Re: [ceph-users] Recover Data from Deleted RBD Volume
As a closure I would like to thank all people who contributed with their knowledge in my problem although the final decision was not to try any sort of recovery since the effort required would have been tremendous with unambiguous results (to say at least). Jason, Ilya, Brad, David, George, Burkhard thank you very much for your contribution Kind regards, G. On Wed, Aug 10, 2016 at 10:55 AM, Ilya Dryomovwrote: I think Jason meant to write "rbd_id." here. Whoops -- thanks for the typo correction. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Recover Data from Deleted RBD Volume
On Mon, Aug 8, 2016 at 11:47 PM, Jason Dillamanwrote: > On Mon, Aug 8, 2016 at 5:39 PM, Jason Dillaman wrote: >> Unfortunately, for v2 RBD images, this image name to image id mapping >> is stored in the LevelDB database within the OSDs and I don't know, >> offhand, how to attempt to recover deleted values from there. > > Actually, to correct myself, the "rbd_id." object just I think Jason meant to write "rbd_id." here. > writes the image id in binary to the file. So if you can recover that > file and retrieve its contents, you can again determine the block name > prefix in the form of "rbd_data..". So if you had a v2 image named "myimage" in a pool named "rbd" $ ceph osd map rbd rbd_id.myimage osdmap e11 pool 'rbd' (0) object 'rbd_id.myimage' -> pg 0.f8d9dc15 (0.5) -> up ([0,2,1], p0) acting ([0,2,1], p0) you'd need to search for a file whose name starts with "rbd\uid.myimage" under /current/0.5_head/. The 0.5 is the short PG id from the ceph osd map command above (the object doesn't have to exist for it to work). The "\u" is literally a "\" followed by a "u" - ceph's FileStore uses underscores as separators so underscores in object names get translated to "\u" in the corresponding file names. The actual file name is going to be something along the lines of "rbd\uid.myimage__head_F8D9DC15__0": $ xxd "./0.5_head/rbd\uid.myimage__head_F8D9DC15__0" : 0c00 3130 3130 3734 6230 6463 3531 101074b0dc51 That's the prefix for the image. myimage actually exists here, so I can verify it with: $ rbd info rbd/myimage | grep block_name_prefix block_name_prefix: rbd_data.101074b0dc51 With the prefix at hand, you'd need to search all /current/ directories for files whose names start with "rbd\udata.101074b0dc51", doing the equivalent of: $ find . -regex ".*/rbd\\\udata.101074b0dc51.*" ./0.4_head/rbd\udata.101074b0dc51.0003__head_64B130D4__0 ./0.0_head/rbd\udata.101074b0dc51.__head_7A694010__0 ./0.3_head/rbd\udata.101074b0dc51.0004__head_85FCAA2B__0 ./0.1_head/rbd\udata.101074b0dc51.0002__head_660B5009__0 ./0.6_head/rbd\udata.101074b0dc51.0001__head_33B916C6__0 ... There is a rbd-recover-tool tool in the ceph source tree, which can reconstruct rbd images from a FileStore structure outlined in this thread. I'm not sure if we document it or even build it (probably not, and it won't be of much use to you anyway since the files are gone), but you can peruse the code for the exact object name regexes. Thanks, Ilya ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Recover Data from Deleted RBD Volume
The image's associated metadata is removed from the directory once the image is removed. Also, the default librbd log level will not log an image's internal id. Therefore, unfortunately, the only way to proceed is how I previously described. On Wed, Aug 10, 2016 at 2:48 AM, Brad Hubbardwrote: > > > On Wed, Aug 10, 2016 at 3:16 PM, Georgios Dimitrakakis > wrote: >> >> Hello! >> >> Brad, >> >> is that possible from the default logging or verbose one is needed?? >> >> I 've managed to get the UUID of the deleted volume from OpenStack but don't >> really know how to get the offsets and OSD maps since "rbd info" doesn't >> provide any information for that volume. > > Did you grep for the UUID (might be safer to grep for the first 8 chars or > so since I'm not 100% sure of the format) in the logs? > > There is also a RADOS object called the rbd directory that contains some > mapping information for rbd images but I don't know if this is erased when an > image is deleted, nor how to look at it but someone more adept at RBD may be > able to make suggestions how to confirm this? > > HTH, > Brad > >> >> Is it possible to somehow get them from leveldb? >> >> Best, >> >> G. >> >> >>> On Tue, Aug 9, 2016 at 7:39 AM, George Mihaiescu >>> wrote: Look in the cinder db, the volumes table to find the Uuid of the deleted volume. >>> >>> >>> You could also look through the logs at the time of the delete and I >>> suspect you should >>> be able to see how the rbd image was prefixed/named at the time of >>> the delete. >>> >>> HTH, >>> Brad >>> If you go through yours OSDs and look for the directories for PG index 20, you might find some fragments from the deleted volume, but it's a long shot... > On Aug 8, 2016, at 4:39 PM, Georgios Dimitrakakis > wrote: > > Dear David (and all), > > the data are considered very critical therefore all this attempt to > recover them. > > Although the cluster hasn't been fully stopped all users actions have. I > mean services are running but users are not able to read/write/delete. > > The deleted image was the exact same size of the example (500GB) but it > wasn't the only one deleted today. Our user was trying to do a "massive" > cleanup by deleting 11 volumes and unfortunately one of them was very > important. > > Let's assume that I "dd" all the drives what further actions should I do > to recover the files? Could you please elaborate a bit more on the phrase > "If you've never deleted any other rbd images and assuming you can recover > data with names, you may be able to find the rbd objects"?? > > Do you mean that if I know the file names I can go through and check for > them? How? > Do I have to know *all* file names or by searching for a few of them I > can find all data that exist? > > Thanks a lot for taking the time to answer my questions! > > All the best, > > G. > >> I dont think theres a way of getting the prefix from the cluster at >> this point. >> >> If the deleted image was a similar size to the example youve given, >> you will likely have had objects on every OSD. If this data is >> absolutely critical you need to stop your cluster immediately or make >> copies of all the drives with something like dd. If youve never >> deleted any other rbd images and assuming you can recover data with >> names, you may be able to find the rbd objects. >> >> On Mon, Aug 8, 2016 at 7:28 PM, Georgios Dimitrakakis wrote: >> > Hi, > > On 08.08.2016 10:50, Georgios Dimitrakakis wrote: > >>> Hi, >>> On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? >>> >>> >>> Short answer: no >>> >>> Long answer: no, but >>> >>> Consider the way Ceph
Re: [ceph-users] Recover Data from Deleted RBD Volume
