Re: [ceph-users] CEPH_FSAL Nfs-ganesha
Do can you do HA on the NFS shares? On Wed, Jan 30, 2019 at 9:10 AM David C wrote: > Hi Patrick > > Thanks for the info. If I did multiple exports, how does that work in > terms of the cache settings defined in ceph.conf, are those settings per > CephFS client or a shared cache? I.e if I've definied client_oc_size, would > that be per export? > > Cheers, > > On Tue, Jan 15, 2019 at 6:47 PM Patrick Donnelly > wrote: > >> On Mon, Jan 14, 2019 at 7:11 AM Daniel Gryniewicz >> wrote: >> > >> > Hi. Welcome to the community. >> > >> > On 01/14/2019 07:56 AM, David C wrote: >> > > Hi All >> > > >> > > I've been playing around with the nfs-ganesha 2.7 exporting a cephfs >> > > filesystem, it seems to be working pretty well so far. A few >> questions: >> > > >> > > 1) The docs say " For each NFS-Ganesha export, FSAL_CEPH uses a >> > > libcephfs client,..." [1]. For arguments sake, if I have ten top level >> > > dirs in my Cephfs namespace, is there any value in creating a separate >> > > export for each directory? Will that potentially give me better >> > > performance than a single export of the entire namespace? >> > >> > I don't believe there are any advantages from the Ceph side. From the >> > Ganesha side, you configure permissions, client ACLs, squashing, and so >> > on on a per-export basis, so you'll need different exports if you need >> > different settings for each top level directory. If they can all use >> > the same settings, one export is probably better. >> >> There may be performance impact (good or bad) with having separate >> exports for CephFS. Each export instantiates a separate instance of >> the CephFS client which has its own bookkeeping and set of >> capabilities issued by the MDS. Also, each client instance has a >> separate big lock (potentially a big deal for performance). If the >> data for each export is disjoint (no hard links or shared inodes) and >> the NFS server is expected to have a lot of load, breaking out the >> exports can have a positive impact on performance. If there are hard >> links, then the clients associated with the exports will potentially >> fight over capabilities which will add to request latency.) >> >> -- >> Patrick Donnelly >> ___ >> ceph-users mailing list >> ceph-users@lists.ceph.com >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CEPH_FSAL Nfs-ganesha
Hi Patrick Thanks for the info. If I did multiple exports, how does that work in terms of the cache settings defined in ceph.conf, are those settings per CephFS client or a shared cache? I.e if I've definied client_oc_size, would that be per export? Cheers, On Tue, Jan 15, 2019 at 6:47 PM Patrick Donnelly wrote: > On Mon, Jan 14, 2019 at 7:11 AM Daniel Gryniewicz wrote: > > > > Hi. Welcome to the community. > > > > On 01/14/2019 07:56 AM, David C wrote: > > > Hi All > > > > > > I've been playing around with the nfs-ganesha 2.7 exporting a cephfs > > > filesystem, it seems to be working pretty well so far. A few questions: > > > > > > 1) The docs say " For each NFS-Ganesha export, FSAL_CEPH uses a > > > libcephfs client,..." [1]. For arguments sake, if I have ten top level > > > dirs in my Cephfs namespace, is there any value in creating a separate > > > export for each directory? Will that potentially give me better > > > performance than a single export of the entire namespace? > > > > I don't believe there are any advantages from the Ceph side. From the > > Ganesha side, you configure permissions, client ACLs, squashing, and so > > on on a per-export basis, so you'll need different exports if you need > > different settings for each top level directory. If they can all use > > the same settings, one export is probably better. > > There may be performance impact (good or bad) with having separate > exports for CephFS. Each export instantiates a separate instance of > the CephFS client which has its own bookkeeping and set of > capabilities issued by the MDS. Also, each client instance has a > separate big lock (potentially a big deal for performance). If the > data for each export is disjoint (no hard links or shared inodes) and > the NFS server is expected to have a lot of load, breaking out the > exports can have a positive impact on performance. If there are hard > links, then the clients associated with the exports will potentially > fight over capabilities which will add to request latency.) > > -- > Patrick Donnelly > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CEPH_FSAL Nfs-ganesha
