Re: [ceph-users] Software Raid 1 for system disks on storage nodes (not for OSD disks)
Hello! On Sat, Sep 19, 2015 at 07:03:35AM +0200, martin wrote: > Thanks all for the suggestions. > Our storage nodes have plenty of RAM and their only purpose is to host the > OSD daemons, so we will not create a swap partition on provisioning. As an option, You can use swap file on demand. It is easy to deploy. > For the OS disk we will then use a software raid 1 to handle eventually > disk failures. For provisioning the hosts we use kickstart and then Ansible > to install an prepare the hosts to be ready to for ceph-deploy. I don't think raid1 is suitable for ceph as of ability to have distributed over hosts copies of data. Think as this is a raid1 over hosts that is more reliable. Even a server crush will not destroy Your data. If Your setup is quite correct :) -- WBR, Max A. Krasilnikov ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] multi-datacenter crush map
Thank you for your answer! We will use size=4 and min_size=2, which should do the trick. For the monitor issue, we have a third datacenter (with higher latency, but that shouldn't be a problem for the monitors) We had also considered the locality issue. Our WAN round trip latency is 1.5 ms (now) and we should get a dedicated light path in the near future (<0.1 ms). So we hope to get acceptable latency without additional tweaking. The plan B is to make two pools, with different weights for the different DC's. VM's in DC 1 will get high weight for DC 1, VM's in DC 2 will get high weight for DC 2. Thanks, Wouter On Sat, Sep 19, 2015 at 9:31 PM, Robert LeBlanc wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA256 > > You will want size=4 min_size=2 if you want to keep I/O going if a DC > fails and ensure some data integrity. Data checksumming (I think is > being added) would provide much stronger data integrity checking in a > two copy situation as you would be able to tell which of the two > copies is the good copy instead of needing a third to break the tie. > > However, you have yet another problem on your hands. The way monitors > works makes this tricky. If you have one monitor in one DC and two in > the other, if the two monitor DC burns down, the surviving cluster > stops working too because there isn't more than 50% of the monitors > available. Putting two monitors in each DC only causes both to stop > working if one goes down (you need three to make a quorum). It has > been suggested that putting the odd monitor in the cloud (or other > off-site location to both DCs) could be an option, but latency could > cause problems. The cloud monitor would complete the quorum with > whichever DC survives. > > Also remember that there is no data locality awareness in Ceph at the > moment. This could mean that the primary for a PG is in the other DC. > So your client has to contact the primary in the other DC, then that > OSD contacts one OSD in it's DC and two in the other and has to get > confirmation that the write is acknowledged then ack the write to the > client. For a write you will be between 2 x ( LAN latency + WAN > latency ) and 2 x ( LAN latency + 2 x WAN latency ). Additionally your > reads will be between 2 x LAN latency and 2 x WAN latency. Then there > is write amplification so you need to make sure you have a lot more > WAN bandwidth than you think you need. > > I think the large majority of us are eagerly waiting for the RBD > replication feature or some sort of lag behind OSD for situations like > this. > -BEGIN PGP SIGNATURE- > Version: Mailvelope v1.1.0 > Comment: https://www.mailvelope.com > > wsFcBAEBCAAQBQJV/bgrCRDmVDuy+mK58QAAOTsQAJd5Q/3uVMP6D0U+iZv/ > FGvEThfxLqarEo/n/TAPiJdCeZP9sKr8szTP72Iajt5UAwH8Ry5qcvClUoet > LmMXfOxHJQJcMbXcKHxI8G7w9h/8ExkGA3GkoBYltUvZ9+oEI30ANHZphBiK > HhaLWanrEKh8L4EbXnqA9JvEYwf1BGDvxKbdvFDNSIIbDywN3DJn7OavRhC9 > M63GQnFmxSO6F+Oy1q5vMfpur/VtZ27GRfzIDsougRTmM5q9zbdpSY8pHrrZ > RDExkM1t0orl1gUnbNhl/YgQTGfU/XWpEKtJju7Wk9Ciem5SFczJRWsputHc > AhBtnxBoEInlsnpHKnCsPvbY8wEcoo+YxNt79/M3cR8x0UzXl+/4SoDlYnSK > X3afL/YmVnbCV6hoxl2LAOqHbTYasN9VxQIbpQe4kAzSq45yJX//k8NRXBfD > +hGF8qfxpcbTe/9IjJiqwe+ZpaAd4vX7Xfq4oHHeMwWUrvd8sXSbr5CIV1AJ > CYsixEy2gJ0oFFVKcBGtzAfBUxJHb/FAcAuV97zSdYyYRplMq5Qjaz/hwGeu > 9pC83kxY40pfzdD9uEElWoI3+6/34LdNo4TLi3IM8aeZmNGzzIgt/MxAuFOk > 9Jf2Dwmab0+Ut6uJasY4Fr6HiyNoeTXea+CSWrnvsMohOseyJg996GUP3gUl > OEoA > =PfhN > -END PGP SIGNATURE- > > Robert LeBlanc > PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 > > > On Sat, Sep 19, 2015 at 12:54 PM, Wouter De Borger > wrote: > > Ok, so if I understand correctly, for replication level 3 or 4 I would > have > > to use the rule > > > > rule replicated_ruleset { > > > > ruleset 0 > > type replicated > > min_size 1 > > max_size 10 > > step take root > > step choose firstn 2 type datacenter > > step chooseleaf firstn 2 type host > > step emit > > } > > > > The question I have now is: how will it behave when a DC goes down? > > (Assuming catastrophic failure, the thing burns down) > > > > For example, if I set replication to 3, min_rep to 3. > > Then, if a DC goes down, crush will only return 2 PG's, so everything > will > > hang (same for 4/4 and 4/3) > > > > If I set replication to 3, min_rep to 2, it could occur that all data of > a > > PG is in one DC (degraded mode). if this DC goes down, the PG will > hang, > > As far as I know, degraded PG's will still accept writes, so data loss is > > possible. (same for 4/2) > > > > > > > > I can't seem to find a way around this. What am I missing. > > > > > > Wouter > > > > > > > > > > On Fri, Sep 18, 2015 at 10:10 PM, Gregory Farnum > wrote: > >> > >> On Fri, Sep 18, 2015 at 4:57 AM, Wouter De Borger > > >> wrote: > >> > Hi all, > >> > > >> > I have found on the mailing list that it should be possible to have a > >> > multi > >> > datacenter setup, if latency is low enough. >
[ceph-users] move/upgrade from straw to straw2
Hi, how can i upgrade / move from straw to straw2? I checked the docs but i was unable to find upgrade informations? Greets, Stefan ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Software Raid 1 for system disks on storage nodes (not for OSD disks)
On Fri, Sep 18, 2015 at 6:33 PM, Robert LeBlanc wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA256 > > Depends on how easy it is to rebuild an OS from scratch. If you have > something like Puppet or Chef that configure a node completely for > you, it may not be too much of a pain to forgo the RAID. We run our > OSD nodes from a single SATADOM and use Puppet for configuration. We > also don't use swap (not very effective on SATADOM), but have enough > RAM that we feel comfortable enough with that decision. > > If you use ceph-disk or ceph-deploy to configure the OSDs, then they > should automatically come back up when you lay down the new OS and set > up the necessary ceph config items (ceph.conf and the OSD bootstrap > keys). > Hello sir This sounds really interesting , could you please elaborate how after reinstalling OS and installing Ceph packages, how does Ceph detects OSD's that were hosted earlier on this node. I am using ceph-deploy to provision ceph , now what all changes i need to do after reinstalling OS of a OSD node. So that it should detect my OSD daemons. Please help me to know this step by step. Thanks in advance. Vickey > - > Robert LeBlanc > PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 > > > On Fri, Sep 18, 2015 at 9:06 AM, Martin Palma wrote: > > Hi, > > > > Is it a good idea to use a software raid for the system disk (Operating > > System) on a Ceph storage node? I mean only for the OS not for the OSD > > disks. > > > > And what about a swap partition? Is that needed? > > > > Best, > > Martin > > > > ___ > > ceph-users mailing list > > ceph-users@lists.ceph.com > > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > > -BEGIN PGP SIGNATURE- > Version: Mailvelope v1.1.0 > Comment: https://www.mailvelope.com > > wsFcBAEBCAAQBQJV/C7UCRDmVDuy+mK58QAAoTMQAMZBv4/lphmntC23b9/l > JWUPjZfbXUtNgnfMvWcVyTSXsTtM5mY/4/iSZ4ZfCQ4YyqWWMpSlocHONHFz > nFTtGupqV3vPCo4X8bl58/iv4J0H2iWUr2klk7jtTj+e+JjyWDo25l8V2ofP > edt5g7qcMAwiWYrrpjxQBK4AFNiPJKSMxrzK1Mgic15nwX0OJu0DDNS5twzZ > s8Y+UfS80+hZvyBTUGhsO8pkYoJQvYRGgyqYtCdxA+m1T8lWVe8SC0eLWOXy > xoyGR7dqcvEXQadrqfmU618eNpNEECPoHeIkeCqpTohrUVsyRcfSGAtfM0YY > Ixf2SCaDMAaRwvXGJUf5OP/3HHWps0m4YyLBOddPZ5XZb1utZiclh26KuOyw > QdGkP7uoYEMO0v40dcsIbOVhtgTdX+HrpEGuqEtNEGe194sS1nluw+49aLxe > eozHSRGq3GmRm/q3bR5f2p+WXwKqmdDRFhqII8H11bb5F7etU2PBo1JA2bTW > hUFqu6+ST8eI34OeC7LbC9Txfw/iUhL62kiCm+gj8Rg+m+TZ7a1HEaVc8uyq > Jw1+5hIgyTWFvKdIiW65k++8w9my6kUIsY8RT8p08DTSPzxuwGtHr7UJJ629 > K/tlpGdQTRf7PXgmea6sSodnmaF5HRIUdU0nhQpRRxjX/V+PENI8Qq45KyfX > BovV > =Gzvl > -END PGP SIGNATURE- > ___ > 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] how to get a mount list?
