* CephFS + Erasure coding @ 2015-04-30 20:55 Somnath Roy 2015-04-30 21:20 ` Gregory Farnum 0 siblings, 1 reply; 11+ messages in thread From: Somnath Roy @ 2015-04-30 20:55 UTC (permalink / raw) To: ceph-devel Hi Greg, Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? If not, is there any plan of supporting this kind of configuration in near future ? Thanks & Regards Somnath ________________________________ PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). ^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: CephFS + Erasure coding 2015-04-30 20:55 CephFS + Erasure coding Somnath Roy @ 2015-04-30 21:20 ` Gregory Farnum 2015-04-30 21:27 ` Somnath Roy 0 siblings, 1 reply; 11+ messages in thread From: Gregory Farnum @ 2015-04-30 21:20 UTC (permalink / raw) To: Somnath Roy; +Cc: ceph-devel On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: CephFS + Erasure coding 2015-04-30 21:20 ` Gregory Farnum @ 2015-04-30 21:27 ` Somnath Roy 2015-04-30 21:57 ` Somnath Roy 0 siblings, 1 reply; 11+ messages in thread From: Somnath Roy @ 2015-04-30 21:27 UTC (permalink / raw) To: Gregory Farnum; +Cc: ceph-devel Got it , thanks ! -----Original Message----- From: Gregory Farnum [mailto:greg@gregs42.com] Sent: Thursday, April 30, 2015 2:21 PM To: Somnath Roy Cc: ceph-devel Subject: Re: CephFS + Erasure coding On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" > in the body of a message to majordomo@vger.kernel.org More majordomo > info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: CephFS + Erasure coding 2015-04-30 21:27 ` Somnath Roy @ 2015-04-30 21:57 ` Somnath Roy 2015-04-30 22:00 ` Gregory Farnum 2015-05-06 2:42 ` Wang, Zhiqiang 0 siblings, 2 replies; 11+ messages in thread From: Somnath Roy @ 2015-04-30 21:57 UTC (permalink / raw) To: Gregory Farnum; +Cc: ceph-devel Greg, Probably not supported right now, but, wanted to confirm if there is any way we can use Ceph cache tier for only writes and reads are forwarded to the backend erasure coded pool. Thanks & Regards Somnath -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Thursday, April 30, 2015 2:28 PM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Got it , thanks ! -----Original Message----- From: Gregory Farnum [mailto:greg@gregs42.com] Sent: Thursday, April 30, 2015 2:21 PM To: Somnath Roy Cc: ceph-devel Subject: Re: CephFS + Erasure coding On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" > in the body of a message to majordomo@vger.kernel.org More majordomo > info at http://vger.kernel.org/majordomo-info.html \x04 {.n + +% lzwm b 맲 r yǩ ׯzX \x17 ܨ} Ơz &j:+v zZ+ +zf h ~ i z \x1e w ? & )ߢ^[f ^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: CephFS + Erasure coding 2015-04-30 21:57 ` Somnath Roy @ 2015-04-30 22:00 ` Gregory Farnum 2015-05-06 2:42 ` Wang, Zhiqiang 1 sibling, 0 replies; 11+ messages in thread From: Gregory Farnum @ 2015-04-30 22:00 UTC (permalink / raw) To: Somnath Roy; +Cc: ceph-devel On Thu, Apr 30, 2015 at 2:57 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Greg, > Probably not supported right now, but, wanted to confirm if there is any way we can use Ceph cache tier for only writes and reads are forwarded to the backend erasure coded pool. Anything like that would be based on what librados does; CephFS can't do anything special there. I'm not following the proxy changes and things that are being done now in any detail. ^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: CephFS + Erasure coding 2015-04-30 21:57 ` Somnath Roy 2015-04-30 22:00 ` Gregory Farnum @ 2015-05-06 2:42 ` Wang, Zhiqiang 2015-05-06 4:17 ` Somnath Roy 1 sibling, 1 reply; 11+ messages in thread From: Wang, Zhiqiang @ 2015-05-06 2:42 UTC (permalink / raw) To: Somnath Roy, Gregory Farnum; +Cc: ceph-devel I think the readproxy mode is