On Wed, Aug 10, 2016 at 3:16 PM, Georgios Dimitrakakiswrote: > > Hello! > > Brad, > > is that possible from the default logging or verbose one is needed?? > > I 've managed to get the UUID of the deleted volume from OpenStack but don't > really know how to get the offsets and OSD maps since "rbd info" doesn't > provide any information for that volume. Did you grep for the UUID (might be safer to grep for the first 8 chars or so since I'm not 100% sure of the format) in the logs? There is also a RADOS object called the rbd directory that contains some mapping information for rbd images but I don't know if this is erased when an image is deleted, nor how to look at it but someone more adept at RBD may be able to make suggestions how to confirm this? HTH, Brad > > Is it possible to somehow get them from leveldb? > > Best, > > G. > > >> On Tue, Aug 9, 2016 at 7:39 AM, George Mihaiescu >> wrote: >>> >>> Look in the cinder db, the volumes table to find the Uuid of the deleted >>> volume. >> >> >> You could also look through the logs at the time of the delete and I >> suspect you should >> be able to see how the rbd image was prefixed/named at the time of >> the delete. >> >> HTH, >> Brad >> >>> >>> If you go through yours OSDs and look for the directories for PG index >>> 20, you might find some fragments from the deleted volume, but it's a long >>> shot... >>> On Aug 8, 2016, at 4:39 PM, Georgios Dimitrakakis wrote: Dear David (and all), the data are considered very critical therefore all this attempt to recover them. Although the cluster hasn't been fully stopped all users actions have. I mean services are running but users are not able to read/write/delete. The deleted image was the exact same size of the example (500GB) but it wasn't the only one deleted today. Our user was trying to do a "massive" cleanup by deleting 11 volumes and unfortunately one of them was very important. Let's assume that I "dd" all the drives what further actions should I do to recover the files? Could you please elaborate a bit more on the phrase "If you've never deleted any other rbd images and assuming you can recover data with names, you may be able to find the rbd objects"?? Do you mean that if I know the file names I can go through and check for them? How? Do I have to know *all* file names or by searching for a few of them I can find all data that exist? Thanks a lot for taking the time to answer my questions! All the best, G. > I dont think theres a way of getting the prefix from the cluster at > this point. > > If the deleted image was a similar size to the example youve given, > you will likely have had objects on every OSD. If this data is > absolutely critical you need to stop your cluster immediately or make > copies of all the drives with something like dd. If youve never > deleted any other rbd images and assuming you can recover data with > names, you may be able to find the rbd objects. > > On Mon, Aug 8, 2016 at 7:28 PM, Georgios Dimitrakakis wrote: > Hi, On 08.08.2016 10:50, Georgios Dimitrakakis wrote: >> Hi, >> >>> On 08.08.2016 09:58, Georgios Dimitrakakis wrote: >>> >>> Dear all, >>> >>> I would like your help with an emergency issue but first >>> let me describe our environment. >>> >>> Our environment consists of 2OSD nodes with 10x 2TB HDDs >>> each and 3MON nodes (2 of them are the OSD nodes as well) >>> all with ceph version 0.80.9 >>> (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) >>> >>> This environment provides RBD volumes to an OpenStack >>> Icehouse installation. >>> >>> Although not a state of the art environment is working >>> well and within our expectations. >>> >>> The issue now is that one of our users accidentally >>> deleted one of the volumes without keeping its data first! >>> >>> Is there any way (since the data are considered critical >>> and very important) to recover them from CEPH? >> >> >> Short answer: no >> >> Long answer: no, but >> >> Consider the way Ceph stores data... each RBD is striped >> into chunks >> (RADOS objects with 4MB size by default); the chunks are >> distributed >> among the OSDs with the configured number of replicates >> (probably two >> in your case since you use 2 OSD hosts). RBD uses thin >> provisioning, >> so chunks are allocated upon first write access. >> If an RBD is deleted all of its chunks are deleted on the
Re: [ceph-users] Recover Data from Deleted RBD Volume
Hello! Brad, is that possible from the default logging or verbose one is needed?? I 've managed to get the UUID of the deleted volume from OpenStack but don't really know how to get the offsets and OSD maps since "rbd info" doesn't provide any information for that volume. Is it possible to somehow get them from leveldb? Best, G. On Tue, Aug 9, 2016 at 7:39 AM, George Mihaiescuwrote: Look in the cinder db, the volumes table to find the Uuid of the deleted volume. You could also look through the logs at the time of the delete and I suspect you should be able to see how the rbd image was prefixed/named at the time of the delete. HTH, Brad If you go through yours OSDs and look for the directories for PG index 20, you might find some fragments from the deleted volume, but it's a long shot... On Aug 8, 2016, at 4:39 PM, Georgios Dimitrakakis wrote: Dear David (and all), the data are considered very critical therefore all this attempt to recover them. Although the cluster hasn't been fully stopped all users actions have. I mean services are running but users are not able to read/write/delete. The deleted image was the exact same size of the example (500GB) but it wasn't the only one deleted today. Our user was trying to do a "massive" cleanup by deleting 11 volumes and unfortunately one of them was very important. Let's assume that I "dd" all the drives what further actions should I do to recover the files? Could you please elaborate a bit more on the phrase "If you've never deleted any other rbd images and assuming you can recover data with names, you may be able to find the rbd objects"?? Do you mean that if I know the file names I can go through and check for them? How? Do I have to know *all* file names or by searching for a few of them I can find all data that exist? Thanks a lot for taking the time to answer my questions! All the best, G. I dont think theres a way of getting the prefix from the cluster at this point. If the deleted image was a similar size to the example youve given, you will likely have had objects on every OSD. If this data is absolutely critical you need to stop your cluster immediately or make copies of all the drives with something like dd. If youve never deleted any other rbd images and assuming you can recover data with names, you may be able to find the rbd objects. On Mon, Aug 8, 2016 at 7:28 PM, Georgios Dimitrakakis wrote: Hi, On 08.08.2016 10:50, Georgios Dimitrakakis wrote: Hi, On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? Short answer: no Long answer: no, but Consider the way Ceph stores data... each RBD is striped into chunks (RADOS objects with 4MB size by default); the chunks are distributed among the OSDs with the configured number of replicates (probably two in your case since you use 2 OSD hosts). RBD uses thin provisioning, so chunks are allocated upon first write access. If an RBD is deleted all of its chunks are deleted on the corresponding OSDs. If you want to recover a deleted RBD, you need to recover all individual chunks. Whether this is possible depends on your filesystem and whether the space of a former chunk is already assigned to other RADOS objects. The RADOS object names are composed of the RBD name and the offset position of the chunk, so if an undelete mechanism exists for the OSDs filesystem, you have to be able to recover file by their filename, otherwise you might end up mixing the content of various deleted RBDs. Due to the thin provisioning there might be some chunks missing (e.g. never allocated before). Given the fact that - you probably use XFS on the OSDs since it is the preferred filesystem for OSDs (there is RDR-XFS, but Ive never had to use it) - you would need to stop the complete ceph cluster (recovery tools do not work on mounted filesystems) - your cluster has been in use after the RBD was deleted and thus parts of its former space might already have been overwritten (replication might help you here, since there are two OSDs to try) - XFS undelete does not work well on fragmented files (and OSDs tend to introduce fragmentation...) the answer is no, since it might not be feasible and the chance of success are way too low. If you want to spend time