I'm assuming you mean from the server: you can list the clients of an MDS by SSHing to the server where it's running and doing "ceph daemon mds. session ls". This has been in releases since Giant iirc. Cheers, John On Mon, Sep 21, 2015 at 4:24 AM, domain0 wrote: > hi , > if use cephfs, how to get a client mount list? > > ___ > 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] move/upgrade from straw to straw2
On 21-09-15 11:06, Stefan Priebe - Profihost AG wrote: > Hi, > > how can i upgrade / move from straw to straw2? I checked the docs but i > was unable to find upgrade informations? > First make sure that all clients are running librados 0.9, but keep in mind that any running VMs or processes have to be restarted first. Afterwards, download the crushmap and change 'alg straw' to 'alg straw2'. You can also change 'straw_calc_version' to 2 in the CRUSHMap. Inject the newly compiled version and you're done. > Greets, > Stefan > > ___ > 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] move/upgrade from straw to straw2
On Mon, Sep 21, 2015 at 12:11 PM, Wido den Hollander wrote: > You can also change 'straw_calc_version' to 2 in the CRUSHMap. AFAIK straw_calc_version = 1 is the optimal. straw_calc_version = 2 is not defined. See src/crush/builder.c Cheers, Dan ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] snapshot failed after enable cache tier
Openstack Kilo use ceph as the backend storage (nova,cinder and glance),after enable cache tier for glance pool, take snapshot for instance failed (it seems generate the snapshot then delete it automatically soon) If cache tier not suitable for glance ? Best Regards! * [图像 007] 向毓(Raijin.Xiang) 计算与存储部(Computing and Storage Dept) 华为技术有限公司(Huawei Technologies Co., Ltd.) Mobile:+86 186 2032 2562 Mail: xiang...@huawei.com 地址:深圳市龙岗区坂田街道雪岗路2018号天安云谷产业园一期1栋B座 邮编:518129 Bldg1-B, Cloud Park, Huancheng Road, Bantian Str., Longgang District, 518129 Shenzhen, P. R. China *** ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] change ruleset with data
I have a ceph cluster set with two ruleset, each ruleset will select different osd, if can change ruleset for a pool online drectly(there have data exist on the pool) ? Best Regards! * [图像 007] 向毓(Raijin.Xiang) 计算与存储部(Computing and Storage Dept) 华为技术有限公司(Huawei Technologies Co., Ltd.) Mobile:+86 186 2032 2562 Mail: xiang...@huawei.com 地址:深圳市龙岗区坂田街道雪岗路2018号天安云谷产业园一期1栋B座 邮编:518129 Bldg1-B, Cloud Park, Huancheng Road, Bantian Str., Longgang District, 518129 Shenzhen, P. R. China *** ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] move/upgrade from straw to straw2
On 21-09-15 13:18, Dan van der Ster wrote: > On Mon, Sep 21, 2015 at 12:11 PM, Wido den Hollander wrote: >> You can also change 'straw_calc_version' to 2 in the CRUSHMap. > > AFAIK straw_calc_version = 1 is the optimal. straw_calc_version = 2 is > not defined. See src/crush/builder.c > Hmm, I could almost swear that I've done that on a setup. But if you say so :) @Stefan, change 'straw' to 'straw2' in your CRUSHMap. Wido > Cheers, Dan > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] snapshot failed after enable cache tier
Hi, depending on cache mode etc - from what we have also experienced (using CloudStack) - CEPH snapshot functionality simply stops working in some cache configuration. This means, we were also unable to deploy new VMs (base-gold snapshot is created on CEPH and new data disk which is child of snapshot etc). Inktank: https://download.inktank.com/docs/ICE%201.2%20-%20Cache%20and%20Erasure%20Coding%20FAQ.pdf Mail-list: https://www.mail-archive.com/ceph-users@lists.ceph.com/msg18338.html On 21 September 2015 at 13:36, Xiangyu (Raijin, BP&IT Dept) < xiang...@huawei.com> wrote: > Openstack Kilo use ceph as the backend storage (nova,cinder and > glance),after enable cache tier for glance pool, take snapshot for instance > failed (it seems generate the snapshot then delete it automatically soon) > > > > If cache tier not suitable for glance ? > > > > *Best Regards!* > > * > > [image: 图像 007] > > *向毓**(Raijin.Xiang)* > > 计算与存储部(Computing and Storage Dept) > > 华为技术有限公司(Huawei Technologies Co., Ltd.) > > Mobile:+86 186 2032 2562 > > Mail: xiang...@huawei.com > > 地址:深圳市龙岗区坂田街道雪岗路2018号天安云谷产业园一期1栋B座 邮编:518129 > Bldg1-B, Cloud Park, Huancheng Road, Bantian Str., Longgang District, > 518129 Shenzhen, P. R. China > > *** > > > > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > -- Andrija Panić ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] mds not starting ?