On Mon, Jan 14, 2019 at 7:11 AM Daniel Gryniewicz wrote: > > Hi. Welcome to the community. > > On 01/14/2019 07:56 AM, David C wrote: > > Hi All > > > > I've been playing around with the nfs-ganesha 2.7 exporting a cephfs > > filesystem, it seems to be working pretty well so far. A few questions: > > > > 1) The docs say " For each NFS-Ganesha export, FSAL_CEPH uses a > > libcephfs client,..." [1]. For arguments sake, if I have ten top level > > dirs in my Cephfs namespace, is there any value in creating a separate > > export for each directory? Will that potentially give me better > > performance than a single export of the entire namespace? > > I don't believe there are any advantages from the Ceph side. From the > Ganesha side, you configure permissions, client ACLs, squashing, and so > on on a per-export basis, so you'll need different exports if you need > different settings for each top level directory. If they can all use > the same settings, one export is probably better. There may be performance impact (good or bad) with having separate exports for CephFS. Each export instantiates a separate instance of the CephFS client which has its own bookkeeping and set of capabilities issued by the MDS. Also, each client instance has a separate big lock (potentially a big deal for performance). If the data for each export is disjoint (no hard links or shared inodes) and the NFS server is expected to have a lot of load, breaking out the exports can have a positive impact on performance. If there are hard links, then the clients associated with the exports will potentially fight over capabilities which will add to request latency.) -- Patrick Donnelly ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CEPH_FSAL Nfs-ganesha
We've found that more aggressive prefetching in the Ceph client can help with some poorly behaving legacy applications (don't know the option off the top of my head but it's documented). It can also be useful to disable logging (even the in-memory logs) if you do a lot IOPS (that's debug client and debug ms mostly). Paul -- Paul Emmerich Looking for help with your Ceph cluster? Contact us at https://croit.io croit GmbH Freseniusstr. 31h 81247 München www.croit.io Tel: +49 89 1896585 90 On Mon, Jan 14, 2019 at 4:11 PM Daniel Gryniewicz wrote: > > Hi. Welcome to the community. > > On 01/14/2019 07:56 AM, David C wrote: > > Hi All > > > > I've been playing around with the nfs-ganesha 2.7 exporting a cephfs > > filesystem, it seems to be working pretty well so far. A few questions: > > > > 1) The docs say " For each NFS-Ganesha export, FSAL_CEPH uses a > > libcephfs client,..." [1]. For arguments sake, if I have ten top level > > dirs in my Cephfs namespace, is there any value in creating a separate > > export for each directory? Will that potentially give me better > > performance than a single export of the entire namespace? > > I don't believe there are any advantages from the Ceph side. From the > Ganesha side, you configure permissions, client ACLs, squashing, and so > on on a per-export basis, so you'll need different exports if you need > different settings for each top level directory. If they can all use > the same settings, one export is probably better. > > > > > 2) Tuning: are there any recommended parameters to tune? So far I've > > found I had to increase client_oc_size which seemed quite conservative. > > Ganesha is just a standard libcephfs client, so any tuning you'd make on > any other cephfs client also applies to Ganesha. I'm not aware of > anything in particular, but I've never deployed it for anything other > than testing. > > Daniel > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CEPH_FSAL Nfs-ganesha
Hi. Welcome to the community. On 01/14/2019 07:56 AM, David C wrote: Hi All I've been playing around with the nfs-ganesha 2.7 exporting a cephfs filesystem, it seems to be working pretty well so far. A few questions: 1) The docs say " For each NFS-Ganesha export, FSAL_CEPH uses a libcephfs client,..." [1]. For arguments sake, if I have ten top level dirs in my Cephfs namespace, is there any value in creating a separate export for each directory? Will that potentially give me better performance than a single export of the entire namespace? I don't believe there are any advantages from the Ceph side. From the Ganesha side, you configure permissions, client ACLs, squashing, and so on on a per-export basis, so you'll need different exports if you need different settings for each top level directory. If they can all use the same settings, one export is probably better. 2) Tuning: are there any recommended parameters to tune? So far I've found I had to increase client_oc_size which seemed quite conservative. Ganesha is just a standard libcephfs client, so any tuning you'd make on any other cephfs client also applies to Ganesha. I'm not aware of anything in particular, but I've never deployed it for anything other than testing. Daniel ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] CEPH_FSAL Nfs-ganesha
Hi All I've been playing around with the nfs-ganesha 2.7 exporting a cephfs filesystem, it seems to be working pretty well so far. A few questions: 1) The docs say " For each NFS-Ganesha export, FSAL_CEPH uses a libcephfs client,..." [1]. For arguments sake, if I have ten top level dirs in my Cephfs namespace, is there any value in creating a separate export for each directory? Will that potentially give me better performance than a single export of the entire namespace? 2) Tuning: are there any recommended parameters to tune? So far I've found I had to increase client_oc_size which seemed quite conservative. Thanks David [1] http://docs.ceph.com/docs/mimic/cephfs/nfs/ ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com