[Gluster-users] glustefs as vmware datastore in production

[김경표]

Sometimes os disk hang occured and re-mounted with ro in vm guest(centos6)
when storage was busy.

After install vmware plugin, increased block response timeout to 30 sec.
But os workload reponse time was not good.

I guess my system composed with 5400 rpm disks with raid6.
Overall storage performance is not good for multiple os images.

best regards.


After tha

2018년 5월 29일 (화) 오전 1:45, João Reis <joao at 7lan.net>님이 작성:

> Nice to read this. Any particular reason to *not* run the OS image in
> glusterfs cluster?
>
> Thanks
>
> On 05/26/2018 02:56 PM, 김경표 wrote:
>
>
> Hi,
>>
>> Does anyone have glusterfs as vmware datastore working in production in a
>> real world case? How to serve the glusterfs cluster? As iscsi, NFS?
>>
>>
> Hi,
>
> I am using glusterfs 3.10.x for VMware ESXi 5.5 NFS DataStore.
>
> Our Environment is
> - 4 node supermicro server (each 50TB, NL SAS 4TB used, LSI 9260-8i)
> - Totally 100TB service volume
> - 10G Storage Network and Service network (for NFS)
> - VMware / Linux / IBM AIX Clients
>
> Currently, VM images on GlusterFS is used for Data(Backup) not OS Image.
>
> There is no glusterfs issue in 10 months.
>
> Best Regards
>
>
>
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20180529/e392840a/attachment.html>