluster manually via /opt/petasan/config/cluster_info.json. The format is very easy to understand but it is easier to deploy a 1 node test vm and play with settings/bongs in ui and take its config file and apply change to running cluster.
You can configure network including bonds via ui when you first setup the cluster, during deployment of first node "Create New Cluster'.
After you deploy, you can change the configuration on a running cluster manually via /opt/petasan/config/cluster_info.json. The format is very easy to understand but it is easier to deploy a 1 node test vm and play with settings/bongs in ui and take its config file and apply change to running cluster.
Pages: 1 2
IOPS benchmark is very low
Abhishek Kumar Singh
18 Posts
Quote from Abhishek Kumar Singh on October 28, 2020, 7:16 amHi Team,
We have created 4 nodes PetaSAN cluster .
We have tested on 3 nodes IOPS benchmark.
4K IOPS rados benchmark
pool: rdb
Threads/Client: 256
Duration : 5 min
Cluster IOPS
Write Read 1171 2721 Can you please suggest how we can improve performance . We are looking to implement PetaSAN as a production environment.
Thanks in advance,
Abhishek
Hi Team,
We have created 4 nodes PetaSAN cluster .
We have tested on 3 nodes IOPS benchmark.
4K IOPS rados benchmark
pool: rdb
Threads/Client: 256
Duration : 5 min
Cluster IOPS
Write | Read |
---|---|
1171 | 2721 |
Can you please suggest how we can improve performance . We are looking to implement PetaSAN as a production environment.
Thanks in advance,
Abhishek
admin
2,930 Posts
Quote from admin on October 28, 2020, 9:39 amhow many OSDs do you have ?
are they spinning hdds ?
after 5 min test, look at chart for disk %utilzation, is it high ?
if you have a spare empty disk (non OSD) , can you run the raw disk performance test from blue console menu ?
how many OSDs do you have ?
are they spinning hdds ?
after 5 min test, look at chart for disk %utilzation, is it high ?
if you have a spare empty disk (non OSD) , can you run the raw disk performance test from blue console menu ?
Abhishek Kumar Singh
18 Posts
Quote from Abhishek Kumar Singh on October 28, 2020, 10:32 amWe have total 8 OSDs UP & IN.
No, They are not spinning HDDs.. We are using SSD.
After 5 min test disk %utilzation is very low...less then 10%
Please find attached below raw disk performance test from blue console menu
We have total 8 OSDs UP & IN.
No, They are not spinning HDDs.. We are using SSD.
After 5 min test disk %utilzation is very low...less then 10%
Please find attached below raw disk performance test from blue console menu
admin
2,930 Posts
Quote from admin on October 28, 2020, 10:58 amThe random read disk test is very low.
The random read disk test is very low.
Abhishek Kumar Singh
18 Posts
Quote from Abhishek Kumar Singh on October 28, 2020, 11:16 amOur random read disk test is very low means there is issue with our disks or any thing else & please suggest what we can do for best performance.
Our random read disk test is very low means there is issue with our disks or any thing else & please suggest what we can do for best performance.
admin
2,930 Posts
Quote from admin on October 28, 2020, 12:14 pmcould be many things: the type of disks itself, controller, firmware...
what is the model of SSD you are using ?
the command we run for random disk iops is
fio --name=xx --filename=/dev/sdXX --iodepth=1 --rw=randread --bs=4k --direct=1 --runtime=10 --time_based --numjobs=8 --group_reporting
replace /dev/sdXX with correct name and numjobs=8 with desired threads
could be many things: the type of disks itself, controller, firmware...
what is the model of SSD you are using ?
the command we run for random disk iops is
fio --name=xx --filename=/dev/sdXX --iodepth=1 --rw=randread --bs=4k --direct=1 --runtime=10 --time_based --numjobs=8 --group_reporting
replace /dev/sdXX with correct name and numjobs=8 with desired threads
Abhishek Kumar Singh
18 Posts
Quote from Abhishek Kumar Singh on November 2, 2020, 6:23 pmHi Team,
I used ceph rbd in my project(create rbd and map in client by mounting it as data partition ,use like a local disk), will the PetaSAN have this similar feature?
Hi Team,
I used ceph rbd in my project(create rbd and map in client by mounting it as data partition ,use like a local disk), will the PetaSAN have this similar feature?
admin
2,930 Posts
Quote from admin on November 2, 2020, 9:57 pmNot sure i understand the question, but PetaSAN includes Ceph, so anything you did before with Ceph you can do, open a shell and just type Ceph commands, create rbd images...etc. Then from a Linux client, you can map the disk and mount it.
Not sure i understand the question, but PetaSAN includes Ceph, so anything you did before with Ceph you can do, open a shell and just type Ceph commands, create rbd images...etc. Then from a Linux client, you can map the disk and mount it.
Abhishek Kumar Singh
18 Posts
Quote from Abhishek Kumar Singh on November 5, 2020, 5:40 amWeather we can implement bond ip for PetaSAN setup ?
Please confirm & how we can implement?
Weather we can implement bond ip for PetaSAN setup ?
Please confirm & how we can implement?
admin
2,930 Posts
Quote from admin on November 5, 2020, 8:13 amYou can configure network including bonds via ui when you first setup the cluster, during deployment of first node "Create New Cluster'.
After you deploy, you can change the configuration on a running cluster manually via /opt/petasan/config/cluster_info.json. The format is very easy to understand but it is easier to deploy a 1 node test vm and play with settings/bongs in ui and take its config file and apply change to running cluster.
You can configure network including bonds via ui when you first setup the cluster, during deployment of first node "Create New Cluster'.
After you deploy, you can change the configuration on a running cluster manually via /opt/petasan/config/cluster_info.json. The format is very easy to understand but it is easier to deploy a 1 node test vm and play with settings/bongs in ui and take its config file and apply change to running cluster.