what you need. Read is proxied to the base tier, and write is on the cache tier. -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Friday, May 1, 2015 5:58 AM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Greg, Probably not supported right now, but, wanted to confirm if there is any way we can use Ceph cache tier for only writes and reads are forwarded to the backend erasure coded pool. Thanks & Regards Somnath -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Thursday, April 30, 2015 2:28 PM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Got it , thanks ! -----Original Message----- From: Gregory Farnum [mailto:greg@gregs42.com] Sent: Thursday, April 30, 2015 2:21 PM To: Somnath Roy Cc: ceph-devel Subject: Re: CephFS + Erasure coding On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" > in the body of a message to majordomo@vger.kernel.org More majordomo > info at http://vger.kernel.org/majordomo-info.html \x04 {.n + +% lzwm b 맲 r yǩ ׯzX \x17 ܨ} Ơz &j:+v zZ+ +zf h ~ i z \x1e w ? & )ߢ^[f N r y b X ǧv ^ ){.n + z ]z {ay \x1dʇڙ ,j f h z \x1e w j:+v w j m zZ+ ݢj" ! i ^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: CephFS + Erasure coding 2015-05-06 2:42 ` Wang, Zhiqiang @ 2015-05-06 4:17 ` Somnath Roy 2015-05-06 4:29 ` Wang, Zhiqiang 0 siblings, 1 reply; 11+ messages in thread From: Somnath Roy @ 2015-05-06 4:17 UTC (permalink / raw) To: Wang, Zhiqiang, Gregory Farnum; +Cc: ceph-devel Thanks Wang ! But, is this supported right now or coming with object stub implementation in Infernalis ? Regards Somnath -----Original Message----- From: Wang, Zhiqiang [mailto:zhiqiang.wang@intel.com] Sent: Tuesday, May 05, 2015 7:42 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding I think the readproxy mode is what you need. Read is proxied to the base tier, and write is on the cache tier. -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Friday, May 1, 2015 5:58 AM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Greg, Probably not supported right now, but, wanted to confirm if there is any way we can use Ceph cache tier for only writes and reads are forwarded to the backend erasure coded pool. Thanks & Regards Somnath -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Thursday, April 30, 2015 2:28 PM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Got it , thanks ! -----Original Message----- From: Gregory Farnum [mailto:greg@gregs42.com] Sent: Thursday, April 30, 2015 2:21 PM To: Somnath Roy Cc: ceph-devel Subject: Re: CephFS + Erasure coding On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" > in the body of a message to majordomo@vger.kernel.org More majordomo > info at http://vger.kernel.org/majordomo-info.html \x04 {.n + +% lzwm b 맲 r yǩ ׯzX \x17 ܨ} Ơz &j:+v zZ+ +zf h ~ i z \x1e w ? & )ߢ^[f N r y b X ǧv ^ ){.n + z ]z {ay \x1dʇڙ ,j f h z \x1e w j:+v w j m zZ+ ݢj" ! i ^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: CephFS + Erasure coding 2015-05-06 4:17 ` Somnath Roy @ 2015-05-06 4:29 ` Wang, Zhiqiang 2015-05-06 4:32 ` Somnath Roy 0 siblings, 1 reply; 11+ messages in thread From: Wang, Zhiqiang @ 2015-05-06 4:29 UTC (permalink / raw) To: Somnath Roy, Gregory Farnum; +Cc: ceph-devel This has been in the Hammer release when the proxy read code get merged in. -----Original Message----- From: Somnath Roy [mailto:Somnath.Roy@sandisk.com] Sent: Wednesday, May 6, 2015 12:17 PM To: Wang, Zhiqiang; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Thanks Wang ! But, is this supported right now or coming with object stub implementation in Infernalis ? Regards Somnath -----Original Message----- From: Wang, Zhiqiang [mailto:zhiqiang.wang@intel.com] Sent: Tuesday, May 05, 2015 7:42 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding I think the readproxy mode is what you need. Read