Re: [ceph-users] memory usage of: radosgw-admin bucket rm
For mailing list archive readers in the future: On Tue, Jul 9, 2019 at 1:22 PM Paul Emmerich wrote: > Try to add "--inconsistent-index" (caution: will obviously leave your > bucket in a broken state during the deletion, so don't try to use the > bucket) > this was bad advice as long as https://tracker.ceph.com/issues/40700 is not fixed, don't do that. > > You can also speed up the deletion with "--max-concurrent-ios" (default > 32). The documentation incorrectly claims that "--max-concurrent-ios" is > only for other operations but that's wrong, it is used for most bucket > operations including deleteion. > this, however, is a good idea to speed up deletion of large buckets. Try to combine the deletion command with timeout or something to not run into OOM all the time affecting other services. (or use cgroups to limit RAM) Paul > > > Paul > > -- > Paul Emmerich > > Looking for help with your Ceph cluster? Contact us at https://croit.io > > croit GmbH > Freseniusstr. 31h > 81247 München > www.croit.io > Tel: +49 89 1896585 90 > > > On Tue, Jul 9, 2019 at 1:11 PM Harald Staub > wrote: > >> Currently removing a bucket with a lot of objects: >> radosgw-admin bucket rm --bucket=$BUCKET --bypass-gc --purge-objects >> >> This process was killed by the out-of-memory killer. Then looking at the >> graphs, we see a continuous increase of memory usage for this process, >> about +24 GB per day. Removal rate is about 3 M objects per day. >> >> It is not the fastest hardware, and this index pool is still without >> SSDs. The bucket is sharded, 1024 shards. We are on Nautilus 14.2.1, now >> about 500 OSDs. >> >> So with this bucket with 60 M objects, we would need about 480 GB of RAM >> to come through. Or is there a workaround? Should I open a tracker issue? >> >> The killed remove command can just be called again, but it will be >> killed again before it finishes. Also, it has to run some time until it >> continues to actually remove objects. This "wait time" is also >> increasing. Last time, after about 16 M objects already removed, the >> wait time was nearly 9 hours. Also during this time, there is a memory >> ramp, but not so steep. >> >> BTW it feels strange that the removal of objects is slower (about 3 >> times) than adding objects. >> >> Harry >> ___ >> 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] memory usage of: radosgw-admin bucket rm
Created https://tracker.ceph.com/issues/40700 (sry forgot to mention). On 11.07.19 16:41, Matt Benjamin wrote: I don't think one has been created yet. Eric Ivancich and Mark Kogan of my team are investigating this behavior. Matt On Thu, Jul 11, 2019 at 10:40 AM Paul Emmerich wrote: Is there already a tracker issue? I'm seeing the same problem here. Started deletion of a bucket with a few hundred million objects a week ago or so and I've now noticed that it's also leaking memory and probably going to crash. Going to investigate this further... Paul -- Paul Emmerich Looking for help with your Ceph cluster? Contact us at https://croit.io croit GmbH Freseniusstr. 31h 81247 München www.croit.io Tel: +49 89 1896585 90 On Tue, Jul 9, 2019 at 1:26 PM Matt Benjamin wrote: Hi Harald, Please file a tracker issue, yes. (Deletes do tend to be slower, presumably due to rocksdb compaction.) Matt On Tue, Jul 9, 2019 at 7:12 AM Harald Staub wrote: Currently removing a bucket with a lot of objects: radosgw-admin bucket rm --bucket=$BUCKET --bypass-gc --purge-objects This process was killed by the out-of-memory killer. Then looking at the graphs, we see a continuous increase of memory usage for this process, about +24 GB per day. Removal rate is about 3 M objects per day. It is not the fastest hardware, and this index pool is still without SSDs. The bucket is sharded, 1024 shards. We are on Nautilus 14.2.1, now about 500 OSDs. So with this bucket with 60 M objects, we would need about 480 GB of RAM to come through. Or is there a workaround? Should I open a tracker issue? The killed remove command can just be called again, but it will be killed again before it finishes. Also, it has to run some time until it continues to actually remove objects. This "wait time" is also increasing. Last time, after about 16 M objects already removed, the wait time was nearly 9 hours. Also during this time, there is a memory ramp, but not so steep. BTW it feels strange that the removal of objects is slower (about 3 times) than adding objects. Harry ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -- Matt Benjamin Red Hat, Inc. 315 West Huron Street, Suite 140A Ann Arbor, Michigan 48103 http://www.redhat.com/en/technologies/storage tel. 734-821-5101 fax. 734-769-8938 cel. 734-216-5309 ___ 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] memory usage of: radosgw-admin bucket rm [EXT]