Hello, i'm facing a problem that mds seems not to start. I started mds in debug mode "ceph-mds -f -i storage08 --debug_mds 10" which outputs in the log: -- cut - 2015-09-21 14:12:14.313534 7ff47983d780 0 ceph version 0.94.3 (95cefea9fd9ab740263bf8bb4796fd864d9afe2b), process ceph-mds, pid 24787 starting mds.storage08 at :/0 2015-09-21 14:12:14.316062 7ff47983d780 10 mds.-1.0 168 MDSCacheObject 2015-09-21 14:12:14.316074 7ff47983d780 10 mds.-1.0 2408CInode 2015-09-21 14:12:14.316075 7ff47983d780 10 mds.-1.0 16 elist<>::item *7=112 2015-09-21 14:12:14.316077 7ff47983d780 10 mds.-1.0 480 inode_t 2015-09-21 14:12:14.316079 7ff47983d780 10 mds.-1.0 48nest_info_t 2015-09-21 14:12:14.316081 7ff47983d780 10 mds.-1.0 32frag_info_t 2015-09-21 14:12:14.316082 7ff47983d780 10 mds.-1.0 40 SimpleLock *5=200 2015-09-21 14:12:14.316083 7ff47983d780 10 mds.-1.0 48 ScatterLock *3=144 2015-09-21 14:12:14.316085 7ff47983d780 10 mds.-1.0 480 CDentry 2015-09-21 14:12:14.316086 7ff47983d780 10 mds.-1.0 16 elist<>::item 2015-09-21 14:12:14.316096 7ff47983d780 10 mds.-1.0 40 SimpleLock 2015-09-21 14:12:14.316097 7ff47983d780 10 mds.-1.0 952 CDir 2015-09-21 14:12:14.316098 7ff47983d780 10 mds.-1.0 16 elist<>::item *2=32 2015-09-21 14:12:14.316099 7ff47983d780 10 mds.-1.0 176 fnode_t 2015-09-21 14:12:14.316100 7ff47983d780 10 mds.-1.0 48nest_info_t *2 2015-09-21 14:12:14.316101 7ff47983d780 10 mds.-1.0 32frag_info_t *2 2015-09-21 14:12:14.316103 7ff47983d780 10 mds.-1.0 264 Capability 2015-09-21 14:12:14.316104 7ff47983d780 10 mds.-1.0 32 xlist<>::item *2=64 2015-09-21 14:12:14.316665 7ff47983d780 -1 mds.-1.0 log_to_monitors {default=true} 2015-09-21 14:12:14.320840 7ff4740c8700 7 mds.-1.server handle_osd_map: full = 0 epoch = 20 2015-09-21 14:12:14.320984 7ff47983d780 10 mds.beacon.storage08 _send up:boot seq 1 2015-09-21 14:12:14.321060 7ff47983d780 10 mds.-1.0 create_logger 2015-09-21 14:12:14.321234 7ff4740c8700 5 mds.-1.0 handle_mds_map epoch 1 from mon.1 2015-09-21 14:12:14.321256 7ff4740c8700 10 mds.-1.0 my compat compat={},rocompat={},incompat={1=base v0.20,2=client writeable ranges,3=default file layouts on dirs,4=dir inode in separate object,5=mds uses versioned encoding,6=dirfrag is stored in omap,7=mds uses inline data,8=no anchor table} 2015-09-21 14:12:14.321264 7ff4740c8700 10 mds.-1.0 mdsmap compat compat={},rocompat={},incompat={} 2015-09-21 14:12:14.321267 7ff4740c8700 10 mds.-1.-1 map says i am 192.168.0.178:6802/24787 mds.-1.-1 state down:dne 2015-09-21 14:12:14.321272 7ff4740c8700 10 mds.-1.-1 not in map yet 2015-09-21 14:12:14.321305 7ff4740c8700 7 mds.-1.server handle_osd_map: full = 0 epoch = 20 2015-09-21 14:12:14.321443 7ff4740c8700 5 mds.-1.-1 handle_mds_map epoch 1 from mon.1 2015-09-21 14:12:14.321447 7ff4740c8700 5 mds.-1.-1 old map epoch 1 <= 1, discarding 2015-09-21 14:12:18.321061 7ff4707c0700 10 mds.beacon.storage08 _send up:boot seq 2 2015-09-21 14:12:19.321093 7ff470fc1700 10 MDSInternalContextBase::complete: N3MDS10C_MDS_TickE 2015-09-21 14:12:22.321119 7ff4707c0700 10 mds.beacon.storage08 _send up:boot seq 3 2015-09-21 14:12:24.321169 7ff470fc1700 10 MDSInternalContextBase::complete: N3MDS10C_MDS_TickE ... -- cut - "cheph -s" shows: cluster 982924a3-32e7-401f-9975-018bb697d717 health HEALTH_OK monmap e1: 3 mons at {0=192.168.0.176:6789/0,1=192.168.0.177:6789/0,2=192.168.0.178:6789/0} election epoch 6, quorum 0,1,2 0,1,2 osdmap e20: 3 osds: 3 up, 3 in pgmap v39: 64 pgs, 1 pools, 0 bytes data, 0 objects 15541 MB used, 388 GB / 403 GB avail 64 active+clean As you see MONs and OSDs seem to be happy. I'm missing the "mdsmap" entry here. Try to verify with the command "ceph mds stat" gives: e1: 0/0/0 up The section of ceph.conf regarding mds reads: [mds] mds data = /var/lib/ceph/mds/ceph-$id keyring = /var/lib/ceph/mds/ceph-$id/keyring [mds.storage08] host = storage08 mds addr = 192.168.0.178 Configuration: 3 Hosts Gentoo Linux (kernel 4.0.5) Ceph 0.94.3 All have MON and OSD One has MDS additionally. Any idea for on how the MDS to get running ? Kind regards Petric ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] move/upgrade from straw to straw2
Am 21.09.2015 um 13:47 schrieb Wido den Hollander: > > > On 21-09-15 13:18, Dan van der Ster wrote: >> On Mon, Sep 21, 2015 at 12:11 PM, Wido den Hollander wrote: >>> You can also change 'straw_calc_version' to 2 in the CRUSHMap. >> >> AFAIK straw_calc_version = 1 is the optimal. straw_calc_version = 2 is >> not defined. See src/crush/builder.c >> > > Hmm, I could almost swear that I've done that on a setup. But if you say > so :) > > > @Stefan, change 'straw' to 'straw2' in your CRUSHMap. THX > > Wido > >> Cheers, Dan >> > ___ > 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] mds not starting ?
Follow the instructions here to set up a filesystem: http://docs.ceph.com/docs/master/cephfs/createfs/ It looks like you haven't done "ceph fs new". Cheers, John On Mon, Sep 21, 2015 at 1:34 PM, Frank, Petric (Petric) wrote: > Hello, > > i'm facing a problem that mds seems not to start. > > I started mds in debug mode "ceph-mds -f -i storage08 --debug_mds 10" which > outputs in the log: > > -- cut - > 2015-09-21 14:12:14.313534 7ff47983d780 0 ceph version 0.94.3 > (95cefea9fd9ab740263bf8bb4796fd864d9afe2b), process ceph-mds, pid 24787 > starting mds.storage08 at :/0 > 2015-09-21 14:12:14.316062 7ff47983d780 10 mds.-1.0 168 MDSCacheObject > 2015-09-21 14:12:14.316074 7ff47983d780 10 mds.-1.0 2408CInode > 2015-09-21 14:12:14.316075 7ff47983d780 10 mds.-1.0 16 elist<>::item > *7=112 > 2015-09-21 14:12:14.316077 7ff47983d780 10 mds.-1.0 480 inode_t > 2015-09-21 14:12:14.316079 7ff47983d780 10 mds.-1.0 48nest_info_t > 2015-09-21 14:12:14.316081 7ff47983d780 10 mds.-1.0 32frag_info_t > 2015-09-21 14:12:14.316082 7ff47983d780 10 mds.-1.0 40 SimpleLock *5=200 > 2015-09-21 14:12:14.316083 7ff47983d780 10 mds.-1.0 48 ScatterLock *3=144 > 2015-09-21 14:12:14.316085 7ff47983d780 10 mds.-1.0 480 CDentry > 2015-09-21 14:12:14.316086 7ff47983d780 10 mds.-1.0 16 elist<>::item > 2015-09-21 14:12:14.316096 7ff47983d780 10 mds.-1.0 40 SimpleLock > 2015-09-21 14:12:14.316097 7ff47983d780 10 mds.-1.0 952 CDir > 2015-09-21 14:12:14.316098 7ff47983d780 10 mds.-1.0 16 elist<>::item *2=32 > 2015-09-21 14:12:14.316099 7ff47983d780 10 mds.-1.0 176 fnode_t > 2015-09-21 14:12:14.316100 7ff47983d780 10 mds.-1.0 48nest_info_t *2 > 2015-09-21 14:12:14.316101 7ff47983d780 10 mds.-1.0 32frag_info_t *2 > 2015-09-21 14:12:14.316103 7ff47983d780 10 mds.-1.0 264 Capability > 2015-09-21 14:12:14.316104 7ff47983d780 10 mds.-1.0 32 xlist<>::item *2=64 > 2015-09-21 14:12:14.316665 7ff47983d780 -1 mds.-1.0 log_to_monitors > {default=true} > 2015-09-21 14:12:14.320840 7ff4740c8700 7 mds.-1.server handle_osd_map: full > = 0 epoch = 20 > 2015-09-21 14:12:14.320984 7ff47983d780 10 mds.beacon.storage08 _send up:boot > seq 1 > 2015-09-21 14:12:14.321060 7ff47983d780 10 mds.