is proxied to the base tier, and write is on the cache tier. -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Friday, May 1, 2015 5:58 AM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Greg, Probably not supported right now, but, wanted to confirm if there is any way we can use Ceph cache tier for only writes and reads are forwarded to the backend erasure coded pool. Thanks & Regards Somnath -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Thursday, April 30, 2015 2:28 PM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Got it , thanks ! -----Original Message----- From: Gregory Farnum [mailto:greg@gregs42.com] Sent: Thursday, April 30, 2015 2:21 PM To: Somnath Roy Cc: ceph-devel Subject: Re: CephFS + Erasure coding On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" > in the body of a message to majordomo@vger.kernel.org More majordomo > info at http://vger.kernel.org/majordomo-info.html \x04 {.n + +% lzwm b 맲 r yǩ ׯzX \x17 ܨ} Ơz &j:+v zZ+ +zf h ~ i z \x1e w ? & )ߢ^[f N r y b X ǧv ^ ){.n + z ]z {ay \x1dʇڙ ,j f h z \x1e w j:+v w j m zZ+ ݢj" ! i ^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: CephFS + Erasure coding 2015-05-06 4:29 ` Wang, Zhiqiang @ 2015-05-06 4:32 ` Somnath Roy 2015-05-06 4:39 ` Wang, Zhiqiang 0 siblings, 1 reply; 11+ messages in thread From: Somnath Roy @ 2015-05-06 4:32 UTC (permalink / raw) To: Wang, Zhiqiang, Gregory Farnum; +Cc: ceph-devel I didn't see (probably missed ?) any documentation on how to setup read proxy mode in the cache tier. Could you please let me know or point to the link on how to set this up ? Thanks & Regards Somnath -----Original Message----- From: Wang, Zhiqiang [mailto:zhiqiang.wang@intel.com] Sent: Tuesday, May 05, 2015 9:30 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding This has been in the Hammer release when the proxy read code get merged in. -----Original Message----- From: Somnath Roy [mailto:Somnath.Roy@sandisk.com] Sent: Wednesday, May 6, 2015 12:17 PM To: Wang, Zhiqiang; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Thanks Wang ! But, is this supported right now or coming with object stub implementation in Infernalis ? Regards Somnath -----Original Message----- From: Wang, Zhiqiang [mailto:zhiqiang.wang@intel.com] Sent: Tuesday, May 05, 2015 7:42 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding I think the readproxy mode is what you need. Read is proxied to the base tier, and write is on the cache tier. -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Friday, May 1, 2015 5:58 AM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Greg, Probably not supported right now, but, wanted to confirm if there is any way we can use Ceph cache tier for only writes and reads are forwarded to the backend erasure coded pool. Thanks & Regards Somnath -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Thursday, April 30, 2015 2:28 PM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Got it , thanks ! -----Original Message----- From: Gregory Farnum [mailto:greg@gregs42.com] Sent: Thursday, April 30, 2015 2:21 PM To: Somnath Roy Cc: ceph-devel Subject: Re: CephFS + Erasure coding On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" > in the body of a message to majordomo@vger.kernel.org More majordomo > info at http://vger.kernel.org/majordomo-info.html \x04 {.n + +% lzwm b 맲 r yǩ ׯzX \x17 ܨ} Ơz &j:+v zZ+ +zf h ~ i z \x1e w ? & )ߢ^[f N r y b X ǧv ^ ){.n + z ]z {ay \x1dʇڙ ,j f h z \x1e w j:+v w j m zZ+ ݢj" ! i ^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: CephFS + Erasure coding 2015-05-06 4:32 ` Somnath Roy @ 2015-05-06 4:39 ` Wang, Zhiqiang 2015-05-06 5:03 ` Somnath Roy 0 siblings, 1 reply; 11+ messages in thread From: Wang, Zhiqiang @ 2015-05-06 4:39 UTC (permalink / raw) To: Somnath Roy, Gregory