Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Hi, which proper hardware do you say?. El 31/10/2021 a las 10:13, Wido den Hollander escribió: Op 30-10-2021 om 05:47 schreef Hean Seng: Hi For CEPH, it is not expected to have all power down, or a sudden of power down, for a proper data center environment. Ceph can handle a power outage just fine as long as you use the proper hardware. I have Ceph seen survive many power outages and came back without any issues. Wido NFS is good, however other then the high availability limitation of it, NFS is filesystem formatted at storage end, This indeed may cause to very high CPU usage of Storage server if the IO requirement is high for VM. Performance issues may occur if this happens. This especially if you hosted database server and Email server, which require a lot of write of a small files . ISCSI and SANS is better for block storage requirement. However in this Cloudstack support of this ISCSI or SANS, it can only configure as local storage, Cluster Filesystem is nightmare . On Sat, Oct 30, 2021 at 3:35 AM Mauro Ferraro - G2K Hosting < mferr...@g2khosting.com> wrote: Ignazio, many thanks for your feedback. In the past we try ceph and it works great, until an electrical outage broken it and we don't want to continue with this technology at least at it get better or we can geo replicate it in othe site. Other thing is, when something big occurs ceph take a lot of time to recovery and repair, so this will leave you offline until the process finish, but you never know if your information is safe until finish, we can say, is not. For a cluster of replica 3, of 80TB it can take a week or more. This is not an option for us. Previusly we use NFS as separated primary storages, and now we still with NFS until we get a replacement. NFS is great too, because you can get an stable solution with KVM and QCOW2, if something happends you have lot of chances of start all again with low risk of degradation. You can start all again in hours. The main problem is the performance bottleneck and high availability of the VMs at storage side. That is the main reason we want to test linstor, because it promise some features, like replication with DRDB, HA, and performance all in one. At this point we cannot finish the configuration in ACS 4.16 RC2, because there is not documentation and we are having some problem with Linstor, ZFS and ACS that we are not able to discover. What solution recommends for a ACS cluster for deploy aprox 1000 VMs?. Regards, Mauro El 29/10/2021 a las 15:56, Ignazio Cassano escribió: Hi Mauro, what would you like to store on the clustered file system ? If you want use it for virtual machine disks I think nfs is a good solution. Clustered file system could be used if your virtualization nodes have a lot of disks. I usually I prefer use a nas or a San. If you have a San you can use iscsi with clustered logical volumes. Each logical volume can host a virtual machine volume and clustered lvm can handle locks. Ignazio Il Gio 28 Ott 2021, 14:02 Mauro Ferraro - G2K Hosting ha scritto: Hi, We are trying to make a lab with ACS 4.16 and Linstor. As soon as we finish the tests we can give you some approach for the results. Are someone already try this technology?. Regards, El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: > Since NFS alone doesn't offer HA. What do you recommend for HA NFS? > > On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: > >> I have similar consideration when start exploring Cloudstack , but in >> reality Clustered Filesystem is not easy to maintain. You seems have >> choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs >> recently only maintained in oracle linux. I believe you do not want to >> choose solution that is very propriety . Thus just SAN or ISCSI o is not >> really a direct solution here , except you want to encapsulate it in NFS >> and facing Cloudstack Storage. >> >> It work good on CEPH and NFS , but performance wise, NFS is better . And >> all documentation and features you saw in Cloudstack , it work perfectly >> on NFS. >> >> If you choose CEPH, may be you have to compensate with some performance >> degradation, >> >> >> >> On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes >> wrote: >> >>> I've been using Ceph in prod for volumes for some time. Note that >> although >>> I had several cloudstack installations, this one runs on top of Cinder, >>> but it basic translates as libvirt and rados. >>> >>> It is totally stable and performance IMHO is enough for virtualized >>> services. >>> >>> IO might suffer some penalization due the data replication inside Ceph. >>> Elasticsearch for instance, the degradation would be a
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Op 30-10-2021 om 05:47 schreef Hean Seng: Hi For CEPH, it is not expected to have all power down, or a sudden of power down, for a proper data center environment. Ceph can handle a power outage just fine as long as you use the proper hardware. I have Ceph seen survive many power outages and came back without any issues. Wido NFS is good, however other then the high availability limitation of it, NFS is filesystem formatted at storage end, This indeed may cause to very high CPU usage of Storage server if the IO requirement is high for VM. Performance issues may occur if this happens. This especially if you hosted database server and Email server, which require a lot of write of a small files . ISCSI and SANS is better for block storage requirement. However in this Cloudstack support of this ISCSI or SANS, it can only configure as local storage, Cluster Filesystem is nightmare . On Sat, Oct 30, 2021 at 3:35 AM Mauro Ferraro - G2K Hosting < mferr...