On 11/07/2019 15:40, Paul Emmerich wrote: Is there already a tracker issue? I'm seeing the same problem here. Started deletion of a bucket with a few hundred million objects a week ago or so and I've now noticed that it's also leaking memory and probably going to crash. Going to investigate this further... We had a bucket rm on a machine that OOM'd (and killed the relevant process), but I wasn't watching at the time to see if it was the thing eating all the RAM. If someone's giving the bucket rm code some love, it'd be nice if https://tracker.ceph.com/issues/40587 (and associated PR) got looked at - missing shadow objects shouldn't really cause a bucket rm to give up... Regards, Matthew -- The Wellcome Sanger Institute is operated by Genome Research Limited, a charity registered in England with number 1021457 and a company registered in England with number 2742969, whose registered office is 215 Euston Road, London, NW1 2BE. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] memory usage of: radosgw-admin bucket rm
I don't think one has been created yet. Eric Ivancich and Mark Kogan of my team are investigating this behavior. Matt On Thu, Jul 11, 2019 at 10:40 AM Paul Emmerich wrote: > > Is there already a tracker issue? > > I'm seeing the same problem here. Started deletion of a bucket with a few > hundred million objects a week ago or so and I've now noticed that it's also > leaking memory and probably going to crash. > Going to investigate this further... > > Paul > > -- > Paul Emmerich > > Looking for help with your Ceph cluster? Contact us at https://croit.io > > croit GmbH > Freseniusstr. 31h > 81247 München > www.croit.io > Tel: +49 89 1896585 90 > > > On Tue, Jul 9, 2019 at 1:26 PM Matt Benjamin wrote: >> >> Hi Harald, >> >> Please file a tracker issue, yes. (Deletes do tend to be slower, >> presumably due to rocksdb compaction.) >> >> Matt >> >> On Tue, Jul 9, 2019 at 7:12 AM Harald Staub wrote: >> > >> > Currently removing a bucket with a lot of objects: >> > radosgw-admin bucket rm --bucket=$BUCKET --bypass-gc --purge-objects >> > >> > This process was killed by the out-of-memory killer. Then looking at the >> > graphs, we see a continuous increase of memory usage for this process, >> > about +24 GB per day. Removal rate is about 3 M objects per day. >> > >> > It is not the fastest hardware, and this index pool is still without >> > SSDs. The bucket is sharded, 1024 shards. We are on Nautilus 14.2.1, now >> > about 500 OSDs. >> > >> > So with this bucket with 60 M objects, we would need about 480 GB of RAM >> > to come through. Or is there a workaround? Should I open a tracker issue? >> > >> > The killed remove command can just be called again, but it will be >> > killed again before it finishes. Also, it has to run some time until it >> > continues to actually remove objects. This "wait time" is also >> > increasing. Last time, after about 16 M objects already removed, the >> > wait time was nearly 9 hours. Also during this time, there is a memory >> > ramp, but not so steep. >> > >> > BTW it feels strange that the removal of objects is slower (about 3 >> > times) than adding objects. >> > >> > Harry >> > ___ >> > ceph-users mailing list >> > ceph-users@lists.ceph.com >> > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> > >> > >> >> >> -- >> >> Matt Benjamin >> Red Hat, Inc. >> 315 West Huron Street, Suite 140A >> Ann Arbor, Michigan 48103 >> >> http://www.redhat.com/en/technologies/storage >> >> tel. 734-821-5101 >> fax. 734-769-8938 >> cel. 734-216-5309 >> ___ >> ceph-users mailing list >> ceph-users@lists.ceph.com >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -- Matt Benjamin Red Hat, Inc. 315 West Huron Street, Suite 140A Ann Arbor, Michigan 48103 http://www.redhat.com/en/technologies/storage tel. 734-821-5101 fax. 734-769-8938 cel. 734-216-5309 ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] memory usage of: radosgw-admin bucket rm