-1.0 create_logger > 2015-09-21 14:12:14.321234 7ff4740c8700 5 mds.-1.0 handle_mds_map epoch 1 > from mon.1 > 2015-09-21 14:12:14.321256 7ff4740c8700 10 mds.-1.0 my compat > compat={},rocompat={},incompat={1=base v0.20,2=client writeable > ranges,3=default file layouts on dirs,4=dir inode in separate object,5=mds > uses versioned encoding,6=dirfrag is stored in omap,7=mds uses inline > data,8=no anchor table} > 2015-09-21 14:12:14.321264 7ff4740c8700 10 mds.-1.0 mdsmap compat > compat={},rocompat={},incompat={} > 2015-09-21 14:12:14.321267 7ff4740c8700 10 mds.-1.-1 map says i am > 192.168.0.178:6802/24787 mds.-1.-1 state down:dne > 2015-09-21 14:12:14.321272 7ff4740c8700 10 mds.-1.-1 not in map yet > 2015-09-21 14:12:14.321305 7ff4740c8700 7 mds.-1.server handle_osd_map: full > = 0 epoch = 20 > 2015-09-21 14:12:14.321443 7ff4740c8700 5 mds.-1.-1 handle_mds_map epoch 1 > from mon.1 > 2015-09-21 14:12:14.321447 7ff4740c8700 5 mds.-1.-1 old map epoch 1 <= 1, > discarding > 2015-09-21 14:12:18.321061 7ff4707c0700 10 mds.beacon.storage08 _send up:boot > seq 2 > 2015-09-21 14:12:19.321093 7ff470fc1700 10 MDSInternalContextBase::complete: > N3MDS10C_MDS_TickE > 2015-09-21 14:12:22.321119 7ff4707c0700 10 mds.beacon.storage08 _send up:boot > seq 3 > 2015-09-21 14:12:24.321169 7ff470fc1700 10 MDSInternalContextBase::complete: > N3MDS10C_MDS_TickE > ... > -- cut - > > "cheph -s" shows: > > cluster 982924a3-32e7-401f-9975-018bb697d717 > health HEALTH_OK > monmap e1: 3 mons at > {0=192.168.0.176:6789/0,1=192.168.0.177:6789/0,2=192.168.0.178:6789/0} > election epoch 6, quorum 0,1,2 0,1,2 > osdmap e20: 3 osds: 3 up, 3 in > pgmap v39: 64 pgs, 1 pools, 0 bytes data, 0 objects > 15541 MB used, 388 GB / 403 GB avail > 64 active+clean > > As you see MONs and OSDs seem to be happy. > I'm missing the "mdsmap" entry here. Try to verify with the command "ceph mds > stat" gives: > > e1: 0/0/0 up > > The section of ceph.conf regarding mds reads: > [mds] > mds data = /var/lib/ceph/mds/ceph-$id > keyring = /var/lib/ceph/mds/ceph-$id/keyring > [mds.storage08] > host = storage08 > mds addr = 192.168.0.178 > > > Configuration: > 3 Hosts > Gentoo Linux (kernel 4.0.5) > Ceph 0.94.3 > All have MON and OSD > One has MDS additionally. > > > Any idea for on how the MDS to get running ? > > > Kind regards > Petric > > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com ___ ceph-users mai
Re: [ceph-users] Important security noticed regarding release signing key
Hi, Forgive the question if the answer is obvious... It's been more than "an hour or so" and eu.ceph.com apparently still hasn't been re-signed or at least what I checked wasn't : # rpm -qp --qf '%{RSAHEADER:pgpsig}' http://eu.ceph.com/rpm-hammer/el7/x86_64/ceph-0.94.3-0.el7.centos.x86_64.rpm RSA/SHA1, Wed 26 Aug 2015 09:57:17 PM CEST, Key ID 7ebfdd5d17ed316d Should this repository/mirror be discarded and should we (in EU) switch to download.ceph.com ? Thanks && regards -Message d'origine- De : ceph-users [mailto:ceph-users-boun...@lists.ceph.com] De la part de Sage Weil Envoyé : jeudi 17 septembre 2015 18:30 À : ceph-annou...@ceph.com; ceph-de...@vger.kernel.org; ceph-us...@ceph.com; ceph-maintain...@ceph.com Objet : [ceph-users] Important security noticed regarding release signing key -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Last week, Red Hat investigated an intrusion on the sites of both the Ceph community project (ceph.com) and Inktank (download.inktank.com), which were hosted on a computer system outside of Red Hat infrastructure. Ceph.com provided Ceph community versions downloads signed with a Ceph signing key (id 7EBFDD5D17ED316D). Download.inktank.comprovided releases of the Red Hat Ceph product for Ubuntu and CentOS operating systems signed with an Inktank signing key (id 5438C7019DCEEEAD). While the investigation into the intrusion is ongoing, our initial focus was on the integrity of the software and distribution channel for both sites. To date, our investigation has not discovered any compromised code or binaries available for download on these sites. However, we cannot fully rule out the possibility that some compromised code or binaries were available for download at some point in the past. Further, we can no longer trust the integrity of the Ceph signing key, and therefore have created a new signing key (id E84AC2C0460F3994) for verifying downloads. This new key is committed to the ceph.git repository and is also available from https://git.ceph.com/release.asc The new key should look like: pub 4096R/460F3994 2015-09-15 uid Ceph.com (release key) All future release git tags will be signed with this new key. This intrusion did not affect other Ceph sites such as download.ceph.com (which contained some older Ceph downloads) or git.ceph.com (which mirrors various source repositories), and is not known to have affected any other Ceph community infrastructure. There is no evidence that build system or the Ceph github source repository were compromised. New hosts for ceph.com and download.ceph.com have been created and the sites have been rebuilt. All content available on download.ceph.com as been verified, and all ceph.com URLs for package locations now redirect there. There is still some content missing from download.ceph.com that will appear later today: source tarballs will be regenerated from git, and older release packages are being resigned with the new release key DNS changes are still propogating so you may not see the new versions of the ceph.com and download.ceph.com sites for another hour or so. The download.inktank.com host has been retired and affected Red Hat customers have been notified, further information is available at https://securityblog.redhat.com/2015/09/17/. Users of Ceph packages should take action as a precautionary measure to download the newly-signed versions. Please see the instructions below. The Ceph community would like to thank Kai Fabian for initially alerting us to this issue. Any questions can be directed to the email discussion lists or the #ceph IRC channel on irc.oftc.net. Thank you! sage - - The following steps should be performed on all nodes with Ceph software installed. Replace APT keys (Debian, Ubuntu) sudo apt-key del 17ED316D curl https://git.ceph.com/release.asc | sudo apt-key add - Replace RPM keys (Fedora, CentOS, SUSE, etc.) sudo rpm -e --allmatches gpg-pubkey-17ed316d-4fb96ee8 sudo rpm --import 'https://git.ceph.com/release.asc' Reinstalling packages (Fedora, CentOS, SUSE, etc.) sudo yum clean metadata sudo yum reinstall -y $(repoquery --disablerepo= --enablerepo=ceph \ --queryformat='%{NAME}' list '*') -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.10 (GNU/Linux) iEYEARECAAYFAlX66k0ACgkQ2kQg7SiJlcg0wQCfVy+/2BfoNqtCfAcbuNABczFx bpIAoLf8RTHisIn5wFvEb4Akym/UNn5l =SEws -END PGP SIGNATURE- ___ 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] mds not starting ?