Re: [ceph-users] Recover Data from Deleted RBD Volume
On Tue, Aug 9, 2016 at 7:39 AM, George Mihaiescuwrote: > Look in the cinder db, the volumes table to find the Uuid of the deleted > volume. You could also look through the logs at the time of the delete and I suspect you should be able to see how the rbd image was prefixed/named at the time of the delete. HTH, Brad > > If you go through yours OSDs and look for the directories for PG index 20, > you might find some fragments from the deleted volume, but it's a long shot... > >> On Aug 8, 2016, at 4:39 PM, Georgios Dimitrakakis >> wrote: >> >> Dear David (and all), >> >> the data are considered very critical therefore all this attempt to recover >> them. >> >> Although the cluster hasn't been fully stopped all users actions have. I >> mean services are running but users are not able to read/write/delete. >> >> The deleted image was the exact same size of the example (500GB) but it >> wasn't the only one deleted today. Our user was trying to do a "massive" >> cleanup by deleting 11 volumes and unfortunately one of them was very >> important. >> >> Let's assume that I "dd" all the drives what further actions should I do to >> recover the files? Could you please elaborate a bit more on the phrase "If >> you've never deleted any other rbd images and assuming you can recover data >> with names, you may be able to find the rbd objects"?? >> >> Do you mean that if I know the file names I can go through and check for >> them? How? >> Do I have to know *all* file names or by searching for a few of them I can >> find all data that exist? >> >> Thanks a lot for taking the time to answer my questions! >> >> All the best, >> >> G. >> >>> I dont think theres a way of getting the prefix from the cluster at >>> this point. >>> >>> If the deleted image was a similar size to the example youve given, >>> you will likely have had objects on every OSD. If this data is >>> absolutely critical you need to stop your cluster immediately or make >>> copies of all the drives with something like dd. If youve never >>> deleted any other rbd images and assuming you can recover data with >>> names, you may be able to find the rbd objects. >>> >>> On Mon, Aug 8, 2016 at 7:28 PM, Georgios Dimitrakakis wrote: >>> >> Hi, >> >> On 08.08.2016 10:50, Georgios Dimitrakakis wrote: >> Hi, > On 08.08.2016 09:58, Georgios Dimitrakakis wrote: > > Dear all, > > I would like your help with an emergency issue but first > let me describe our environment. > > Our environment consists of 2OSD nodes with 10x 2TB HDDs > each and 3MON nodes (2 of them are the OSD nodes as well) > all with ceph version 0.80.9 > (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) > > This environment provides RBD volumes to an OpenStack > Icehouse installation. > > Although not a state of the art environment is working > well and within our expectations. > > The issue now is that one of our users accidentally > deleted one of the volumes without keeping its data first! > > Is there any way (since the data are considered critical > and very important) to recover them from CEPH? Short answer: no Long answer: no, but Consider the way Ceph stores data... each RBD is striped into chunks (RADOS objects with 4MB size by default); the chunks are distributed among the OSDs with the configured number of replicates (probably two in your case since you use 2 OSD hosts). RBD uses thin provisioning, so chunks are allocated upon first write access. If an RBD is deleted all of its chunks are deleted on the corresponding OSDs. If you want to recover a deleted RBD, you need to recover all individual chunks. Whether this is possible depends on your filesystem and whether the space of a former chunk is already assigned to other RADOS objects. The RADOS object names are composed of the RBD name and the offset position of the chunk, so if an undelete mechanism exists for the OSDs filesystem, you have to be able to recover file by their filename, otherwise you might end up mixing the content of various deleted RBDs. Due to the thin provisioning there might be some chunks missing (e.g. never allocated before). Given the fact that - you probably use XFS on the OSDs since it is the preferred filesystem for OSDs (there is RDR-XFS, but Ive never had to use it) - you would need to stop the complete ceph cluster (recovery tools do not work on mounted filesystems)
Re: [ceph-users] Recover Data from Deleted RBD Volume
On Mon, Aug 8, 2016 at 9:39 PM, Georgios Dimitrakakiswrote: > Dear David (and all), > > the data are considered very critical therefore all this attempt to > recover them. > > Although the cluster hasn't been fully stopped all users actions have. I > mean services are running but users are not able to read/write/delete. > > The deleted image was the exact same size of the example (500GB) but it > wasn't the only one deleted today. Our user was trying to do a "massive" > cleanup by deleting 11 volumes and unfortunately one of them was very > important. > > Let's assume that I "dd" all the drives what further actions should I do > to recover the files? Could you please elaborate a bit more on the phrase > "If you've never deleted any other rbd images and assuming you can recover > data with names, you may be able to find the rbd objects"?? > Sorry that last comment was a bit confusing, I was suggesting at this stage you just need to concentrate on recovering everything you can and then try and find the data you need. The dd is to make a backup of the partition so you can work on it safely. Ideally you would make a 2nd copy of the dd'd partition and work on that. Then you need to find tools to attempt the recovery which is going to be slow and painful and not guaranteed to be successful. > > Do you mean that if I know the file names I can go through and check for > them? How? > Do I have to know *all* file names or by searching for a few of them I can > find all data that exist? > > Thanks a lot for taking the time to answer my questions! > > All the best, > > G. > > I dont think theres a way of getting the prefix from the cluster at >> this point. >> >> If the deleted image was a similar size to the example youve given, >> you will likely have had objects on every OSD. If