@g2khosting.com> wrote: Ignazio, many thanks for your feedback. In the past we try ceph and it works great, until an electrical outage broken it and we don't want to continue with this technology at least at it get better or we can geo replicate it in othe site. Other thing is, when something big occurs ceph take a lot of time to recovery and repair, so this will leave you offline until the process finish, but you never know if your information is safe until finish, we can say, is not. For a cluster of replica 3, of 80TB it can take a week or more. This is not an option for us. Previusly we use NFS as separated primary storages, and now we still with NFS until we get a replacement. NFS is great too, because you can get an stable solution with KVM and QCOW2, if something happends you have lot of chances of start all again with low risk of degradation. You can start all again in hours. The main problem is the performance bottleneck and high availability of the VMs at storage side. That is the main reason we want to test linstor, because it promise some features, like replication with DRDB, HA, and performance all in one. At this point we cannot finish the configuration in ACS 4.16 RC2, because there is not documentation and we are having some problem with Linstor, ZFS and ACS that we are not able to discover. What solution recommends for a ACS cluster for deploy aprox 1000 VMs?. Regards, Mauro El 29/10/2021 a las 15:56, Ignazio Cassano escribió: Hi Mauro, what would you like to store on the clustered file system ? If you want use it for virtual machine disks I think nfs is a good solution. Clustered file system could be used if your virtualization nodes have a lot of disks. I usually I prefer use a nas or a San. If you have a San you can use iscsi with clustered logical volumes. Each logical volume can host a virtual machine volume and clustered lvm can handle locks. Ignazio Il Gio 28 Ott 2021, 14:02 Mauro Ferraro - G2K Hosting ha scritto: Hi, We are trying to make a lab with ACS 4.16 and Linstor. As soon as we finish the tests we can give you some approach for the results. Are someone already try this technology?. Regards, El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: > Since NFS alone doesn't offer HA. What do you recommend for HA NFS? > > On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: > >> I have similar consideration when start exploring Cloudstack , but in >> reality Clustered Filesystem is not easy to maintain. You seems have >> choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs >> recently only maintained in oracle linux. I believe you do not want to >> choose solution that is very propriety . Thus just SAN or ISCSI o is not >> really a direct solution here , except you want to encapsulate it in NFS >> and facing Cloudstack Storage. >> >> It work good on CEPH and NFS , but performance wise, NFS is better . And >> all documentation and features you saw in Cloudstack , it work perfectly >> on NFS. >> >> If you choose CEPH, may be you have to compensate with some performance >> degradation, >> >> >> >> On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes >> wrote: >> >>> I've been using Ceph in prod for volumes for some time. Note that >> although >>> I had several cloudstack installations, this one runs on top of Cinder, >>> but it basic translates as libvirt and rados. >>> >>> It is totally stable and performance IMHO is enough for virtualized >>> services. >>> >>> IO might suffer some penalization due the data replication inside Ceph. >>> Elasticsearch for instance, the degradation would be a bit worse as there >>> is replication also in the application size, but IMHO, unless you need
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Op 28-10-2021 om 07:34 schreef Pratik Chandrakar: Since NFS alone doesn't offer HA. What do you recommend for HA NFS? We use TrueNAS M50 NFS boxes which have redundant controllers for example. Our environment has both Ceph (~5PB) and TrueNAS M50 (500TB, NFS) as storage. TrueNAS is used in case that Ceph doesn't meet the I/O latency requirement for some applications. Wido On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: I have similar consideration when start exploring Cloudstack , but in reality Clustered Filesystem is not easy to maintain. You seems have choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs recently only maintained in oracle linux. I believe you do not want to choose solution that is very propriety . Thus just SAN or ISCSI o is not really a direct solution here , except you want to encapsulate it in NFS and facing Cloudstack Storage. It work good on CEPH and NFS , but performance wise, NFS is better . And all documentation and features you saw in Cloudstack , it work perfectly on NFS. If you choose CEPH, may be you have to compensate with some performance degradation, On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes wrote: I've been using Ceph in prod for volumes for some time. Note that although I had several cloudstack installations, this one runs on top of Cinder, but it basic translates as libvirt and rados. It is totally stable and performance IMHO is enough for virtualized services. IO might suffer some penalization due the data replication inside Ceph. Elasticsearch for instance, the degradation would be a bit worse as there is replication also in the application size, but IMHO, unless you need extreme low latency it would be ok. Best, Leandro. On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < michael.bru...@nttdata.com wrote: Hello community, today I need your experience and knowhow about clustered/shared filesystems based on SAN storage to be used with KVM. We need to consider about a clustered/shared filesystem based on SAN storage (no NFS or iSCSI), but do not have any knowhow or experience with this. Those I would like to ask if there any productive used environments out there based on SAN storage on KVM? If so, which clustered/shared filesystem you are using and how is your experience with that (stability, reliability, maintainability, performance, useability,...)? Furthermore, if you had already to consider in the past between SAN storage or CEPH, I would also like to participate on your considerations and results :) Regards, Michael -- Regards, Hean Seng