Hello John, that was the info i missed (both - create pools and fs). Works now. Thank you very much. Kind regards Petric > -Original Message- > From: John Spray [mailto:jsp...@redhat.com] > Sent: Montag, 21. September 2015 14:41 > To: Frank, Petric (Petric) > Cc: ceph-users@lists.ceph.com > Subject: Re: [ceph-users] mds not starting ? > > Follow the instructions here to set up a filesystem: > http://docs.ceph.com/docs/master/cephfs/createfs/ > > It looks like you haven't done "ceph fs new". > > Cheers, > John > > On Mon, Sep 21, 2015 at 1:34 PM, Frank, Petric (Petric) > wrote: > > Hello, > > > > i'm facing a problem that mds seems not to start. > > > > I started mds in debug mode "ceph-mds -f -i storage08 --debug_mds 10" > which outputs in the log: > > > > -- cut - > > 2015-09-21 14:12:14.313534 7ff47983d780 0 ceph version 0.94.3 > > (95cefea9fd9ab740263bf8bb4796fd864d9afe2b), process ceph-mds, pid > > 24787 starting mds.storage08 at :/0 > > 2015-09-21 14:12:14.316062 7ff47983d780 10 mds.-1.0 168 > MDSCacheObject > > 2015-09-21 14:12:14.316074 7ff47983d780 10 mds.-1.0 2408 > CInode > > 2015-09-21 14:12:14.316075 7ff47983d780 10 mds.-1.0 16 > elist<>::item *7=112 > > 2015-09-21 14:12:14.316077 7ff47983d780 10 mds.-1.0 480 inode_t > > 2015-09-21 14:12:14.316079 7ff47983d780 10 mds.-1.0 48nest_info_t > > 2015-09-21 14:12:14.316081 7ff47983d780 10 mds.-1.0 32frag_info_t > > 2015-09-21 14:12:14.316082 7ff47983d780 10 mds.-1.0 40 SimpleLock > *5=200 > > 2015-09-21 14:12:14.316083 7ff47983d780 10 mds.-1.0 48 ScatterLock > *3=144 > > 2015-09-21 14:12:14.316085 7ff47983d780 10 mds.-1.0 480 CDentry > > 2015-09-21 14:12:14.316086 7ff47983d780 10 mds.-1.0 16 > elist<>::item > > 2015-09-21 14:12:14.316096 7ff47983d780 10 mds.-1.0 40 SimpleLock > > 2015-09-21 14:12:14.316097 7ff47983d780 10 mds.-1.0 952 CDir > > 2015-09-21 14:12:14.316098 7ff47983d780 10 mds.-1.0 16 > elist<>::item *2=32 > > 2015-09-21 14:12:14.316099 7ff47983d780 10 mds.-1.0 176 fnode_t > > 2015-09-21 14:12:14.316100 7ff47983d780 10 mds.-1.0 48nest_info_t > *2 > > 2015-09-21 14:12:14.316101 7ff47983d780 10 mds.-1.0 32frag_info_t > *2 > > 2015-09-21 14:12:14.316103 7ff47983d780 10 mds.-1.0 264 Capability > > 2015-09-21 14:12:14.316104 7ff47983d780 10 mds.-1.0 32 > xlist<>::item *2=64 > > 2015-09-21 14:12:14.316665 7ff47983d780 -1 mds.-1.0 log_to_monitors > > {default=true} > > 2015-09-21 14:12:14.320840 7ff4740c8700 7 mds.-1.server > > handle_osd_map: full = 0 epoch = 20 > > 2015-09-21 14:12:14.320984 7ff47983d780 10 mds.beacon.storage08 _send > > up:boot seq 1 > > 2015-09-21 14:12:14.321060 7ff47983d780 10 mds.-1.0 create_logger > > 2015-09-21 14:12:14.321234 7ff4740c8700 5 mds.-1.0 handle_mds_map > epoch 1 from mon.1 > > 2015-09-21 14:12:14.321256 7ff4740c8700 10 mds.-1.0 my compat > compat={},rocompat={},incompat={1=base v0.20,2=client writeable > ranges,3=default file layouts on dirs,4=dir inode in separate > object,5=mds uses versioned encoding,6=dirfrag is stored in omap,7=mds > uses inline data,8=no anchor table} > > 2015-09-21 14:12:14.321264 7ff4740c8700 10 mds.-1.0 mdsmap compat > > compat={},rocompat={},incompat={} > > 2015-09-21 14:12:14.321267 7ff4740c8700 10 mds.-1.-1 map says i am > > 192.168.0.178:6802/24787 mds.-1.-1 state down:dne > > 2015-09-21 14:12:14.321272 7ff4740c8700 10 mds.-1.-1 not in map yet > > 2015-09-21 14:12:14.321305 7ff4740c8700 7 mds.-1.server > > handle_osd_map: full = 0 epoch = 20 > > 2015-09-21 14:12:14.321443 7ff4740c8700 5 mds.-1.-1 handle_mds_map > > epoch 1 from mon.1 > > 2015-09-21 14:12:14.321447 7ff4740c8700 5 mds.-1.-1 old map epoch 1 > > <= 1, discarding > > 2015-09-21 14:12:18.321061 7ff4707c0700 10 mds.beacon.storage08 _send > > up:boot seq 2 > > 2015-09-21 14:12:19.321093 7ff470fc1700 10 > > MDSInternalContextBase::complete: N3MDS10C_MDS_TickE > > 2015-09-21 14:12:22.321119 7ff4707c0700 10 mds.beacon.storage08 _send > > up:boot seq 3 > > 2015-09-21 14:12:24.321169 7ff470fc1700 10 > > MDSInternalContextBase::complete: N3MDS10C_MDS_TickE ... > > -- cut - > > > > "cheph -s" shows: > > > > cluster 982924a3-32e7-401f-9975-018bb697d717 > > health HEALTH_OK > > monmap e1: 3 mons at > {0=192.168.0.176:6789/0,1=192.168.0.177:6789/0,2=192.168.0.178:6789/0} > > election epoch 6, quorum 0,1,2 0,1,2 > > osdmap e20: 3 osds: 3 up, 3 in > > pgmap v39: 64 pgs, 1 pools, 0 bytes data, 0 objects > > 15541 MB used, 388 GB / 403 GB avail > > 64 active+clean > > > > As you see MONs and OSDs seem to be happy. > > I'm missing the "mdsmap" entry here. Try to verify with the command > "ceph mds stat" gives: > > > > e1: 0/0/0 up > > > > The section of ceph.conf regarding mds reads: > > [mds] > > mds data = /var/lib/ceph/mds/ceph-$id > > keyring = /var/lib/ceph/mds/ceph-$id/keyring > > [mds
[ceph-users] mds0: Client client008 failing to respond to capability release
Hi all! A quick question: We are syncing data over cephfs , and we are seeing messages in our output like: mds0: Client client008 failing to respond to capability release What does this mean? I don't find information about this somewhere else. We are running ceph 9.0.3 On earlier versions, we often saw messages like 'failing to respond to cache pressure', is this related? Thanks! Kenneth ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Important security noticed regarding release signing key
On 21-09-15 15:05, SCHAER Frederic wrote: > Hi, > > Forgive the question if the answer is obvious... It's been more than "an hour > or so" and eu.ceph.com apparently still hasn't been re-signed or at least > what I checked wasn't : > > # rpm -qp --qf '%{RSAHEADER:pgpsig}' > http://eu.ceph.com/rpm-hammer/el7/x86_64/ceph-0.94.3-0.el7.centos.x86_64.rpm > RSA/SHA1, Wed 26 Aug 2015 09:57:17 PM CEST, Key ID 7ebfdd5d17ed316d > > Should this repository/mirror be discarded and should we (in EU) switch to > download.ceph.com ? I fixed eu.ceph.com by putting a Varnish HTTP cache in between which now links to ceph.com You can still use eu.ceph.com and should be able to do so. eu.ceph.com caches all traffic so that should be much snappier then downloading everything from download.ceph.com directly. Wido > > Thanks && regards > > > -Message d'origine- > De : ceph-users [mailto:ceph-users-boun...@lists.ceph.com] De la part de Sage > Weil > Envoyé : jeudi 17 septembre 2015 18:30 > À : ceph-annou...@ceph.com; ceph-de...@vger.kernel.org; ceph-us...@ceph.com; > ceph-maintain...