Farnum; +Cc: ceph-devel Just follow the steps in the official doc here: http://ceph.com/docs/master/rados/operations/cache-tiering/ But change the cache mode to readproxy when setting cache-mode -----Original Message----- From: Somnath Roy [mailto:Somnath.Roy@sandisk.com] Sent: Wednesday, May 6, 2015 12:33 PM To: Wang, Zhiqiang; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding I didn't see (probably missed ?) any documentation on how to setup read proxy mode in the cache tier. Could you please let me know or point to the link on how to set this up ? Thanks & Regards Somnath -----Original Message----- From: Wang, Zhiqiang [mailto:zhiqiang.wang@intel.com] Sent: Tuesday, May 05, 2015 9:30 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding This has been in the Hammer release when the proxy read code get merged in. -----Original Message----- From: Somnath Roy [mailto:Somnath.Roy@sandisk.com] Sent: Wednesday, May 6, 2015 12:17 PM To: Wang, Zhiqiang; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Thanks Wang ! But, is this supported right now or coming with object stub implementation in Infernalis ? Regards Somnath -----Original Message----- From: Wang, Zhiqiang [mailto:zhiqiang.wang@intel.com] Sent: Tuesday, May 05, 2015 7:42 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding I think the readproxy mode is what you need. Read is proxied to the base tier, and write is on the cache tier. -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Friday, May 1, 2015 5:58 AM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Greg, Probably not supported right now, but, wanted to confirm if there is any way we can use Ceph cache tier for only writes and reads are forwarded to the backend erasure coded pool. Thanks & Regards Somnath -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Thursday, April 30, 2015 2:28 PM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Got it , thanks ! -----Original Message----- From: Gregory Farnum [mailto:greg@gregs42.com] Sent: Thursday, April 30, 2015 2:21 PM To: Somnath Roy Cc: ceph-devel Subject: Re: CephFS + Erasure coding On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" > in the body of a message to majordomo@vger.kernel.org More majordomo > info at http://vger.kernel.org/majordomo-info.html \x04 {.n + +% lzwm b 맲 r yǩ ׯzX \x17 ܨ} Ơz &j:+v zZ+ +zf h ~ i z \x1e w ? & )ߢ^[f N r y b X ǧv ^ ){.n + z ]z {ay \x1dʇڙ ,j f h z \x1e w j:+v w j m zZ+ ݢj" ! i ^ permalink raw reply [flat|nested] 11+ messages in thread
* RE: CephFS + Erasure coding 2015-05-06 4:39 ` Wang, Zhiqiang @ 2015-05-06 5:03 ` Somnath Roy 0 siblings, 0 replies; 11+ messages in thread From: Somnath Roy @ 2015-05-06 5:03 UTC (permalink / raw) To: Wang, Zhiqiang, Gregory Farnum; +Cc: ceph-devel Thanks Wang ! I will try this out. Regards Somnath -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Wang, Zhiqiang Sent: Tuesday, May 05, 2015 9:39 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Just follow the steps in the official doc here: http://ceph.com/docs/master/rados/operations/cache-tiering/ But change the cache mode to readproxy when setting cache-mode -----Original Message----- From: Somnath Roy [mailto:Somnath.Roy@sandisk.com] Sent: Wednesday, May 6, 2015 12:33 PM To: Wang, Zhiqiang; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding I didn't see (probably missed ?) any documentation on how to setup read proxy mode in the cache tier. Could you please let me know or point to the link on how to set this up ? Thanks & Regards Somnath -----Original Message----- From: Wang, Zhiqiang [mailto:zhiqiang.wang@intel.com] Sent: Tuesday, May 05, 2015 9:30 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding This has been in the Hammer release when the proxy read code get merged in. -----Original