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Hi For CEPH, it is not expected to have all power down, or a sudden of power down, for a proper data center environment. NFS is good, however other then the high availability limitation of it, NFS is filesystem formatted at storage end, This indeed may cause to very high CPU usage of Storage server if the IO requirement is high for VM. Performance issues may occur if this happens. This especially if you hosted database server and Email server, which require a lot of write of a small files . ISCSI and SANS is better for block storage requirement. However in this Cloudstack support of this ISCSI or SANS, it can only configure as local storage, Cluster Filesystem is nightmare . On Sat, Oct 30, 2021 at 3:35 AM Mauro Ferraro - G2K Hosting < mferr...@g2khosting.com> wrote: > Ignazio, many thanks for your feedback. > > In the past we try ceph and it works great, until an electrical outage > broken it and we don't want to continue with this technology at least at > it get better or we can geo replicate it in othe site. Other thing is, > when something big occurs ceph take a lot of time to recovery and > repair, so this will leave you offline until the process finish, but you > never know if your information is safe until finish, we can say, is not. > For a cluster of replica 3, of 80TB it can take a week or more. This is > not an option for us. > > Previusly we use NFS as separated primary storages, and now we still > with NFS until we get a replacement. NFS is great too, because you can > get an stable solution with KVM and QCOW2, if something happends you > have lot of chances of start all again with low risk of degradation. You > can start all again in hours. The main problem is the performance > bottleneck and high availability of the VMs at storage side. > > That is the main reason we want to test linstor, because it promise some > features, like replication with DRDB, HA, and performance all in one. At > this point we cannot finish the configuration in ACS 4.16 RC2, because > there is not documentation and we are having some problem with Linstor, > ZFS and ACS that we are not able to discover. > > What solution recommends for a ACS cluster for deploy aprox 1000 VMs?. > > Regards, > > Mauro > > El 29/10/2021 a las 15:56, Ignazio Cassano escribió: > > Hi Mauro, what would you like to store on the clustered file system ? > > If you want use it for virtual machine disks I think nfs is a good > > solution. > > Clustered file system could be used if your virtualization nodes have > > a lot of disks. > > I usually I prefer use a nas or a San. > > If you have a San you can use iscsi with clustered logical volumes. > > Each logical volume can host a virtual machine volume and clustered > > lvm can handle locks. > > Ignazio > > > > > > > > Il Gio 28 Ott 2021, 14:02 Mauro Ferraro - G2K Hosting > > ha scritto: > > > > Hi, > > > > We are trying to make a lab with ACS 4.16 and Linstor. As soon as we > > finish the tests we can give you some approach for the results. Are > > someone already try this technology?. > > > > Regards, > > > > El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: > > > Since NFS alone doesn't offer HA. What do you recommend for HA NFS? > > > > > > On Thu, Oct 28, 2021 at 7:37 AM Hean Seng > > wrote: > > > > > >> I have similar consideration when start exploring Cloudstack , > > but in > > >> reality Clustered Filesystem is not easy to maintain. You > > seems have > > >> choice of OCFS or GFS2 , gfs2 is hard to maintain and in > > redhat , ocfs > > >> recently only maintained in oracle linux. I believe you do not > > want to > > >> choose solution that is very propriety . Thus just SAN or > > ISCSI o is not > > >> really a direct solution here , except you want to encapsulate > > it in NFS > > >> and facing Cloudstack Storage. > > >> > > >> It work good on CEPH and NFS , but performance wise, NFS is > > better . And > > >> all documentation and features you saw in Cloudstack , it work > > perfectly > > >> on NFS. > > >> > > >> If you choose CEPH, may be you have to compensate with some > > performance > > >> degradation, > > >> > > >> > > >> > > >> On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes > > > > >> wrote: > > >> > > >>> I've been using Ceph in prod for volumes for some time. Note that > > >> although > > >>> I had several cloudstack installations, this one runs on top > > of Cinder, > > >>> but it basic translates as libvirt and rados. > > >>> > > >>> It is totally stable and performance IMHO is enough for > > virtualized > > >>> services. > > >>> > > >>> IO might suffer some penalization due the data replication > > inside Ceph. > > >>> Elasticsearch for instance, the degradation would be a bit > > worse as there > > >>> is replication
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Ignazio, many thanks for your feedback. In the past we try ceph and it works great, until an electrical outage broken it and we don't want to continue with this technology at least at it get better or we can geo replicate it in othe site. Other thing is, when something big occurs ceph take a lot of time to recovery and repair, so this will leave you offline until the process finish, but you never know if your information is safe until finish, we can say, is not. For a cluster of replica 3, of 80TB it can take a week or more. This is not an option for us. Previusly we use NFS as separated primary storages, and now we still with NFS until we get a replacement. NFS is great too, because you can get an stable solution with KVM and QCOW2, if something happends you have lot of chances of start all again with low risk of degradation. You can start all again in hours. The main problem is the performance bottleneck and high availability of the VMs at storage side. That is the main reason we want to test linstor, because it promise some features, like replication with DRDB, HA, and performance all in one. At this point we cannot finish the configuration in ACS 4.16 RC2, because there is not documentation and we are having some problem with Linstor, ZFS and ACS that we are not able to discover. What solution recommends for a ACS cluster for deploy aprox 1000 VMs?. Regards, Mauro El 29/10/2021 a las 15:56, Ignazio Cassano escribió: Hi Mauro, what would you like to store on the clustered file system ? If you want use it for virtual machine disks I think nfs is a good