@ceph.com > Objet : [ceph-users] Important security noticed regarding release signing key > > Last week, Red Hat investigated an intrusion on the sites of both the Ceph > community project (ceph.com) and Inktank (download.inktank.com), which > were hosted on a computer system outside of Red Hat infrastructure. > > Ceph.com provided Ceph community versions downloads signed with a Ceph > signing key (id 7EBFDD5D17ED316D). Download.inktank.comprovided releases > of the Red Hat Ceph product for Ubuntu and CentOS operating systems signed > with an Inktank signing key (id 5438C7019DCEEEAD). While the investigation > into the intrusion is ongoing, our initial focus was on the integrity of > the software and distribution channel for both sites. > > To date, our investigation has not discovered any compromised code or > binaries available for download on these sites. However, we cannot fully > rule out the possibility that some compromised code or binaries were > available for download at some point in the past. Further, we can no > longer trust the integrity of the Ceph signing key, and therefore have > created a new signing key (id E84AC2C0460F3994) for verifying downloads. > This new key is committed to the ceph.git repository and is > also available from > > https://git.ceph.com/release.asc > > The new key should look like: > > pub 4096R/460F3994 2015-09-15 > uid Ceph.com (release key) > > All future release git tags will be signed with this new key. > > This intrusion did not affect other Ceph sites such as download.ceph.com > (which contained some older Ceph downloads) or git.ceph.com (which mirrors > various source repositories), and is not known to have affected any other > Ceph community infrastructure. There is no evidence that build system or > the Ceph github source repository were compromised. > > New hosts for ceph.com and download.ceph.com have been created and the > sites have been rebuilt. All content available on download.ceph.com as > been verified, and all ceph.com URLs for package locations now redirect > there. There is still some content missing from download.ceph.com that > will appear later today: source tarballs will be regenerated from git, and > older release packages are being resigned with the new release key DNS > changes are still propogating so you may not see the new versions of the > ceph.com and download.ceph.com sites for another hour or so. > > The download.inktank.com host has been retired and affected Red Hat > customers have been notified, further information is available at > https://securityblog.redhat.com/2015/09/17/. > > Users of Ceph packages should take action as a precautionary measure to > download the newly-signed versions. Please see the instructions below. > > The Ceph community would like to thank Kai Fabian for initially alerting > us to this issue. > > Any questions can be directed to the email discussion lists or the #ceph > IRC channel on irc.oftc.net. > > Thank you! > sage > > - > > The following steps should be performed on all nodes with Ceph software > installed. > > Replace APT keys (Debian, Ubuntu) > > sudo apt-key del 17ED316D > curl https://git.ceph.com/release.asc | sudo apt-key add - > > Replace RPM keys (Fedora, CentOS, SUSE, etc.) > > sudo rpm -e --allmatches gpg-pubkey-17ed316d-4fb96ee8 > sudo rpm --import 'https://git.ceph.com/release.asc' > > Reinstalling packages (Fedora, CentOS, SUSE, etc.) > > sudo yum clean metadata > sudo yum reinstall -y $(repoquery --disablerepo= --enablerepo=ceph \ > --queryformat='%{NAME}' list '*') > > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > __
Re: [ceph-users] Important security noticed regarding release signing key
On Mon, Sep 21, 2015 at 3:50 PM, Wido den Hollander wrote: > > > On 21-09-15 15:05, SCHAER Frederic wrote: >> Hi, >> >> Forgive the question if the answer is obvious... It's been more than "an >> hour or so" and eu.ceph.com apparently still hasn't been re-signed or at >> least what I checked wasn't : >> >> # rpm -qp --qf '%{RSAHEADER:pgpsig}' >> http://eu.ceph.com/rpm-hammer/el7/x86_64/ceph-0.94.3-0.el7.centos.x86_64.rpm >> RSA/SHA1, Wed 26 Aug 2015 09:57:17 PM CEST, Key ID 7ebfdd5d17ed316d >> >> Should this repository/mirror be discarded and should we (in EU) switch to >> download.ceph.com ? > > I fixed eu.ceph.com by putting a Varnish HTTP cache in between which now > links to ceph.com > > You can still use eu.ceph.com and should be able to do so. > > eu.ceph.com caches all traffic so that should be much snappier then > downloading everything from download.ceph.com directly. > Thanks Wido for running this mirror/cache! It's a pity though now that rsync'ing eu.ceph.com won't work. (And I guess you should close eu.ceph.com's rsync doors now because it still serves up the old packages). Cheers, Dan ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] EU Ceph mirror changes
Hi, Since the security notice regarding ceph.com the mirroring system broke. This meant that eu.ceph.com didn't serve new packages since the whole download system changed. I didn't have much time to fix this, but today I resolved it by installing Varnish [0] on eu.ceph.com The VCL which is being used on eu.ceph.com can be found on my Github gist page [1]. All URLs to eu.ceph.com should still work and data is served from the EU. rsync is however no longer available since all data is stored in memory and is downloaded from 'download.ceph.com' when not available locally. It's not a ideal mirroring system right now, but it still works. If you have multiple machines downloading the same package, the first request for a RPM / DEB might be a cache-miss which requires a download from the US, but afterwards it should serve the other requests from cache. The VCL [1] I use can also be used locally on your own mirror. Feel free to use it. I'll try to keep the one on Github as up to date as possible. Wido [0]: http://www.varnish-cache.org/ [1]: https://gist.github.com/wido/40ffb92ea99842c2666b ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Important security noticed regarding release signing key
On 21-09-15 15:57, Dan van der Ster wrote: > On Mon, Sep 21, 2015 at 3:50 PM, Wido den Hollander wrote: >> >> >> On 21-09-15 15:05, SCHAER Frederic wrote: >>> Hi, >>> >>> Forgive the question if the answer is obvious... It's been more than "an >>> hour or so" and eu.ceph.com apparently still hasn't been re-signed or at >>> least what I checked wasn't : >>> >>> # rpm -qp --qf '%{RSAHEADER:pgpsig}' >>> http://eu.ceph.com/rpm-hammer/el7/x86_64/ceph-0.94.3-0.el7.centos.x86_64.rpm >>> RSA/SHA1, Wed 26 Aug 2015 09:57:17 PM CEST, Key ID 7ebfdd5d17ed316d >>> >>> Should this repository/mirror be discarded and should we (in EU) switch to >>> download.ceph.com ? >> >> I fixed eu.ceph.com by putting a Varnish HTTP cache in between which now >> links to ceph.com >> >> You can still use eu.ceph.com and should be able to do so. >> >> eu.ceph.com caches all traffic so that should be much snappier then >> downloading everything from download.ceph.com directly. >> > > Thanks Wido for running this mirror/cache! > You're welcome! > It's a pity though now that rsync'ing eu.ceph.com won't work. (And I > guess you should close eu.ceph.com's rsync doors now because it still > serves up the old packages). I just did. It's only serving HTTP now. The active data should all be in cache now, so downloads should be fast. I personally love Varnish, great reverse HTTP proxy. Wido > > Cheers, Dan > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] multi-datacenter crush map