this data is >> absolutely critical you need to stop your cluster immediately or make >> copies of all the drives with something like dd. If youve never >> deleted any other rbd images and assuming you can recover data with >> names, you may be able to find the rbd objects. >> >> On Mon, Aug 8, 2016 at 7:28 PM, Georgios Dimitrakakis wrote: >> >> Hi, > > On 08.08.2016 10:50, Georgios Dimitrakakis wrote: > > Hi, >>> >>> On 08.08.2016 09:58, Georgios Dimitrakakis wrote: >>> >>> Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? >>> >>> Short answer: no >>> >>> Long answer: no, but >>> >>> Consider the way Ceph stores data... each RBD is striped >>> into chunks >>> (RADOS objects with 4MB size by default); the chunks are >>> distributed >>> among the OSDs with the configured number of replicates >>> (probably two >>> in your case since you use 2 OSD hosts). RBD uses thin >>> provisioning, >>> so chunks are allocated upon first write access. >>> If an RBD is deleted all of its chunks are deleted on the >>> corresponding OSDs. If you want to recover a deleted RBD, >>> you need to >>> recover all individual chunks. Whether this is possible >>> depends on >>> your filesystem and whether the space of a former chunk is >>> already >>> assigned to other RADOS objects. The RADOS object names are >>> composed >>> of the RBD name and the offset position of the chunk, so if >>> an >>> undelete mechanism exists for the OSDs filesystem, you have >>> to be >>> able to recover file by their filename, otherwise you might >>> end up >>> mixing the content of various deleted RBDs. Due to the thin >>> provisioning there might be some chunks missing (e.g. never >>> allocated >>> before). >>> >>> Given the fact that >>> - you probably use XFS on the OSDs since it is the >>> preferred >>> filesystem for OSDs (there is RDR-XFS, but Ive never had to >>> >>> use it) >>> - you would need to stop the complete ceph cluster >>> (recovery tools do >>> not work on mounted filesystems) >>> - your cluster has been in use after the RBD was deleted >>> and thus >>> parts of its former space might already have been >>> overwritten >>>
Re: [ceph-users] Recover Data from Deleted RBD Volume
On Mon, Aug 8, 2016 at 5:39 PM, Jason Dillamanwrote: > Unfortunately, for v2 RBD images, this image name to image id mapping > is stored in the LevelDB database within the OSDs and I don't know, > offhand, how to attempt to recover deleted values from there. Actually, to correct myself, the "rbd_id." object just writes the image id in binary to the file. So if you can recover that file and retrieve its contents, you can again determine the block name prefix in the form of "rbd_data..". -- Jason ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Recover Data from Deleted RBD Volume
All RBD images use a backing RADOS object to facilitate mapping between the external image name and the internal image id. For v1 images this object would be named ".rbd" and for v2 images this object would be named "rbd_id.". You would need to find this deleted object first in order to start figuring out the internal image id. For example, if image "test" was a v1 RBD image in the pool rbd, you would run: # ceph osd map rbd test.rbd osdmap e9 pool 'rbd' (0) object 'rbd_id.test' -> pg 0.9a2f7478 (0.0) -> up ([0,2,1], p0) acting ([0,2,1], p0) In this example, the object would be placed in PG 0.0 on OSD 0, 2, and 1. Since this object still exists for me, I can locate it on the OSD disk: # find /var/lib/ceph/osd/ceph-0/current/0.0_head/ -name "test.rbd*" /var/lib/ceph/osd/ceph-0/current/0.0_head/test.rbd__head_9A2F7478__0 In your case, you would need to search for a deleted file substring matching your image name within the appropriate PG directory on the associated OSDs. If you can recover the v1 RBD header (e.g. test.rbd), you can dump its contents and extract the block name prefix. In my example, if I hexdump my v1 header object, I see: # hexdump -C /var/lib/ceph/osd/ceph-0/current/0.0_head/test.rbd__head_9A2F7478__0 3c 3c 3c 20 52 61 64 6f 73 20 42 6c 6f 63 6b 20 |<<< Rados Block | 0010 44 65 76 69 63 65 20 49 6d 61 67 65 20 3e 3e 3e |Device Image >>>| 0020 0a 00 00 00 00 00 00 00 72 62 2e 30 2e 31 30 31 |rb.0.101| 0030 30 2e 37 34 62 30 64 63 35 31 00 00 00 00 00 00 |0.74b0dc51..| 0040 52 42 44 00 30 30 31 2e 30 30 35 00 16 00 00 00 |RBD.001.005.| 0050 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 || * 0070 All the data blocks associated with this image will be named with a "rb.0.1010.74b0dc51." prefix followed by a 12 character, zero-padded, hexadecimal number representing the object offset within the image. For example, assuming the default 4MB object size, "rb.0.1010.74b0dc51.00cf" would represent the offset 188MB through 192MB within the image. For each one of these object names, you would need to run the "ceph osd map" command to determine where these data blocks would have lived and then attempt to undelete them. Unfortunately, for v2 RBD images, this image name to image id mapping is stored in the LevelDB database within the OSDs and I don't know, offhand, how to attempt to recover deleted values from there. On Mon, Aug 8, 2016 at 4:39 PM, Georgios Dimitrakakiswrote: > Dear David (and all), > > the data are considered very critical therefore all this attempt to recover > them. > > Although the cluster hasn't been fully stopped all users actions have. I > mean services are running but users are not able to read/write/delete. > > The deleted image was the exact same size of the example (500GB) but it > wasn't the only one deleted today. Our user was trying to do a "massive" > cleanup by deleting 11 volumes and unfortunately one of them was very > important. > > Let's assume that I "dd" all the drives what further actions should I do to > recover the files? Could you please elaborate a bit more on the phrase "If > you've never deleted any other rbd images and assuming you can recover data > with names, you may be able to find the rbd objects"?? > > Do you mean that if I know the file names I can go through and check for > them? How? > Do I have to know *all* file names or by searching for a few of them I can > find all data that exist? > > Thanks a lot for taking the time to answer my questions! > > All the best, > > G. > >> I dont think theres a way of getting the prefix from the cluster at >> this point. >> >> If the deleted image was a similar size to the example youve given, >> you will likely have had objects on every OSD. If this data is >> absolutely critical you need to stop your cluster immediately or make >> copies of all the drives with something like dd. If youve never >> deleted any other rbd images and assuming you can recover data with >> names, you may be able to find the rbd objects. >> >> On Mon, Aug 8, 2016 at 7:28 PM, Georgios Dimitrakakis wrote: >> > Hi, > > On 08.08.2016 10:50, Georgios Dimitrakakis wrote: > >>> Hi, >>> >>> On 08.08.2016 09:58, Georgios Dimitrakakis wrote: >>> Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users
Re: [ceph-users] Recover Data from Deleted RBD Volume