solution. Clustered file system could be used if your virtualization nodes have a lot of disks. I usually I prefer use a nas or a San. If you have a San you can use iscsi with clustered logical volumes. Each logical volume can host a virtual machine volume and clustered lvm can handle locks. Ignazio Il Gio 28 Ott 2021, 14:02 Mauro Ferraro - G2K Hosting ha scritto: Hi, We are trying to make a lab with ACS 4.16 and Linstor. As soon as we finish the tests we can give you some approach for the results. Are someone already try this technology?. Regards, El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: > Since NFS alone doesn't offer HA. What do you recommend for HA NFS? > > On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: > >> I have similar consideration when start exploring Cloudstack , but in >> reality Clustered Filesystem is not easy to maintain. You seems have >> choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs >> recently only maintained in oracle linux. I believe you do not want to >> choose solution that is very propriety . Thus just SAN or ISCSI o is not >> really a direct solution here , except you want to encapsulate it in NFS >> and facing Cloudstack Storage. >> >> It work good on CEPH and NFS , but performance wise, NFS is better . And >> all documentation and features you saw in Cloudstack , it work perfectly >> on NFS. >> >> If you choose CEPH, may be you have to compensate with some performance >> degradation, >> >> >> >> On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes >> wrote: >> >>> I've been using Ceph in prod for volumes for some time. Note that >> although >>> I had several cloudstack installations, this one runs on top of Cinder, >>> but it basic translates as libvirt and rados. >>> >>> It is totally stable and performance IMHO is enough for virtualized >>> services. >>> >>> IO might suffer some penalization due the data replication inside Ceph. >>> Elasticsearch for instance, the degradation would be a bit worse as there >>> is replication also in the application size, but IMHO, unless you need >>> extreme low latency it would be ok. >>> >>> >>> Best, >>> >>> Leandro. >>> >>> On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < >> michael.bru...@nttdata.com >>> wrote: >>> Hello community, today I need your experience and knowhow about clustered/shared filesystems based on SAN storage to be used with KVM. We need to consider about a clustered/shared filesystem based on SAN storage (no NFS or iSCSI), but do not have any knowhow or experience >> with this. Those I would like to ask if there any productive used environments out there based on SAN storage on KVM? If so, which clustered/shared filesystem you are using and how is your experience with that (stability, reliability, maintainability, >>> performance, useability,...)? Furthermore, if you had already to consider in the past between SAN storage or CEPH, I would also like to participate
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Hi Mauro, what would you like to store on the clustered file system ? If you want use it for virtual machine disks I think nfs is a good solution. Clustered file system could be used if your virtualization nodes have a lot of disks. I usually I prefer use a nas or a San. If you have a San you can use iscsi with clustered logical volumes. Each logical volume can host a virtual machine volume and clustered lvm can handle locks. Ignazio Il Gio 28 Ott 2021, 14:02 Mauro Ferraro - G2K Hosting < mferr...@g2khosting.com> ha scritto: > Hi, > > We are trying to make a lab with ACS 4.16 and Linstor. As soon as we > finish the tests we can give you some approach for the results. Are > someone already try this technology?. > > Regards, > > El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: > > Since NFS alone doesn't offer HA. What do you recommend for HA NFS? > > > > On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: > > > >> I have similar consideration when start exploring Cloudstack , but in > >> reality Clustered Filesystem is not easy to maintain. You seems have > >> choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs > >> recently only maintained in oracle linux. I believe you do not want to > >> choose solution that is very propriety . Thus just SAN or ISCSI o is > not > >> really a direct solution here , except you want to encapsulate it in NFS > >> and facing Cloudstack Storage. > >> > >> It work good on CEPH and NFS , but performance wise, NFS is better . > And > >> all documentation and features you saw in Cloudstack , it work > perfectly > >> on NFS. > >> > >> If you choose CEPH, may be you have to compensate with some performance > >> degradation, > >> > >> > >> > >> On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes > >> wrote: > >> > >>> I've been using Ceph in prod for volumes for some time. Note that > >> although > >>> I had several cloudstack installations, this one runs on top of > Cinder, > >>> but it basic translates as libvirt and rados. > >>> > >>> It is totally stable and performance IMHO is enough for virtualized > >>> services. > >>> > >>> IO might suffer some penalization due the data replication inside Ceph. > >>> Elasticsearch for instance, the degradation would be a bit worse as > there > >>> is replication also in the application size, but IMHO, unless you need > >>> extreme low latency it would be ok. > >>> > >>> > >>> Best, > >>> > >>> Leandro. > >>> > >>> On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < > >> michael.bru...@nttdata.com > >>> wrote: > >>> > Hello community, > > today I need your experience and knowhow about clustered/shared > filesystems based on SAN storage to be used with KVM. > We need to consider about a clustered/shared filesystem based on SAN > storage (no NFS or iSCSI), but do not have any knowhow or experience > >> with > this. > Those I would like to ask if there any productive used environments > out > there based on SAN storage on KVM? > If so, which clustered/shared filesystem you are using and how is your > experience with that (stability, reliability, maintainability, > >>> performance, > useability,...)? > Furthermore, if you had already to consider in the past between SAN > storage or CEPH, I would also like to participate on your > >> considerations > and results :) > > Regards, > Michael > > >> > >> -- > >> Regards, > >> Hean Seng > >> > > >