Is there already a tracker issue? I'm seeing the same problem here. Started deletion of a bucket with a few hundred million objects a week ago or so and I've now noticed that it's also leaking memory and probably going to crash. Going to investigate this further... Paul -- Paul Emmerich Looking for help with your Ceph cluster? Contact us at https://croit.io croit GmbH Freseniusstr. 31h 81247 München www.croit.io Tel: +49 89 1896585 90 On Tue, Jul 9, 2019 at 1:26 PM Matt Benjamin wrote: > Hi Harald, > > Please file a tracker issue, yes. (Deletes do tend to be slower, > presumably due to rocksdb compaction.) > > Matt > > On Tue, Jul 9, 2019 at 7:12 AM Harald Staub > wrote: > > > > Currently removing a bucket with a lot of objects: > > radosgw-admin bucket rm --bucket=$BUCKET --bypass-gc --purge-objects > > > > This process was killed by the out-of-memory killer. Then looking at the > > graphs, we see a continuous increase of memory usage for this process, > > about +24 GB per day. Removal rate is about 3 M objects per day. > > > > It is not the fastest hardware, and this index pool is still without > > SSDs. The bucket is sharded, 1024 shards. We are on Nautilus 14.2.1, now > > about 500 OSDs. > > > > So with this bucket with 60 M objects, we would need about 480 GB of RAM > > to come through. Or is there a workaround? Should I open a tracker issue? > > > > The killed remove command can just be called again, but it will be > > killed again before it finishes. Also, it has to run some time until it > > continues to actually remove objects. This "wait time" is also > > increasing. Last time, after about 16 M objects already removed, the > > wait time was nearly 9 hours. Also during this time, there is a memory > > ramp, but not so steep. > > > > BTW it feels strange that the removal of objects is slower (about 3 > > times) than adding objects. > > > > Harry > > ___ > > ceph-users mailing list > > ceph-users@lists.ceph.com > > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > > > > > -- > > Matt Benjamin > Red Hat, Inc. > 315 West Huron Street, Suite 140A > Ann Arbor, Michigan 48103 > > http://www.redhat.com/en/technologies/storage > > tel. 734-821-5101 > fax. 734-769-8938 > cel. 734-216-5309 > ___ > 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] memory usage of: radosgw-admin bucket rm
Hi Harald, Please file a tracker issue, yes. (Deletes do tend to be slower, presumably due to rocksdb compaction.) Matt On Tue, Jul 9, 2019 at 7:12 AM Harald Staub wrote: > > Currently removing a bucket with a lot of objects: > radosgw-admin bucket rm --bucket=$BUCKET --bypass-gc --purge-objects > > This process was killed by the out-of-memory killer. Then looking at the > graphs, we see a continuous increase of memory usage for this process, > about +24 GB per day. Removal rate is about 3 M objects per day. > > It is not the fastest hardware, and this index pool is still without > SSDs. The bucket is sharded, 1024 shards. We are on Nautilus 14.2.1, now > about 500 OSDs. > > So with this bucket with 60 M objects, we would need about 480 GB of RAM > to come through. Or is there a workaround? Should I open a tracker issue? > > The killed remove command can just be called again, but it will be > killed again before it finishes. Also, it has to run some time until it > continues to actually remove objects. This "wait time" is also > increasing. Last time, after about 16 M objects already removed, the > wait time was nearly 9 hours. Also during this time, there is a memory > ramp, but not so steep. > > BTW it feels strange that the removal of objects is slower (about 3 > times) than adding objects. > > Harry > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > -- Matt Benjamin Red Hat, Inc. 315 West Huron Street, Suite 140A Ann Arbor, Michigan 48103 http://www.redhat.com/en/technologies/storage tel. 734-821-5101 fax. 734-769-8938 cel. 734-216-5309 ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] memory usage of: radosgw-admin bucket rm