Look in the cinder db, the volumes table to find the Uuid of the deleted volume. If you go through yours OSDs and look for the directories for PG index 20, you might find some fragments from the deleted volume, but it's a long shot... > On Aug 8, 2016, at 4:39 PM, Georgios Dimitrakakis> wrote: > > Dear David (and all), > > the data are considered very critical therefore all this attempt to recover > them. > > Although the cluster hasn't been fully stopped all users actions have. I mean > services are running but users are not able to read/write/delete. > > The deleted image was the exact same size of the example (500GB) but it > wasn't the only one deleted today. Our user was trying to do a "massive" > cleanup by deleting 11 volumes and unfortunately one of them was very > important. > > Let's assume that I "dd" all the drives what further actions should I do to > recover the files? Could you please elaborate a bit more on the phrase "If > you've never deleted any other rbd images and assuming you can recover data > with names, you may be able to find the rbd objects"?? > > Do you mean that if I know the file names I can go through and check for > them? How? > Do I have to know *all* file names or by searching for a few of them I can > find all data that exist? > > Thanks a lot for taking the time to answer my questions! > > All the best, > > G. > >> I dont think theres a way of getting the prefix from the cluster at >> this point. >> >> If the deleted image was a similar size to the example youve given, >> you will likely have had objects on every OSD. If this data is >> absolutely critical you need to stop your cluster immediately or make >> copies of all the drives with something like dd. If youve never >> deleted any other rbd images and assuming you can recover data with >> names, you may be able to find the rbd objects. >> >> On Mon, Aug 8, 2016 at 7:28 PM, Georgios Dimitrakakis wrote: >> > Hi, > > On 08.08.2016 10:50, Georgios Dimitrakakis wrote: > >>> Hi, >>> On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? >>> >>> Short answer: no >>> >>> Long answer: no, but >>> >>> Consider the way Ceph stores data... each RBD is striped >>> into chunks >>> (RADOS objects with 4MB size by default); the chunks are >>> distributed >>> among the OSDs with the configured number of replicates >>> (probably two >>> in your case since you use 2 OSD hosts). RBD uses thin >>> provisioning, >>> so chunks are allocated upon first write access. >>> If an RBD is deleted all of its chunks are deleted on the >>> corresponding OSDs. If you want to recover a deleted RBD, >>> you need to >>> recover all individual chunks. Whether this is possible >>> depends on >>> your filesystem and whether the space of a former chunk is >>> already >>> assigned to other RADOS objects. The RADOS object names are >>> composed >>> of the RBD name and the offset position of the chunk, so if >>> an >>> undelete mechanism exists for the OSDs filesystem, you have >>> to be >>> able to recover file by their filename, otherwise you might >>> end up >>> mixing the content of various deleted RBDs. Due to the thin >>> provisioning there might be some chunks missing (e.g. never >>> allocated >>> before). >>> >>> Given the fact that >>> - you probably use XFS on the OSDs since it is the >>> preferred >>> filesystem for OSDs (there is RDR-XFS, but Ive never had to >>> use it) >>> - you would need to stop the complete ceph cluster >>> (recovery tools do >>> not work on mounted filesystems) >>> - your cluster has been in use after the RBD was deleted >>> and thus >>> parts of its former space might already have been >>> overwritten >>> (replication might help you here, since there are two OSDs >>> to try) >>> - XFS undelete does not work well on fragmented files (and >>> OSDs tend >>> to introduce
Re: [ceph-users] Recover Data from Deleted RBD Volume
Dear David (and all), the data are considered very critical therefore all this attempt to recover them. Although the cluster hasn't been fully stopped all users actions have. I mean services are running but users are not able to read/write/delete. The deleted image was the exact same size of the example (500GB) but it wasn't the only one deleted today. Our user was trying to do a "massive" cleanup by deleting 11 volumes and unfortunately one of them was very important. Let's assume that I "dd" all the drives what further actions should I do to recover the files? Could you please elaborate a bit more on the phrase "If you've never deleted any other rbd images and assuming you can recover data with names, you may be able to find the rbd objects"?? Do you mean that if I know the file names I can go through and check for them? How? Do I have to know *all* file names or by searching for a few of them I can find all data that exist? Thanks a lot for taking the time to answer my questions! All the best, G. I dont think theres a way of getting the prefix from the cluster at this point. If the deleted image was a similar size to the example youve given, you will likely have had objects on every OSD. If this data is absolutely critical you need to stop your cluster immediately or make copies of all the drives with something like dd. If youve never deleted any other rbd images and assuming you can recover data with names, you may be able to find the rbd objects. On Mon, Aug 8, 2016 at 7:28 PM, Georgios Dimitrakakis wrote: Hi, On 08.08.2016 10:50, Georgios Dimitrakakis wrote: Hi, On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? Short answer: no Long answer: no, but Consider the way Ceph stores data... each RBD is striped into chunks (RADOS objects with 4MB size by default); the chunks are distributed among the OSDs with the configured number of replicates (probably two in your case since you use 2 OSD hosts). RBD uses thin provisioning, so chunks are allocated upon first write access. If an RBD is deleted all of its chunks are deleted on the corresponding OSDs. If you want to recover a deleted RBD, you need to recover all individual chunks. Whether this is possible depends on your filesystem and whether the space of a former chunk is already assigned to other RADOS objects. The RADOS object names are composed of the RBD name and the offset position of the chunk, so if an undelete mechanism exists for the OSDs filesystem, you have to be able to recover file by their filename, otherwise you might end up mixing the content of various deleted RBDs. Due to the thin provisioning there might be some chunks missing (e.g. never allocated before). Given the fact that - you probably use XFS on the OSDs since it is the preferred filesystem for OSDs (there is RDR-XFS, but Ive never had to use it) - you would need to stop the complete ceph cluster (recovery tools do not work on mounted filesystems) - your cluster has been in use after the RBD was deleted and thus parts of its former space might already have been overwritten (replication might help you here, since there are two OSDs to try) - XFS undelete does not work well on fragmented files (and OSDs tend to introduce fragmentation...) the answer is no, since it might not be feasible and the chance of success are way too low. If you want to spend time on it I would propose the stop the ceph cluster as soon as possible, create copies of all involved OSDs, start the cluster again and attempt the recovery on the copies. Regards, Burkhard Hi! Thanks for the info...I understand that this is a very difficult and probably not feasible task but in case I need to try a recovery what other info should I need? Can I somehow find out on which OSDs the specific data were stored and minimize my search there? Any ideas on how should I proceed? First of all you need to know the exact object names for the RADOS objects. As mentioned before, the name is composed of the RBD name and an offset. In case of OpenStack, there are three different patterns for RBD names: , e.g. 50f2a0bd-15b1-4dbb-8d1f-fc43ce535f13 for glance images, , e.g. 9aec1f45-9053-461e-b176-c65c25a48794_disk for nova images , e.g. volume-0ca52f58-7e75-4b21-8b0f-39cbcd431c42 for cinder volumes (not considering