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Hi Vivek Which part of XCP xen better then KVM ? Performance ?Is tht NFS for XCP also ? On Fri, Oct 29, 2021 at 4:14 PM Vivek Kumar wrote: > I have been using GFS2 with shared mount point in production KVM since > long, Trust me you need to have an expert to manage your whole cluster > otherwise it becomes very hard to manage, NFS works pretty fine with KVM, > if you are planning to use ISCSi or FC, XenServer/XCP and VMware works far > far better then KVM and very easy to manage. > > > > > Vivek Kumar > Sr. Manager - Cloud & DevOps > IndiQus Technologies > M +91 7503460090 > www.indiqus.com > > > > > > On 29-Oct-2021, at 1:14 PM, Hean Seng wrote: > > > > For primitive way for NFS HA, you can consider is just using DRDB . > > > > I think is not yet supported linstor here. > > > > > > > > On Fri, Oct 29, 2021 at 2:29 PM Piotr Pisz wrote: > > > >> Hi > >> > >> So we plan to use linstor in parallel to ceph as a fast resource on nvme > >> cards. > >> Its advantage is that it natively supports zfs with deduplication and > >> compression :-) > >> The test results were more than passable. > >> > >> Regards, > >> Piotr > >> > >> > >> -Original Message- > >> From: Mauro Ferraro - G2K Hosting > >> Sent: Thursday, October 28, 2021 2:02 PM > >> To: users@cloudstack.apache.org; Pratik Chandrakar < > >> chandrakarpra...@gmail.com> > >> Subject: Re: Experience with clustered/shared filesystems based on SAN > >> storage on KVM? > >> > >> Hi, > >> > >> We are trying to make a lab with ACS 4.16 and Linstor. As soon as we > >> finish the tests we can give you some approach for the results. Are > someone > >> already try this technology?. > >> > >> Regards, > >> > >> El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: > >>> Since NFS alone doesn't offer HA. What do you recommend for HA NFS? > >>> > >>> On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: > >>> > I have similar consideration when start exploring Cloudstack , but > in reality Clustered Filesystem is not easy to maintain. You seems > have choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat > , ocfs recently only maintained in oracle linux. I believe you do > not > >> want to > choose solution that is very propriety . Thus just SAN or ISCSI o is > >> not > really a direct solution here , except you want to encapsulate it in > NFS and facing Cloudstack Storage. > > It work good on CEPH and NFS , but performance wise, NFS is better . > And all documentation and features you saw in Cloudstack , it work > perfectly on NFS. > > If you choose CEPH, may be you have to compensate with some > performance degradation, > > > > On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes > > wrote: > > > I've been using Ceph in prod for volumes for some time. Note that > although > > I had several cloudstack installations, this one runs on top of > > Cinder, but it basic translates as libvirt and rados. > > > > It is totally stable and performance IMHO is enough for virtualized > > services. > > > > IO might suffer some penalization due the data replication inside > Ceph. > > Elasticsearch for instance, the degradation would be a bit worse as > > there is replication also in the application size, but IMHO, unless > > you need extreme low latency it would be ok. > > > > > > Best, > > > > Leandro. > > > > On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < > michael.bru...@nttdata.com > > wrote: > > > >> Hello community, > >> > >> today I need your experience and knowhow about clustered/shared > >> filesystems based on SAN storage to be used with KVM. > >> We need to consider about a clustered/shared filesystem based on > >> SAN storage (no NFS or iSCSI), but do not have any knowhow or > >> experience > with > >> this. > >> Those I would like to ask if there any productive used environments > >> out there based on SAN storage on KVM? > >> If so, which clustered/shared filesystem you are using and how is > >> your experience with that (stability, reliability, maintainability, > > performance, > >> useability,...)? > >> Furthermore, if you had already to consider in the past between SAN > >> storage or CEPH, I would also like to participate on your > considerations > >> and results :) > >> > >> Regards, > >> Michael > >> > > -- > Regards, > Hean Seng > > >>> > >> > >> > > > > -- > > Regards, > > Hean Seng > > -- Regards, Hean Seng
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
I have been using GFS2 with shared mount point in production KVM since long, Trust me you need to have an expert to manage your whole cluster otherwise it becomes very hard to manage, NFS works pretty fine with KVM, if you are planning to use ISCSi or FC, XenServer/XCP and VMware works far far better then KVM and very easy to manage. Vivek Kumar Sr. Manager - Cloud & DevOps IndiQus Technologies M +91 7503460090 www.indiqus.com > On 29-Oct-2021, at 1:14 PM, Hean Seng wrote: > > For primitive way for NFS HA, you can consider is just using DRDB . > > I think is not yet supported linstor here. > > > > On Fri, Oct 29, 2021 at 2:29 PM Piotr Pisz wrote: > >> Hi >> >> So we plan to use linstor in parallel to ceph as a fast resource on nvme >> cards. >> Its advantage is that it natively supports zfs with deduplication and >> compression :-) >> The test results were more than passable. >> >> Regards, >> Piotr >> >> >> -Original Message- >> From: Mauro Ferraro - G2K Hosting >> Sent: Thursday, October 28, 2021 2:02 PM >> To: users@cloudstack.apache.org; Pratik Chandrakar < >> chandrakarpra...