-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 On Mon, Sep 21, 2015 at 3:02 AM, Wouter De Borger wrote: > Thank you for your answer! We will use size=4 and min_size=2, which should > do the trick. > > For the monitor issue, we have a third datacenter (with higher latency, but > that shouldn't be a problem for the monitors) Just be sure that the IP address in the third DC is higher than the other two. Ceph chooses the lowest IP address as the primary monitor. Having the monitor with the highest latency as your primary is sure to give you grief. > We had also considered the locality issue. Our WAN round trip latency is 1.5 > ms (now) and we should get a dedicated light path in the near future (<0.1 > ms). > So we hope to get acceptable latency without additional tweaking. > The plan B is to make two pools, with different weights for the different > DC's. VM's in DC 1 will get high weight for DC 1, VM's in DC 2 will get high > weight for DC 2. You don't want to mess with weights or else you will get stuck PGs because there isn't enough storage at the remote DC to hold all your data or the local DC fills up faster or CRUSH can't figure out how to distribute balanced data in an unbalanced way. You will probably want to look at primary affinity. This talks about SSD, but the same principle applies http://www.sebastien-han.fr/blog/2015/08/06/ceph-get-the-best-of-your-ssd-with-primary-affinity/ - Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 -BEGIN PGP SIGNATURE- Version: Mailvelope v1.1.0 Comment: https://www.mailvelope.com wsFcBAEBCAAQBQJWAA80CRDmVDuy+mK58QAAK2UQAIadviUNo+hybghYO2de 0Ayqy1SQ9hPjpwJUTWt0VKIgIoDMMbp1+LVd6EiPRNXPPwalDZen8z1ARW5F o0g0nxMkJIJWxY2U3ch4s3oE85Hl5NqyPZIdaLfqQv7PXfFsRTM7rZDMRuLn X9PWcxzZ3lvXj6WA/jiN42zXlhTlhLhtKV153poCtd/iCkytJUEPZF/c+Pr+ /mIVVbbtzPDh5XC/Il/KEI1W+fZzPG27EL6N2YoskYWTEpUr0auBH7jTLm8B kk4HKZToBsakP/j/LEhrh+MMW/ZNwuUaigWe351YQrkmlUBXxKVtnlgfJpDL KIGvVDICRMwe6e3ubU7umsiFVchYPBlXFN3OoRmx3UfPp3WlfKong+PG9X8+ JoukMyj630jmaDy7KPH5sKv+LUaLpWlWv6271bVUDlSMjPNHqVMlk/HsOGit QYaWQQygQ+D/YedLP66xz+O6A8qfmrYfWBZZDdG9C49erw6Q6Ihzp6u+Hj1O zt96JsmBjHcq27AfK1jSbZDGOHchL78/Ok3O4O01tC00HwRvQLy/ofppOzgn KHnuLMs/9fZpSqh5sZ1BxWSgKBnYzc3npFloaOZLoVPT4Dv+hM8kL9lF0mHm 3j1D4ZmysVaSU+zVw0WsWaNVQyrrPn+i9ivT6U/3VHiaS2Nz+BQTQeq0oMqQ awOM =sl/W -END PGP SIGNATURE- ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] change ruleset with data
-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 I think you will be OK, but you should double check on a test cluster. You should be able to revert the rulesets if the data isn't found. - Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 On Mon, Sep 21, 2015 at 5:42 AM, Xiangyu (Raijin, BP&IT Dept) wrote: I have a ceph cluster set with two ruleset, each ruleset will select different osd, if can change ruleset for a pool online drectly(there have data exist on the pool) ? Best Regards! * 向毓(Raijin.Xiang) 计算与存储部(Computing and Storage Dept) 华为技术有限公司(Huawei Technologies Co., Ltd.) Mobile:+86 186 2032 2562 Mail: xiang...@huawei.com 地址:深圳市龙岗区坂田街道雪岗路2018号天安云谷产业园一期1栋B座 邮编:518129 Bldg1-B, Cloud Park, Huancheng Road, Bantian Str., Longgang District, 518129 Shenzhen, P. R. China *** ___ ceph-users mailing listceph-us...@lists.ceph.comhttp://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -BEGIN PGP SIGNATURE- Version: Mailvelope v1.1.0 Comment: https://www.mailvelope.com wsFcBAEBCAAQBQJWABD7CRDmVDuy+mK58QAAJvMP/RVKLWw+HN3mF35VXkOc Resrw0CjLw3z/Rsh1qZ3j/OrMvGY3RmrEWRldOUEy8sn5dNsMOKr+pRPeCi2 9t8y4JxsCHsvrIKJGHa4Btbz5f9ZVzafJhkjeykeQGDrSMrJaIARLy0Lrjrm F+cZ05gb9cWDLbAGARN3oUl3HEbFdJ3T9jXJhuzgiwKCRwwgaacNykGl0oNR IkesOITrRsZDxSma4YjqGxrNgTh/pdO4r0C9GLq6Iva73qE/XZw5J+1YrzPa jeIkSZtU0nUGolF83/yVRuDL7EdCNvq1qeWhsX70URBNDthpOtGlxhdPnOkc U3PVTHU4fnPwT+bSbJ81YfcCn6URa316MTOQGTGYRB6BtvrfUtqRWjTrJlD+ vlJBqWK4eTfiG1RSC1gFrOkPxOP9+A0wJW6K3SHbRiz5Hi0Dqr+msR9R5k1H prq1pV6r4o71YoS9vjyKoVMHvqUVN2VFge6sjqnnvbqUsLCluwDzevZN15nB DIVFtyiSq1UtOHdSyYTvQbKs7HnedM0HQ0Fhn0Zkaf8blgq2MDOVGmRyoGcb 8uYy11Pc88GZJmVLYOeOQPE3qt9yddosYf38EHBeweNVVTAlMw9/ipAe/6Gb +jUzv4b3K9hlr0+GZEPTGSNQtHvZj5F9gKskj+Ti6LU4ryUtH/08GiWXL4Xp yD3y =HOeT -END PGP SIGNATURE- ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] snapshot failed after enable cache tier
-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 If I recall, there was a bug or two that was found with cache tiers and snapshots and were fixed. I hope it is being backported to Hammer. I don't know if this exactly fixes your issue. - Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 On Mon, Sep 21, 2015 at 6:09 AM, Andrija Panic wrote: Hi, depending on cache mode etc - from what we have also experienced (using CloudStack) - CEPH snapshot functionality simply stops working in some cache configuration. This means, we were also unable to deploy new VMs (base-gold snapshot is created on CEPH and new data disk which is child of snapshot etc). Inktank:https://download.inktank.com/docs/ICE%201.2%20-%20Cache%20and%20Erasure%20Coding%20FAQ.pdf Mail-list:https://www.mail-archive.com/ceph-users@lists.ceph.com/msg18338.html On 21 September 2015 at 13:36, Xiangyu (Raijin, BP&IT Dept) wrote: Openstack Kilo use ceph as the backend storage (nova,cinder and glance),after enable cache tier for glance pool, take snapshot for instance failed (it seems generate the snapshot then delete it automatically soon) If cache tier not suitable for glance ? Best Regards! * 向毓(Raijin.Xiang) 计算与存储部(Computing and Storage Dept) 华为技术有限公司(Huawei Technologies Co., Ltd.) Mobile:+86 186 2032 2562 Mail: xiang...@huawei.com 地址:深圳市龙岗区坂田街道雪岗路2018号天安云谷产业园一期1栋B座 邮编:518129 Bldg1-B, Cloud Park, Huancheng Road, Bantian Str., Longgang District, 518129 Shenzhen, P. R. China *** ___ ceph-users mailing listceph-us...@lists.ceph.comhttp://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com - -- Andrija Panić ___ ceph-users mailing listceph-us...@lists.ceph.comhttp://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -BEGIN PGP SIGNATURE- Version: Mailvelope v1.1.0 Comment: https://www.mailvelope.com wsFcBAEBCAAQBQJWABG4CRDmVDuy+mK58QAAr+EQAMkjHrL88ByPx4pbmbPB 1ktYHq4sSkJ5AZGg4azlIl3lh5E8QVPOf6XcZ4z1jfgplBGw1XBcVeEoC+3S wuXnK15O4TIlvDRo7Mfe5CMXcUZzfWs/lv9UHk5iyIE9eO/pf8d5OALoUxI4 fCB4KZX/AxnCjoD0uO4RANqRzbOGDYTacwM0tNVMJ/oxeGrrAgiXDk0UvX1r hF3kch2U78HUEivt1tJr2YO32Db0FqzAJ3JLRwgnUcWD6/cvpZtECbZOANAY EAvNINAkv63btnGX76R9BwabguXMlfLYcnvEy+X2mFBmMdVv/IEEVzT+ovET /f2WEvGMLUFy6lriavrKG7O73vuzqhvSSKfPj+5VKLmNp2JvsDHqEswIMbNE WuS6JybbL/hrEZOfaIJ8hzU6PeyLpiHZwR468K0kR2R6wNY5ekkClR4IH7W0 jkitm/ues3oncAo3fIkSSIxE68cLiMZwSpwWVqRC2wRt9KjFFr/RTHAuIYn2 QV7ucdydwzkpqpBC3LMoDWjzG3XCRXKwwP6odOlfG6rN0Z8N1UC4bD8+O71h UmPo60nIDeJ0VGWeqtcttQgbusynk2NB4cPYR9ios9Da/ywAn0nH9PbB+nsw D3IgVrttO1qhyd/1RG/De9b4CS4zyYeqBmG6wk7Nop9Eee4b4ujSQBKnmtHA 1gXm =MuKM -END PGP SIGNATURE- ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Important security noticed regarding release signing key