Message----- From: Somnath Roy [mailto:Somnath.Roy@sandisk.com] Sent: Wednesday, May 6, 2015 12:17 PM To: Wang, Zhiqiang; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Thanks Wang ! But, is this supported right now or coming with object stub implementation in Infernalis ? Regards Somnath -----Original Message----- From: Wang, Zhiqiang [mailto:zhiqiang.wang@intel.com] Sent: Tuesday, May 05, 2015 7:42 PM To: Somnath Roy; Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding I think the readproxy mode is what you need. Read is proxied to the base tier, and write is on the cache tier. -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Friday, May 1, 2015 5:58 AM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Greg, Probably not supported right now, but, wanted to confirm if there is any way we can use Ceph cache tier for only writes and reads are forwarded to the backend erasure coded pool. Thanks & Regards Somnath -----Original Message----- From: ceph-devel-owner@vger.kernel.org [mailto:ceph-devel-owner@vger.kernel.org] On Behalf Of Somnath Roy Sent: Thursday, April 30, 2015 2:28 PM To: Gregory Farnum Cc: ceph-devel Subject: RE: CephFS + Erasure coding Got it , thanks ! -----Original Message----- From: Gregory Farnum [mailto:greg@gregs42.com] Sent: Thursday, April 30, 2015 2:21 PM To: Somnath Roy Cc: ceph-devel Subject: Re: CephFS + Erasure coding On Thu, Apr 30, 2015 at 1:55 PM, Somnath Roy <Somnath.Roy@sandisk.com> wrote: > Hi Greg, > Forgive my ignorance on this part if it is already discussed in the community. Could you please let me know if CephFS is supporting Erasure coded pool in the backend or not ? > If not, is there any plan of supporting this kind of configuration in near future ? You can set replicated cache pools, positioned as tiers over an EC pool, as data pools for CephFS. You cannot use EC pools directly for CephFS. We have no plans to add support for EC pools in the foreseeable future — since they have limited RADOS functionality we'd need to implement a whole log-structured file storage system or something. :( -Greg > > Thanks & Regards > Somnath > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is intended only for the use of the designated recipient(s) named above. If the reader of this message is not the intended recipient, you are hereby notified that you have received this message in error and that any review, dissemination, distribution, or copying of this message is strictly prohibited. If you have received this communication in error, please notify the sender by telephone or e-mail (as shown above) immediately and destroy any and all copies of this message in your possession (whether hard copies or electronically stored copies). > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" > in the body of a message to majordomo@vger.kernel.org More majordomo > info at http://vger.kernel.org/majordomo-info.html \x04 {.n + +% lzwm b 맲 r yǩ ׯzX \x17 ܨ} Ơz &j:+v zZ+ +zf h ~ i z \x1e w ? & )ߢ^[f N r y b X ǧv ^ ){.n + z ]z {ay \x1dʇڙ ,j f h z \x1e w j:+v w j m zZ+ ݢj" ! i \x13 칻\x1c & ~ & \x18 +- ݶ\x17 w ˛ m \x1e \x17^ b ^n r z \x1a h & \x1e G h \x03( 階 ݢj" \x1a ^[m z ޖ f h ~ m ^ permalink raw reply [flat|nested] 11+ messages in thread
end of thread, other threads:[~2015-05-06 5:04 UTC | newest] Thread overview: 11+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2015-04-30 20:55 CephFS + Erasure coding Somnath Roy 2015-04-30 21:20 ` Gregory Farnum 2015-04-30 21:27 ` Somnath Roy 2015-04-30 21:57 ` Somnath Roy 2015-04-30 22:00 ` Gregory Farnum 2015-05-06 2:42 ` Wang, Zhiqiang 2015-05-06 4:17 ` Somnath Roy 2015-05-06 4:29 ` Wang, Zhiqiang 2015-05-06 4:32 ` Somnath Roy 2015-05-06 4:39 ` Wang, Zhiqiang 2015-05-06 5:03 ` Somnath Roy
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.