@gmail.com> >> Subject: Re: Experience with clustered/shared filesystems based on SAN >> storage on KVM? >> >> Hi, >> >> We are trying to make a lab with ACS 4.16 and Linstor. As soon as we >> finish the tests we can give you some approach for the results. Are someone >> already try this technology?. >> >> Regards, >> >> El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: >>> Since NFS alone doesn't offer HA. What do you recommend for HA NFS? >>> >>> On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: >>> I have similar consideration when start exploring Cloudstack , but in reality Clustered Filesystem is not easy to maintain. You seems have choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs recently only maintained in oracle linux. I believe you do not >> want to choose solution that is very propriety . Thus just SAN or ISCSI o is >> not really a direct solution here , except you want to encapsulate it in NFS and facing Cloudstack Storage. It work good on CEPH and NFS , but performance wise, NFS is better . And all documentation and features you saw in Cloudstack , it work perfectly on NFS. If you choose CEPH, may be you have to compensate with some performance degradation, On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes wrote: > I've been using Ceph in prod for volumes for some time. Note that although > I had several cloudstack installations, this one runs on top of > Cinder, but it basic translates as libvirt and rados. > > It is totally stable and performance IMHO is enough for virtualized > services. > > IO might suffer some penalization due the data replication inside Ceph. > Elasticsearch for instance, the degradation would be a bit worse as > there is replication also in the application size, but IMHO, unless > you need extreme low latency it would be ok. > > > Best, > > Leandro. > > On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < michael.bru...@nttdata.com > wrote: > >> Hello community, >> >> today I need your experience and knowhow about clustered/shared >> filesystems based on SAN storage to be used with KVM. >> We need to consider about a clustered/shared filesystem based on >> SAN storage (no NFS or iSCSI), but do not have any knowhow or >> experience with >> this. >> Those I would like to ask if there any productive used environments >> out there based on SAN storage on KVM? >> If so, which clustered/shared filesystem you are using and how is >> your experience with that (stability, reliability, maintainability, > performance, >> useability,...)? >> Furthermore, if you had already to consider in the past between SAN >> storage or CEPH, I would also like to participate on your considerations >> and results :) >> >> Regards, >> Michael >> -- Regards, Hean Seng >>> >> >> > > -- > Regards, > Hean Seng
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
For primitive way for NFS HA, you can consider is just using DRDB . I think is not yet supported linstor here. On Fri, Oct 29, 2021 at 2:29 PM Piotr Pisz wrote: > Hi > > So we plan to use linstor in parallel to ceph as a fast resource on nvme > cards. > Its advantage is that it natively supports zfs with deduplication and > compression :-) > The test results were more than passable. > > Regards, > Piotr > > > -Original Message- > From: Mauro Ferraro - G2K Hosting > Sent: Thursday, October 28, 2021 2:02 PM > To: users@cloudstack.apache.org; Pratik Chandrakar < > chandrakarpra...@gmail.com> > Subject: Re: Experience with clustered/shared filesystems based on SAN > storage on KVM? > > Hi, > > We are trying to make a lab with ACS 4.16 and Linstor. As soon as we > finish the tests we can give you some approach for the results. Are someone > already try this technology?. > > Regards, > > El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: > > Since NFS alone doesn't offer HA. What do you recommend for HA NFS? > > > > On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: > > > >> I have similar consideration when start exploring Cloudstack , but > >> in reality Clustered Filesystem is not easy to maintain. You seems > >> have choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat > >> , ocfs recently only maintained in oracle linux. I believe you do not > want to > >> choose solution that is very propriety . Thus just SAN or ISCSI o is > not > >> really a direct solution here , except you want to encapsulate it in > >> NFS and facing Cloudstack Storage. > >> > >> It work good on CEPH and NFS , but performance wise, NFS is better . > >> And all documentation and features you saw in Cloudstack , it work > >> perfectly on NFS. > >> > >> If you choose CEPH, may be you have to compensate with some > >> performance degradation, > >> > >> > >> > >> On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes > >> > >> wrote: > >> > >>> I've been using Ceph in prod for volumes for some time. Note that > >> although > >>> I had several cloudstack installations, this one runs on top of > >>> Cinder, but it basic translates as libvirt and rados. > >>> > >>> It is totally stable and performance IMHO is enough for virtualized > >>> services. > >>> > >>> IO might suffer some penalization due the data replication inside Ceph. > >>> Elasticsearch for instance, the degradation would be a bit worse as > >>> there is replication also in the application size, but IMHO, unless > >>> you need extreme low latency it would be ok. > >>> > >>> > >>> Best, > >>> > >>> Leandro. > >>> > >>> On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < > >> michael.bru...@nttdata.com > >>> wrote: > >>> > Hello community, > > today I need your experience and knowhow about clustered/shared > filesystems based on SAN storage to be used with KVM. > We need to consider about a clustered/shared filesystem based on > SAN storage (no NFS or iSCSI), but do not have any knowhow or > experience > >> with > this. > Those I would like to ask if there any productive used environments > out there based on SAN storage on KVM? > If so, which clustered/shared filesystem you are using and how is > your experience with that (stability, reliability, maintainability, > >>> performance, > useability,...)? > Furthermore, if you had already to consider in the past between SAN > storage or CEPH, I would also like to participate on your > >> considerations > and results :) > > Regards, > Michael > > >> > >> -- > >> Regards, > >> Hean Seng > >> > > > > -- Regards, Hean Seng
RE: Experience with clustered/shared filesystems based on SAN storage on KVM?
