Bill, if my memory serves me correctly, there was a fix done in later versions of Scale (there may be an efix available) for the situation you described. Notably, Scale was not properly propagating information about files created through NFS. I suggest you contact Scale support to see if they can provide more details, as well as options for obtaining the fix, assuming my mind has not completely failed me on this issue 😊
Fred Fred Stock, Spectrum Scale Development Advocacy [email protected]<mailto:[email protected]> | 720-430-8821 From: gpfsug-discuss <[email protected]> on behalf of Bill Peters <[email protected]> Date: Wednesday, February 22, 2023 at 12:53 PM To: [email protected] <[email protected]> Subject: [EXTERNAL] [gpfsug-discuss] spanning datacenter to AWS Hello all, I’ve been on the mailing list for a few years but have not been active except my introduction email. We are having an issue I’d like to run past everyone and see if anyone has experience that may help. Currently using ZjQcmQRYFpfptBannerStart This Message Is From an External Sender This message came from outside your organization. ZjQcmQRYFpfptBannerEnd Hello all, I’ve been on the mailing list for a few years but have not been active except my introduction email. We are having an issue I’d like to run past everyone and see if anyone has experience that may help. Currently using Spectrum Scale Data Management Edition 5.1.1.0 Our Spectrum Scale cluster is running on Linux VMs on IBM z/VM. We have one application that cannot support the z/VM architecture so we used to have those servers running on VMware in our datacenter and those servers were client nodes in the Spectrum Scale cluster. This configuration worked great. We recently retired VMWare and moved all that workload to AWS. Because this was no longer on our LAN we thought it would be a good idea (IBM support also recommended it) to use CES NFS rather than adding the AWS instances to the cluster. Since doing this we have seen problems under high IO. Some NFS clients will try to access files that don’t seem to be there resulting in file not found errors. We know the files have been created but the NFS clients can’t see them. The read process runs successfully shortly after. We are not saturating our AWS connection. I haven’t seen any NFS tuning that looks like it would help, but that is an option I would be willing to try. The other option I’m thinking about is just adding the NFS clients to the cluster. Has anyone spanned datacenters like this? Thanks, any help is appreciated. -Bill Bill Peters Senior Platform Engineer 703-475-3386 [email protected]<mailto:[email protected]> atpco.net 45005 Aviation Drive Dulles, VA 20166 [A close up of a sign Description automatically generated]<http://bit.ly/35vlWu3> [Title: Facebook - Description: Facebook icon]<https://www.facebook.com/atpconews/> [Title: Twitter - Description: Twitter icon] <https://twitter.com/ATPCOnews> [Title: LinkedIn - Description: LinkedIn icon] <https://www.linkedin.com/company/atpco/>
_______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org