Try to add "--inconsistent-index" (caution: will obviously leave your bucket in a broken state during the deletion, so don't try to use the bucket) You can also speed up the deletion with "--max-concurrent-ios" (default 32). The documentation incorrectly claims that "--max-concurrent-ios" is only for other operations but that's wrong, it is used for most bucket operations including deleteion. Paul -- Paul Emmerich Looking for help with your Ceph cluster? Contact us at https://croit.io croit GmbH Freseniusstr. 31h 81247 München www.croit.io Tel: +49 89 1896585 90 On Tue, Jul 9, 2019 at 1:11 PM Harald Staub wrote: > Currently removing a bucket with a lot of objects: > radosgw-admin bucket rm --bucket=$BUCKET --bypass-gc --purge-objects > > This process was killed by the out-of-memory killer. Then looking at the > graphs, we see a continuous increase of memory usage for this process, > about +24 GB per day. Removal rate is about 3 M objects per day. > > It is not the fastest hardware, and this index pool is still without > SSDs. The bucket is sharded, 1024 shards. We are on Nautilus 14.2.1, now > about 500 OSDs. > > So with this bucket with 60 M objects, we would need about 480 GB of RAM > to come through. Or is there a workaround? Should I open a tracker issue? > > The killed remove command can just be called again, but it will be > killed again before it finishes. Also, it has to run some time until it > continues to actually remove objects. This "wait time" is also > increasing. Last time, after about 16 M objects already removed, the > wait time was nearly 9 hours. Also during this time, there is a memory > ramp, but not so steep. > > BTW it feels strange that the removal of objects is slower (about 3 > times) than adding objects. > > Harry > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] memory usage of: radosgw-admin bucket rm
Currently removing a bucket with a lot of objects: radosgw-admin bucket rm --bucket=$BUCKET --bypass-gc --purge-objects This process was killed by the out-of-memory killer. Then looking at the graphs, we see a continuous increase of memory usage for this process, about +24 GB per day. Removal rate is about 3 M objects per day. It is not the fastest hardware, and this index pool is still without SSDs. The bucket is sharded, 1024 shards. We are on Nautilus 14.2.1, now about 500 OSDs. So with this bucket with 60 M objects, we would need about 480 GB of RAM to come through. Or is there a workaround? Should I open a tracker issue? The killed remove command can just be called again, but it will be killed again before it finishes. Also, it has to run some time until it continues to actually remove objects. This "wait time" is also increasing. Last time, after about 16 M objects already removed, the wait time was nearly 9 hours. Also during this time, there is a memory ramp, but not so steep. BTW it feels strange that the removal of objects is slower (about 3 times) than adding objects. Harry ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] memory usage ceph jewel OSDs
Hello, in the last days I try to figure out why my OSDs needs a huge amount of RAM. (1,2 - 4 GB). With this my System memory is on limit. At beginning I thougt it is because of huge amount of backfilling (some disks died). But now since a few days all is good but the memory keeps at its level. Restarting of the OSDs did nothing on this behaviour. I running Ceph Jewel (10.2.6) on RedHat7. The cluster has 8 Hosts with 36 4TB OSDs each and 4 Hosts with 15 4 TB OSDs I tried to profile the used memory like documented here: http://docs.ceph.com/docs/jewel/rados/troubleshooting/memory-profiling/ But the output of this commands didn't help me. But I am confused about the used memory. from ceph tell osd.98 heap dump I get the following output: # ceph tell osd.98 heap dump osd.98 dumping heap profile now. MALLOC: 1290458456 ( 1230.7 MiB) Bytes in use by application MALLOC: +0 (0.0 MiB) Bytes in page heap freelist MALLOC: + 63583000 ( 60.6 MiB) Bytes in central cache freelist MALLOC: + 5896704 (5.6 MiB) Bytes in transfer cache freelist MALLOC: +102784400 ( 98.0 MiB) Bytes in thread cache freelists MALLOC: + 11350176 ( 10.8 MiB) Bytes