Hi So we plan to use linstor in parallel to ceph as a fast resource on nvme cards. Its advantage is that it natively supports zfs with deduplication and compression :-) The test results were more than passable. Regards, Piotr -Original Message- From: Mauro Ferraro - G2K Hosting Sent: Thursday, October 28, 2021 2:02 PM To: users@cloudstack.apache.org; Pratik Chandrakar Subject: Re: Experience with clustered/shared filesystems based on SAN storage on KVM? Hi, We are trying to make a lab with ACS 4.16 and Linstor. As soon as we finish the tests we can give you some approach for the results. Are someone already try this technology?. Regards, El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: > Since NFS alone doesn't offer HA. What do you recommend for HA NFS? > > On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: > >> I have similar consideration when start exploring Cloudstack , but >> in reality Clustered Filesystem is not easy to maintain. You seems >> have choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat >> , ocfs recently only maintained in oracle linux. I believe you do not want >> to >> choose solution that is very propriety . Thus just SAN or ISCSI o is not >> really a direct solution here , except you want to encapsulate it in >> NFS and facing Cloudstack Storage. >> >> It work good on CEPH and NFS , but performance wise, NFS is better . >> And all documentation and features you saw in Cloudstack , it work >> perfectly on NFS. >> >> If you choose CEPH, may be you have to compensate with some >> performance degradation, >> >> >> >> On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes >> >> wrote: >> >>> I've been using Ceph in prod for volumes for some time. Note that >> although >>> I had several cloudstack installations, this one runs on top of >>> Cinder, but it basic translates as libvirt and rados. >>> >>> It is totally stable and performance IMHO is enough for virtualized >>> services. >>> >>> IO might suffer some penalization due the data replication inside Ceph. >>> Elasticsearch for instance, the degradation would be a bit worse as >>> there is replication also in the application size, but IMHO, unless >>> you need extreme low latency it would be ok. >>> >>> >>> Best, >>> >>> Leandro. >>> >>> On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < >> michael.bru...@nttdata.com >>> wrote: >>> Hello community, today I need your experience and knowhow about clustered/shared filesystems based on SAN storage to be used with KVM. We need to consider about a clustered/shared filesystem based on SAN storage (no NFS or iSCSI), but do not have any knowhow or experience >> with this. Those I would like to ask if there any productive used environments out there based on SAN storage on KVM? If so, which clustered/shared filesystem you are using and how is your experience with that (stability, reliability, maintainability, >>> performance, useability,...)? Furthermore, if you had already to consider in the past between SAN storage or CEPH, I would also like to participate on your >> considerations and results :) Regards, Michael >> >> -- >> Regards, >> Hean Seng >> >
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Hi, We are trying to make a lab with ACS 4.16 and Linstor. As soon as we finish the tests we can give you some approach for the results. Are someone already try this technology?. Regards, El 28/10/2021 a las 02:34, Pratik Chandrakar escribió: Since NFS alone doesn't offer HA. What do you recommend for HA NFS? On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: I have similar consideration when start exploring Cloudstack , but in reality Clustered Filesystem is not easy to maintain. You seems have choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs recently only maintained in oracle linux. I believe you do not want to choose solution that is very propriety . Thus just SAN or ISCSI o is not really a direct solution here , except you want to encapsulate it in NFS and facing Cloudstack Storage. It work good on CEPH and NFS , but performance wise, NFS is better . And all documentation and features you saw in Cloudstack , it work perfectly on NFS. If you choose CEPH, may be you have to compensate with some performance degradation, On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes wrote: I've been using Ceph in prod for volumes for some time. Note that although I had several cloudstack installations, this one runs on top of Cinder, but it basic translates as libvirt and rados. It is totally stable and performance IMHO is enough for virtualized services. IO might suffer some penalization due the data replication inside Ceph. Elasticsearch for instance, the degradation would be a bit worse as there is replication also in the application size, but IMHO, unless you need extreme low latency it would be ok. Best, Leandro. On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < michael.bru...@nttdata.com wrote: Hello community, today I need your experience and knowhow about clustered/shared filesystems based on SAN storage to be used with KVM. We need to consider about a clustered/shared filesystem based on SAN storage (no NFS or iSCSI), but do not have any knowhow or experience with this. Those I would like to ask if there any productive used environments out there based on SAN storage on KVM? If so, which clustered/shared filesystem you are using and how is your experience with that (stability, reliability, maintainability, performance, useability,...)? Furthermore, if you had already to consider in the past between SAN storage or CEPH, I would also like to participate on your considerations and results :) Regards, Michael -- Regards, Hean Seng
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
Since NFS alone doesn't offer HA. What do you recommend for HA NFS? On Thu, Oct 28, 2021 at 7:37 AM Hean Seng wrote: > I have similar consideration when start exploring Cloudstack , but in > reality Clustered Filesystem is not easy to maintain. You seems have > choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs > recently only maintained in oracle linux. I believe you do not want to > choose solution that is very propriety . Thus just SAN or ISCSI o is not > really a direct solution here , except you want to encapsulate it in NFS > and facing Cloudstack Storage. > > It work good on CEPH and NFS , but performance wise, NFS is better . And > all documentation and features you saw in Cloudstack , it work perfectly > on NFS. > > If you choose CEPH, may be you have to compensate with some performance > degradation, > > > > On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes > wrote: > > > I've been using Ceph in prod for volumes for some time. Note that > although > > I had several cloudstack installations, this one runs on top of Cinder, > > but it basic translates as libvirt and rados. > > > > It is totally stable and performance IMHO is enough for virtualized > > services. > > > > IO might suffer some penalization due the data replication inside Ceph. > > Elasticsearch for instance, the degradation would be a bit worse as there > > is replication also in the application size, but IMHO, unless you need > > extreme low latency it would be ok. > > > > > > Best, > > > > Leandro. > > > > On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael < > michael.bru...