Re: [ceph-users] Recover Data from Deleted RBD Volume
Hi, On 08.08.2016 10:50, Georgios Dimitrakakis wrote: Hi, On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? Short answer: no Long answer: no, but Consider the way Ceph stores data... each RBD is striped into chunks (RADOS objects with 4MB size by default); the chunks are distributed among the OSDs with the configured number of replicates (probably two in your case since you use 2 OSD hosts). RBD uses thin provisioning, so chunks are allocated upon first write access. If an RBD is deleted all of its chunks are deleted on the corresponding OSDs. If you want to recover a deleted RBD, you need to recover all individual chunks. Whether this is possible depends on your filesystem and whether the space of a former chunk is already assigned to other RADOS objects. The RADOS object names are composed of the RBD name and the offset position of the chunk, so if an undelete mechanism exists for the OSDs' filesystem, you have to be able to recover file by their filename, otherwise you might end up mixing the content of various deleted RBDs. Due to the thin provisioning there might be some chunks missing (e.g. never allocated before). Given the fact that - you probably use XFS on the OSDs since it is the preferred filesystem for OSDs (there is RDR-XFS, but I've never had to use it) - you would need to stop the complete ceph cluster (recovery tools do not work on mounted filesystems) - your cluster has been in use after the RBD was deleted and thus parts of its former space might already have been overwritten (replication might help you here, since there are two OSDs to try) - XFS undelete does not work well on fragmented files (and OSDs tend to introduce fragmentation...) the answer is no, since it might not be feasible and the chance of success are way too low. If you want to spend time on it I would propose the stop the ceph cluster as soon as possible, create copies of all involved OSDs, start the cluster again and attempt the recovery on the copies. Regards, Burkhard Hi! Thanks for the info...I understand that this is a very difficult and probably not feasible task but in case I need to try a recovery what other info should I need? Can I somehow find out on which OSDs the specific data were stored and minimize my search there? Any ideas on how should I proceed? First of all you need to know the exact object names for the RADOS objects. As mentioned before, the name is composed of the RBD name and an offset. In case of OpenStack, there are three different patterns for RBD names: , e.g. 50f2a0bd-15b1-4dbb-8d1f-fc43ce535f13 for glance images, , e.g. 9aec1f45-9053-461e-b176-c65c25a48794_disk for nova images , e.g. volume-0ca52f58-7e75-4b21-8b0f-39cbcd431c42 for cinder volumes (not considering snapshots etc, which might use different patterns) The RBD chunks are created using a certain prefix (using examples from our openstack setup): # rbd -p os-images info 8fa3d9eb-91ed-4c60-9550-a62f34aed014 rbd image '8fa3d9eb-91ed-4c60-9550-a62f34aed014': size 446 MB in 56 objects order 23 (8192 kB objects) block_name_prefix: rbd_data.30e57d54dea573 format: 2 features: layering, striping flags: stripe unit: 8192 kB stripe count: 1 # rados -p os-images ls | grep rbd_data.30e57d54dea573 rbd_data.30e57d54dea573.0015 rbd_data.30e57d54dea573.0008 rbd_data.30e57d54dea573.000a rbd_data.30e57d54dea573.002d rbd_data.30e57d54dea573.0032 I don't know how whether the prefix is derived from some other information, but the recover the RBD you definitely need it. _If_ you are able to recover the prefix, you can use 'ceph osd map' to find the OSDs for each chunk: # ceph osd map os-images rbd_data.30e57d54dea573.001a osdmap e418590 pool 'os-images' (38) object 'rbd_data.30e57d54dea573.001a' -> pg 38.d5d81d65 (38.65) -> up ([45,17,108], p45) acting ([45,17,108], p45) With 20 OSDs in your case you will likely have to process all of them if the RBD has a size of several GBs. Regards, Burkhard Is it possible to get the prefix if the RBD has been deleted already?? Is this info somewhere stored? Can I retrieve it with another way besides "rbd info"? Because when I try to get it using the "rbd info"
Re: [ceph-users] Recover Data from Deleted RBD Volume
Hi, On 08.08.2016 10:50, Georgios Dimitrakakis wrote: Hi, On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? Short answer: no Long answer: no, but Consider the way Ceph stores data... each RBD is striped into chunks (RADOS objects with 4MB size by default); the chunks are distributed among the OSDs with the configured number of replicates (probably two in your case since you use 2 OSD hosts). RBD uses thin provisioning, so chunks are allocated upon first write access. If an RBD is deleted all of its chunks are deleted on the corresponding OSDs. If you want to recover a deleted RBD, you need to recover all individual chunks. Whether this is possible depends on your filesystem and whether the space of a former chunk is already assigned to other RADOS objects. The RADOS object names are composed of the RBD name and the offset position of the chunk, so if an undelete mechanism exists for the OSDs' filesystem, you have to be able to recover file by their filename, otherwise you might end up mixing the content of various deleted RBDs. Due to the thin provisioning there might be some chunks missing (e.g. never allocated before). Given the fact that - you probably use XFS on the OSDs since it is the preferred filesystem for OSDs (there is RDR-XFS, but I've never had to use it) - you would need to stop the complete ceph cluster (recovery tools do not work on mounted filesystems) - your cluster has been in use after the RBD was deleted and thus parts of its former space might already have been overwritten (replication might help you here, since there are two OSDs to try) - XFS undelete does not work well on fragmented files (and OSDs tend to introduce fragmentation...) the answer is no, since it might not be feasible and the chance of success are way too low. If you want to spend time on it I would propose the stop the ceph cluster as soon as possible, create copies of all involved OSDs, start the cluster again and attempt the recovery on the copies. Regards, Burkhard Hi! Thanks for the info...I understand that this is a very difficult and probably not feasible task but in case I need to try a recovery what other info should I need? Can I somehow find out on which OSDs the specific data were stored and