in malloc metadata MALLOC: MALLOC: = 1474072736 ( 1405.8 MiB) Actual memory used (physical + swap) MALLOC: +129064960 ( 123.1 MiB) Bytes released to OS (aka unmapped) MALLOC: MALLOC: = 1603137696 ( 1528.9 MiB) Virtual address space used MALLOC: MALLOC: 88305 Spans in use MALLOC: 1627 Thread heaps in use MALLOC: 8192 Tcmalloc page size Call ReleaseFreeMemory() to release freelist memory to the OS (via madvise()). Bytes released to the OS take up virtual address space but no physical memory. I would say the application needs 1230.7 MB of RAM. But if I analyse the corresponding dump whit pprof The are only a few Megabytes mentioned. Follwing the first few lines of pprof: # pprof --text /usr/bin/ceph-osd osd.98.profile.0002.heap Using local file /usr/bin/ceph-osd. Using local file osd.98.profile.0002.heap. Total: 8.9 MB 3.3 36.7% 36.7% 3.3 36.7% ceph::log::Log::create_entry 2.3 25.5% 62.2% 2.3 25.5% ceph::buffer::list::append@a1f280 1.1 12.1% 74.3% 2.0 23.1% SimpleMessenger::add_accept_pipe 0.9 10.4% 84.7% 0.9 10.5% Pipe::Pipe 0.2 2.8% 87.5% 0.2 2.8% std::map::operator[] 0.2 2.2% 89.7% 0.2 2.2% std::vector::_M_default_append 0.2 1.8% 91.5% 0.2 1.8% std::_Rb_tree::_M_copy 0.1 0.8% 92.4% 0.1 0.8% ceph::buffer::create_aligned 0.1 0.8% 93.2% 0.1 0.8% std::string::_Rep::_S_create Is this normal? Do I do something wrong? Is there a Bug? Why need my OSDs so much RAM? Thanks for your help Regards, Manuel -- Manuel Lausch Systemadministrator Cloud Services 1&1 Mail & Media Development & Technology GmbH | Brauerstraße 48 | 76135 Karlsruhe | Germany Phone: +49 721 91374-1847 E-Mail: manuel.lau...@1und1.de | Web: www.1und1.de Amtsgericht Montabaur, HRB 5452 Geschäftsführer: Frank Einhellinger, Thomas Ludwig, Jan Oetjen Member of United Internet Diese E-Mail kann vertrauliche und/oder gesetzlich geschützte Informationen enthalten. Wenn Sie nicht der bestimmungsgemäße Adressat sind oder diese E-Mail irrtümlich erhalten haben, unterrichten Sie bitte den Absender und vernichten Sie diese E-Mail. Anderen als dem bestimmungsgemäßen Adressaten ist untersagt, diese E-Mail zu speichern, weiterzuleiten oder ihren Inhalt auf welche Weise auch immer zu verwenden. This e-mail may contain confidential and/or privileged information. If you are not the intended recipient of this e-mail, you are hereby notified that saving, distribution or use of the content of this e-mail in any way is prohibited. If you have received this e-mail in error, please notify the sender and delete the e-mail. ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Memory-Usage
On Mon, Aug 17, 2015 at 8:21 PM, Patrik Plank pat...@plank.me wrote: Hi, have a ceph cluster witch tree nodes and 32 osds. The tree nodes have 16Gb memory but only 5Gb is in use. Nodes are Dell Poweredge R510. my ceph.conf: [global] mon_initial_members = ceph01 mon_host = 10.0.0.20,10.0.0.21,10.0.0.22 auth_cluster_required = cephx auth_service_required = cephx auth_client_required = cephx filestore_xattr_use_omap = true filestore_op_threads = 32 public_network = 10.0.0.0/24 cluster_network = 10.0.1.0/24 osd_pool_default_size = 3 osd_pool_default_min_size = 1 osd_pool_default_pg_num = 4096 osd_pool_default_pgp_num = 4096 osd_max_write_size = 200 osd_map_cache_size = 1024 osd_map_cache_bl_size = 128 osd_recovery_op_priority = 1 osd_max_recovery_max_active = 1 osd_recovery_max_backfills = 1 osd_op_threads = 32 osd_disk_threads = 8 is that normal or a bottleneck? Any memory not used by the OSD processes directly will be used by Linux for page caching. That's what we want to have happen! So it's not a problem that it's using only 5 GB. Keep in mind that the memory usage might spike dramatically if the OSDs need to deal with an outage, though — your normal-state usage ought to be lower than our recommended values for that reason. -Greg best regards Patrik ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] Memory-Usage