@nttdata.com > > > > > wrote: > > > > > Hello community, > > > > > > today I need your experience and knowhow about clustered/shared > > > filesystems based on SAN storage to be used with KVM. > > > We need to consider about a clustered/shared filesystem based on SAN > > > storage (no NFS or iSCSI), but do not have any knowhow or experience > with > > > this. > > > Those I would like to ask if there any productive used environments out > > > there based on SAN storage on KVM? > > > If so, which clustered/shared filesystem you are using and how is your > > > experience with that (stability, reliability, maintainability, > > performance, > > > useability,...)? > > > Furthermore, if you had already to consider in the past between SAN > > > storage or CEPH, I would also like to participate on your > considerations > > > and results :) > > > > > > Regards, > > > Michael > > > > > > > > -- > Regards, > Hean Seng > -- *Regards,* *Pratik Chandrakar*
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
I have similar consideration when start exploring Cloudstack , but in reality Clustered Filesystem is not easy to maintain. You seems have choice of OCFS or GFS2 , gfs2 is hard to maintain and in redhat , ocfs recently only maintained in oracle linux. I believe you do not want to choose solution that is very propriety . Thus just SAN or ISCSI o is not really a direct solution here , except you want to encapsulate it in NFS and facing Cloudstack Storage. It work good on CEPH and NFS , but performance wise, NFS is better . And all documentation and features you saw in Cloudstack , it work perfectly on NFS. If you choose CEPH, may be you have to compensate with some performance degradation, On Thu, Oct 28, 2021 at 12:44 AM Leandro Mendes wrote: > I've been using Ceph in prod for volumes for some time. Note that although > I had several cloudstack installations, this one runs on top of Cinder, > but it basic translates as libvirt and rados. > > It is totally stable and performance IMHO is enough for virtualized > services. > > IO might suffer some penalization due the data replication inside Ceph. > Elasticsearch for instance, the degradation would be a bit worse as there > is replication also in the application size, but IMHO, unless you need > extreme low latency it would be ok. > > > Best, > > Leandro. > > On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael > > wrote: > > > Hello community, > > > > today I need your experience and knowhow about clustered/shared > > filesystems based on SAN storage to be used with KVM. > > We need to consider about a clustered/shared filesystem based on SAN > > storage (no NFS or iSCSI), but do not have any knowhow or experience with > > this. > > Those I would like to ask if there any productive used environments out > > there based on SAN storage on KVM? > > If so, which clustered/shared filesystem you are using and how is your > > experience with that (stability, reliability, maintainability, > performance, > > useability,...)? > > Furthermore, if you had already to consider in the past between SAN > > storage or CEPH, I would also like to participate on your considerations > > and results :) > > > > Regards, > > Michael > > > -- Regards, Hean Seng
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
I've been using Ceph in prod for volumes for some time. Note that although I had several cloudstack installations, this one runs on top of Cinder, but it basic translates as libvirt and rados. It is totally stable and performance IMHO is enough for virtualized services. IO might suffer some penalization due the data replication inside Ceph. Elasticsearch for instance, the degradation would be a bit worse as there is replication also in the application size, but IMHO, unless you need extreme low latency it would be ok. Best, Leandro. On Thu, Oct 21, 2021, 11:20 AM Brussk, Michael wrote: > Hello community, > > today I need your experience and knowhow about clustered/shared > filesystems based on SAN storage to be used with KVM. > We need to consider about a clustered/shared filesystem based on SAN > storage (no NFS or iSCSI), but do not have any knowhow or experience with > this. > Those I would like to ask if there any productive used environments out > there based on SAN storage on KVM? > If so, which clustered/shared filesystem you are using and how is your > experience with that (stability, reliability, maintainability, performance, > useability,...)? > Furthermore, if you had already to consider in the past between SAN > storage or CEPH, I would also like to participate on your considerations > and results :) > > Regards, > Michael >
Re: Experience with clustered/shared filesystems based on SAN storage on KVM?
a.v.o.i.d = due to clustered file system stability... CEPH = an awful of knowledge required to have this in production - and definitively a much better/stable choice than clustered file systems. Best, On Thu, 21 Oct 2021 at 11:20, Brussk, Michael wrote: > Hello community, > > today I need your experience and knowhow about clustered/shared > filesystems based on SAN storage to be used with KVM. > We need to consider about a clustered/shared filesystem based on SAN > storage (no NFS or iSCSI), but do not have any knowhow or experience with > this. > Those I would like to ask if there any productive used environments out > there based on SAN storage on KVM? > If so, which clustered/shared filesystem you are using and how is your > experience with that (stability, reliability, maintainability, performance, > useability,...)? > Furthermore, if you had already to consider in the past between SAN > storage or CEPH, I would also like to participate on your considerations > and results :) > > Regards, > Michael > -- Andrija Panić
Experience with clustered/shared filesystems based on SAN storage on KVM?
Hello community, today I need your experience and knowhow about clustered/shared filesystems based on SAN storage to be used with KVM. We need to consider about a clustered/shared filesystem based on SAN storage (no NFS or iSCSI), but do not have any knowhow or experience with this. Those I would like to ask if there any productive used environments out there based on SAN storage on KVM? If so, which clustered/shared filesystem you are using and how is your experience with that (stability, reliability, maintainability, performance, useability,...)? Furthermore, if you had already to consider in the past between SAN storage or CEPH, I would also like to participate on your considerations and results :) Regards, Michael