minimize my search there? Any ideas on how should I proceed? First of all you need to know the exact object names for the RADOS objects. As mentioned before, the name is composed of the RBD name and an offset. In case of OpenStack, there are three different patterns for RBD names: , e.g. 50f2a0bd-15b1-4dbb-8d1f-fc43ce535f13 for glance images, , e.g. 9aec1f45-9053-461e-b176-c65c25a48794_disk for nova images , e.g. volume-0ca52f58-7e75-4b21-8b0f-39cbcd431c42 for cinder volumes (not considering snapshots etc, which might use different patterns) The RBD chunks are created using a certain prefix (using examples from our openstack setup): # rbd -p os-images info 8fa3d9eb-91ed-4c60-9550-a62f34aed014 rbd image '8fa3d9eb-91ed-4c60-9550-a62f34aed014': size 446 MB in 56 objects order 23 (8192 kB objects) block_name_prefix: rbd_data.30e57d54dea573 format: 2 features: layering, striping flags: stripe unit: 8192 kB stripe count: 1 # rados -p os-images ls | grep rbd_data.30e57d54dea573 rbd_data.30e57d54dea573.0015 rbd_data.30e57d54dea573.0008 rbd_data.30e57d54dea573.000a rbd_data.30e57d54dea573.002d rbd_data.30e57d54dea573.0032 I don't know how whether the prefix is derived from some other information, but the recover the RBD you definitely need it. _If_ you are able to recover the prefix, you can use 'ceph osd map' to find the OSDs for each chunk: # ceph osd map os-images rbd_data.30e57d54dea573.001a osdmap e418590 pool 'os-images' (38) object 'rbd_data.30e57d54dea573.001a' -> pg 38.d5d81d65 (38.65) -> up ([45,17,108], p45) acting ([45,17,108], p45) With 20 OSDs in your case you will likely have to process all of them if the RBD has a size of several GBs. Regards, Burkhard Is it possible to get the prefix if the RBD has been deleted already?? Is this info somewhere stored? Can I retrieve it with another way besides "rbd info"? Because when I try to get it using the "rbd info"
Re: [ceph-users] Recover Data from Deleted RBD Volume
Hi, On 08.08.2016 10:50, Georgios Dimitrakakis wrote: Hi, On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? Short answer: no Long answer: no, but Consider the way Ceph stores data... each RBD is striped into chunks (RADOS objects with 4MB size by default); the chunks are distributed among the OSDs with the configured number of replicates (probably two in your case since you use 2 OSD hosts). RBD uses thin provisioning, so chunks are allocated upon first write access. If an RBD is deleted all of its chunks are deleted on the corresponding OSDs. If you want to recover a deleted RBD, you need to recover all individual chunks. Whether this is possible depends on your filesystem and whether the space of a former chunk is already assigned to other RADOS objects. The RADOS object names are composed of the RBD name and the offset position of the chunk, so if an undelete mechanism exists for the OSDs' filesystem, you have to be able to recover file by their filename, otherwise you might end up mixing the content of various deleted RBDs. Due to the thin provisioning there might be some chunks missing (e.g. never allocated before). Given the fact that - you probably use XFS on the OSDs since it is the preferred filesystem for OSDs (there is RDR-XFS, but I've never had to use it) - you would need to stop the complete ceph cluster (recovery tools do not work on mounted filesystems) - your cluster has been in use after the RBD was deleted and thus parts of its former space might already have been overwritten (replication might help you here, since there are two OSDs to try) - XFS undelete does not work well on fragmented files (and OSDs tend to introduce fragmentation...) the answer is no, since it might not be feasible and the chance of success are way too low. If you want to spend time on it I would propose the stop the ceph cluster as soon as possible, create copies of all involved OSDs, start the cluster again and attempt the recovery on the copies. Regards, Burkhard Hi! Thanks for the info...I understand that this is a very difficult and probably not feasible task but in case I need to try a recovery what other info should I need? Can I somehow find out on which OSDs the specific data were stored and minimize my search there? Any ideas on how should I proceed? First of all you need to know the exact object names for the RADOS objects. As mentioned before, the name is composed of the RBD name and an offset. In case of OpenStack, there are three different patterns for RBD names: , e.g. 50f2a0bd-15b1-4dbb-8d1f-fc43ce535f13 for glance images, , e.g. 9aec1f45-9053-461e-b176-c65c25a48794_disk for nova images , e.g. volume-0ca52f58-7e75-4b21-8b0f-39cbcd431c42 for cinder volumes (not considering snapshots etc, which might use different patterns) The RBD chunks are created using a certain prefix (using examples from our openstack setup): # rbd -p os-images info 8fa3d9eb-91ed-4c60-9550-a62f34aed014 rbd image '8fa3d9eb-91ed-4c60-9550-a62f34aed014': size 446 MB in 56 objects order 23 (8192 kB objects) block_name_prefix: rbd_data.30e57d54dea573 format: 2 features: layering, striping flags: stripe unit: 8192 kB stripe count: 1 # rados -p os-images ls | grep rbd_data.30e57d54dea573 rbd_data.30e57d54dea573.0015 rbd_data.30e57d54dea573.0008 rbd_data.30e57d54dea573.000a rbd_data.30e57d54dea573.002d rbd_data.30e57d54dea573.0032 I don't know how whether the prefix is derived from some other information, but the recover the RBD you definitely need it. _If_ you are able to recover the prefix, you can use 'ceph osd map' to find the OSDs for each chunk: # ceph osd map os-images rbd_data.30e57d54dea573.001a osdmap e418590 pool 'os-images' (38) object 'rbd_data.30e57d54dea573.001a' -> pg 38.d5d81d65 (38.65) -> up ([45,17,108], p45) acting ([45,17,108], p45) With 20 OSDs in your case you will likely have to process all of them if the RBD has a size of several GBs. Regards, Burkhard ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Recover Data from Deleted RBD Volume
That will be down to the pool the rbd was in, the crush rule for that pool will dictate which osd's store objects. In a standard config that rbd will likely have objects on every osd in your cluster. On 8 Aug 2016 9:51 a.m., "Georgios Dimitrakakis"wrote: > Hi, >> >> >> On 08.08.2016 09:58, Georgios Dimitrakakis wrote: >> >>> Dear all, >>> >>> I would like your help with an emergency issue but first let me describe >>> our environment. >>> >>> Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON >>> nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 >>> (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) >>> >>> This environment provides RBD volumes to an OpenStack Icehouse >>> installation. >>> >>> Although not a state of the art environment is working well and within >>> our expectations. >>> >>> The issue now is that one of our users accidentally deleted one of the >>> volumes without keeping its data first! >>> >>> Is there any way (since the data are considered critical and very >>> important) to recover them from CEPH? >>> >> >> Short answer: no >> >> Long answer: no, but >> >> Consider the way Ceph stores data... each RBD is striped into chunks >> (RADOS objects with 4MB size by default); the chunks are distributed >> among the OSDs