Hi, have a ceph cluster witch tree nodes and 32 osds. The tree nodes have 16Gb memory but only 5Gb is in use. Nodes are Dell Poweredge R510. my ceph.conf: [global] mon_initial_members = ceph01 mon_host = 10.0.0.20,10.0.0.21,10.0.0.22 auth_cluster_required = cephx auth_service_required = cephx auth_client_required = cephx filestore_xattr_use_omap = true filestore_op_threads = 32 public_network = 10.0.0.0/24 cluster_network = 10.0.1.0/24 osd_pool_default_size = 3 osd_pool_default_min_size = 1 osd_pool_default_pg_num = 4096 osd_pool_default_pgp_num = 4096 osd_max_write_size = 200 osd_map_cache_size = 1024 osd_map_cache_bl_size = 128 osd_recovery_op_priority = 1 osd_max_recovery_max_active = 1 osd_recovery_max_backfills = 1 osd_op_threads = 32 osd_disk_threads = 8 is that normal or a bottleneck? best regards Patrik ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] Memory usage of librados
Hi! I`am accessing to Ceph cluster via librados and found that memory usage (VSZ in ps) is extremely increases on writing/reading/removing objects. If I successively write+read+remove the object with the same name, then memory usage is not increased, but if I do the same operations with the different object names then VSZ increases up to 4G and stops at this level. It seems that some internal buffering is enabled, can I configure the maximum size of them? Memory usage is very critical for me and I want to reduce it as much as possible. Operations write+read+stat+remove in loop with different object names: lion@kubuntu-12:~$ ps aux | grep RADOS lion 7890 0.2 0.0 4289264 3988 ?Sl 10:28 0:00 /home/lion/Projects/RMS/TestRADOS/TestRADOS Operations write+read+stat+remove in loop with one object name: lion@kubuntu-12:~$ ps aux | grep RADOS lion 8149 0.1 0.0 556424 3520 ?Sl 10:30 0:00 /home/lion/Projects/RMS/TestRADOS/TestRADOS Listing of test program: http://pastebin.com/idqt1PEv ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Memory usage of librados
On Wed, 25 Dec 2013, Potapov Sergey wrote: Hi! I`am accessing to Ceph cluster via librados and found that memory usage (VSZ in ps) is extremely increases on writing/reading/removing objects. If I successively write+read+remove the object with the same name, then memory usage is not increased, but if I do the same operations with the different object names then VSZ increases up to 4G and stops at this level. It seems that some internal buffering is enabled, can I configure the maximum size of them? Memory usage is very critical for me and I want to reduce it as much as possible. Operations write+read+stat+remove in loop with different object names: lion@kubuntu-12:~$ ps aux | grep RADOS lion 7890 0.2 0.0 4289264 3988 ?Sl 10:28 0:00 /home/lion/Projects/RMS/TestRADOS/TestRADOS Operations write+read+stat+remove in loop with one object name: lion@kubuntu-12:~$ ps aux | grep RADOS lion 8149 0.1 0.0 556424 3520 ?Sl 10:30 0:00 /home/lion/Projects/RMS/TestRADOS/TestRADOS Listing of test program: http://pastebin.com/idqt1PEv There will be some memory usage that is proportinoal to the size of the cluster because of the sockets open to the various OSDs. I'm not sure what level you should expect, though: it depends on the size of the cluster, your architecture...and I haven't really measured it. In any case, if you can run your program through valgrind massif, that will tell us exactly where the memory is going, and whether there is anything obviously wrong or easy to fix! sage ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] Memory usage of librados
Hi! I`am accessing to Ceph cluster via librados and found that memory usage (VSZ in ps) is extremely increases on writing/reading/removing objects. If I successively write+read+remove the object with the same name, then memory usage is not increased, but if I do the same operations with the different object names then VSZ increases up to 4G and stops at this level. It seems that some internal buffering is enabled, can I configure the maximum size of them? Memory usage is very critical for me and I want to reduce it as much as possible. Operations write+read+stat+remove in loop with different object names: lion@kubuntu-12:~$ ps aux | grep RADOS lion 7890 0.2 0.0 4289264 3988 ?Sl 10:28 0:00 /home/lion/Projects/RMS/TestRADOS/TestRADOS Operations write+read+stat+remove in loop with one object name: lion@kubuntu-12:~$ ps aux | grep RADOS lion 8149 0.1 0.0 556424 3520 ?Sl 10:30 0:00 /home/lion/Projects/RMS/TestRADOS/TestRADOS Listing of test program: http://pastebin.com/idqt1PEv ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com