with the configured number of replicates (probably two >> in your case since you use 2 OSD hosts). RBD uses thin provisioning, >> so chunks are allocated upon first write access. >> If an RBD is deleted all of its chunks are deleted on the >> corresponding OSDs. If you want to recover a deleted RBD, you need to >> recover all individual chunks. Whether this is possible depends on >> your filesystem and whether the space of a former chunk is already >> assigned to other RADOS objects. The RADOS object names are composed >> of the RBD name and the offset position of the chunk, so if an >> undelete mechanism exists for the OSDs' filesystem, you have to be >> able to recover file by their filename, otherwise you might end up >> mixing the content of various deleted RBDs. Due to the thin >> provisioning there might be some chunks missing (e.g. never allocated >> before). >> >> Given the fact that >> - you probably use XFS on the OSDs since it is the preferred >> filesystem for OSDs (there is RDR-XFS, but I've never had to use it) >> - you would need to stop the complete ceph cluster (recovery tools do >> not work on mounted filesystems) >> - your cluster has been in use after the RBD was deleted and thus >> parts of its former space might already have been overwritten >> (replication might help you here, since there are two OSDs to try) >> - XFS undelete does not work well on fragmented files (and OSDs tend >> to introduce fragmentation...) >> >> the answer is no, since it might not be feasible and the chance of >> success are way too low. >> >> If you want to spend time on it I would propose the stop the ceph >> cluster as soon as possible, create copies of all involved OSDs, start >> the cluster again and attempt the recovery on the copies. >> >> Regards, >> Burkhard >> > > Hi! Thanks for the info...I understand that this is a very difficult and > probably not feasible task but in case I need to try a recovery what other > info should I need? Can I somehow find out on which OSDs the specific data > were stored and minimize my search there? > Any ideas on how should I proceed? > > > Best, > > G. > ___ > 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] Recover Data from Deleted RBD Volume
Hi, On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? Short answer: no Long answer: no, but Consider the way Ceph stores data... each RBD is striped into chunks (RADOS objects with 4MB size by default); the chunks are distributed among the OSDs with the configured number of replicates (probably two in your case since you use 2 OSD hosts). RBD uses thin provisioning, so chunks are allocated upon first write access. If an RBD is deleted all of its chunks are deleted on the corresponding OSDs. If you want to recover a deleted RBD, you need to recover all individual chunks. Whether this is possible depends on your filesystem and whether the space of a former chunk is already assigned to other RADOS objects. The RADOS object names are composed of the RBD name and the offset position of the chunk, so if an undelete mechanism exists for the OSDs' filesystem, you have to be able to recover file by their filename, otherwise you might end up mixing the content of various deleted RBDs. Due to the thin provisioning there might be some chunks missing (e.g. never allocated before). Given the fact that - you probably use XFS on the OSDs since it is the preferred filesystem for OSDs (there is RDR-XFS, but I've never had to use it) - you would need to stop the complete ceph cluster (recovery tools do not work on mounted filesystems) - your cluster has been in use after the RBD was deleted and thus parts of its former space might already have been overwritten (replication might help you here, since there are two OSDs to try) - XFS undelete does not work well on fragmented files (and OSDs tend to introduce fragmentation...) the answer is no, since it might not be feasible and the chance of success are way too low. If you want to spend time on it I would propose the stop the ceph cluster as soon as possible, create copies of all involved OSDs, start the cluster again and attempt the recovery on the copies. Regards, Burkhard Hi! Thanks for the info...I understand that this is a very difficult and probably not feasible task but in case I need to try a recovery what other info should I need? Can I somehow find out on which OSDs the specific data were stored and minimize my search there? Any ideas on how should I proceed? Best, G. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Recover Data from Deleted RBD Volume
Hi, On 08.08.2016 09:58, Georgios Dimitrakakis wrote: Dear all, I would like your help with an emergency issue but first let me describe our environment. Our environment consists of 2OSD nodes with 10x 2TB HDDs each and 3MON nodes (2 of them are the OSD nodes as well) all with ceph version 0.80.9 (b5a67f0e1d15385bc0d60a6da6e7fc810bde6047) This environment provides RBD volumes to an OpenStack Icehouse installation. Although not a state of the art environment is working well and within our expectations. The issue now is that one of our users accidentally deleted one of the volumes without keeping its data first! Is there any way (since the data are considered critical and very important) to recover them from CEPH? Short answer: no Long answer: no, but Consider the way Ceph stores data... each RBD is striped into chunks (RADOS objects with 4MB size by default); the chunks are distributed among the OSDs with the configured number of replicates (probably two in your case since you use 2 OSD hosts). RBD uses thin provisioning, so chunks are allocated upon first write access. If an RBD is deleted all of its chunks are deleted on the corresponding OSDs. If you want to recover a deleted RBD, you need to recover all individual chunks. Whether this is possible depends on your filesystem and whether the space of a former chunk is already assigned to other RADOS objects. The RADOS object names are composed of the RBD name and the offset position of the chunk, so if an undelete mechanism exists for the OSDs' filesystem, you have to be able to recover file by their filename, otherwise you might end up mixing the content of various deleted RBDs. Due to the thin provisioning there might be some chunks missing (e.g. never allocated before). Given the fact that - you probably use XFS on the OSDs since it is the preferred filesystem for OSDs (there is RDR-XFS, but I've never had to use it) - you would need to stop the complete ceph cluster (recovery tools do not work on mounted filesystems) - your cluster has been in use after the RBD was deleted and thus parts of its former space might already have been overwritten (replication might help you here, since there are two OSDs to try) - XFS undelete does not work well on fragmented files (and OSDs tend to introduce fragmentation...) the answer is no, since it might not be feasible and the chance of success are way too low. If you want to spend time on it I would propose the stop the ceph cluster as soon as possible, create copies of all involved OSDs, start the cluster again and attempt the recovery on the copies. Regards, Burkhard ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com