-Message d'origine- De : ceph-users [mailto:ceph-users-boun...@lists.ceph.com] De la part de Wido den Hollander Envoyé : lundi 21 septembre 2015 15:50 À : ceph-users@lists.ceph.com Objet : Re: [ceph-users] Important security noticed regarding release signing key On 21-09-15 15:05, SCHAER Frederic wrote: > Hi, > > Forgive the question if the answer is obvious... It's been more than "an hour > or so" and eu.ceph.com apparently still hasn't been re-signed or at least > what I checked wasn't : > > # rpm -qp --qf '%{RSAHEADER:pgpsig}' > http://eu.ceph.com/rpm-hammer/el7/x86_64/ceph-0.94.3-0.el7.centos.x86_64.rpm > RSA/SHA1, Wed 26 Aug 2015 09:57:17 PM CEST, Key ID 7ebfdd5d17ed316d > > Should this repository/mirror be discarded and should we (in EU) switch to > download.ceph.com ? I fixed eu.ceph.com by putting a Varnish HTTP cache in between which now links to ceph.com You can still use eu.ceph.com and should be able to do so. eu.ceph.com caches all traffic so that should be much snappier then downloading everything from download.ceph.com directly. Wido [>- FS : -<] Many thanks for your quick reply and quick reaction ! Frederic ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] mds0: Client client008 failing to respond to capability release
On Mon, Sep 21, 2015 at 2:33 PM, Kenneth Waegeman wrote: > Hi all! > > A quick question: > We are syncing data over cephfs , and we are seeing messages in our output > like: > > mds0: Client client008 failing to respond to capability release > > What does this mean? I don't find information about this somewhere else. It means the MDS thinks that client is exhibiting a buggy behaviour in failing to respond to requests to release resources. > We are running ceph 9.0.3 > > On earlier versions, we often saw messages like 'failing to respond to cache > pressure', is this related? They're two different health checks that both indicate potential problems with the clients. What version of ceph-fuse or kernel client is in use? John ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Software Raid 1 for system disks on storage nodes (not for OSD disks)
-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 Ceph-disk (which ceph-deploy uses), uses GPT to partition OSDs so that they can be automatically started by udev and reference partitions for journals using unique identifiers. The necessary data to start the OSD, the auth key, fsid, etc, are stored on the OSD file system. This allows you to move OSD disks between nodes in a Ceph cluster. As long as you don't reformat the OSD drives (and any journals), then if you reimage the host, install Ceph, copy the ceph.conf and the OSD bootstrap keys, then it will act as if you have just moved the disks between servers. We have reformatted the OS of one of the nodes last week and the OSDs survived and rejoined the cluster after Puppet laid down the configuration. If you have journals on SSD and you try to move a spindle, then you have some more work to do. You either have to move the SSD as well (and any other spindles that have journals on it), or flush the journal and create a new one on the destination host. If you are using dm-crypt, you also need to save the encryption key as it is not on the OSD FS for obvious reasons. - Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 On Mon, Sep 21, 2015 at 3:18 AM, Vickey Singh wrote: > > > On Fri, Sep 18, 2015 at 6:33 PM, Robert LeBlanc > wrote: >> >> -BEGIN PGP SIGNED MESSAGE- >> Hash: SHA256 >> >> Depends on how easy it is to rebuild an OS from scratch. If you have >> something like Puppet or Chef that configure a node completely for >> you, it may not be too much of a pain to forgo the RAID. We run our >> OSD nodes from a single SATADOM and use Puppet for configuration. We >> also don't use swap (not very effective on SATADOM), but have enough >> RAM that we feel comfortable enough with that decision. >> >> If you use ceph-disk or ceph-deploy to configure the OSDs, then they >> should automatically come back up when you lay down the new OS and set >> up the necessary ceph config items (ceph.conf and the OSD bootstrap >> keys). > > > Hello sir > > This sounds really interesting , could you please elaborate how after > reinstalling OS and installing Ceph packages, how does Ceph detects OSD's > that were hosted earlier on this node. > > I am using ceph-deploy to provision ceph , now what all changes i need to do > after reinstalling OS of a OSD node. So that it should detect my OSD > daemons. Please help me to know this step by step. > > Thanks in advance. > > Vickey > > >> >> - >> Robert LeBlanc >> PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 >> >> >> On Fri, Sep 18, 2015 at 9:06 AM, Martin Palma wrote: >> > Hi, >> > >> > Is it a good idea to use a software raid for the system disk (Operating >> > System) on a Ceph storage node? I mean only for the OS not for the OSD >> > disks. >> > >> > And what about a swap partition? Is that needed? >> > >> > Best, >> > Martin >> > >> > ___ >> > ceph-users mailing list >> > ceph-users@lists.ceph.com >> > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> > >> >> -BEGIN PGP SIGNATURE- >> Version: Mailvelope v1.1.0 >> Comment: https://www.mailvelope.com >> >> wsFcBAEBCAAQBQJV/C7UCRDmVDuy+mK58QAAoTMQAMZBv4/lphmntC23b9/l >> JWUPjZfbXUtNgnfMvWcVyTSXsTtM5mY/4/iSZ4ZfCQ4YyqWWMpSlocHONHFz >> nFTtGupqV3vPCo4X8bl58/iv4J0H2iWUr2klk7jtTj+e+JjyWDo25l8V2ofP >> edt5g7qcMAwiWYrrpjxQBK4AFNiPJKSMxrzK1Mgic15nwX0OJu0DDNS5twzZ >> s8Y+UfS80+hZvyBTUGhsO8pkYoJQvYRGgyqYtCdxA+m1T8lWVe8SC0eLWOXy >> xoyGR7dqcvEXQadrqfmU618eNpNEECPoHeIkeCqpTohrUVsyRcfSGAtfM0YY >> Ixf2SCaDMAaRwvXGJUf5OP/3HHWps0m4YyLBOddPZ5XZb1utZiclh26KuOyw >> QdGkP7uoYEMO0v40dcsIbOVhtgTdX+HrpEGuqEtNEGe194sS1nluw+49aLxe >> eozHSRGq3GmRm/q3bR5f2p+WXwKqmdDRFhqII8H11bb5F7etU2PBo1JA2bTW >> hUFqu6+ST8eI34OeC7LbC9Txfw/iUhL62kiCm+gj8Rg+m+TZ7a1HEaVc8uyq >> Jw1+5hIgyTWFvKdIiW65k++8w9my6kUIsY8RT8p08DTSPzxuwGtHr7UJJ629 >> K/tlpGdQTRf7PXgmea6sSodnmaF5HRIUdU0nhQpRRxjX/V+PENI8Qq45KyfX >> BovV >> =Gzvl >> -END PGP SIGNATURE- >> ___ >> ceph-users mailing list >> ceph-users@lists.ceph.com >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > -BEGIN PGP SIGNATURE- Version: Mailvelope v1.1.0 Comment: https://www.mailvelope.com wsFcBAEBCAAQBQJWACdUCRDmVDuy+mK58QAAMFsP/3CdU8PvnbWYpT0uur5/ iUCEixJL3ChKY2RSODraR1FIUqFDannAzw/njafy21ZhzfY6YKtWfajE2qiC vNr1Y7bkZ711lhn8XRE4zYTBAzOZWkGEfE9DV2eYaEXB2ZbktJcJkEW8ykOG ynyDkKCkilROhyQTdiIUEx7IH12OJFUB3jjXIKdWtiMizZxDf/CnsXw6RwpY k9diX0FnZ0tcDprKc5GkT7ZNHLPNPHr39cG+0fwsmjA/bgzoh2GL4TytGON6 f6wqBR9Msb+qIGtSLd2AytJYhtwQoaMLAvmJc/uoplGbArU4yQwan5XIsMww jp5jK9z6uEBPHvMTOQjP8dp1eZoNE+PMrRssDsW28nLhr9TPohbOpjPyNVs7 /bpoEgZmmkKq3w8TWbkErS7O2ibNHSdKCjq0JISe0Qg5s58mcCLmiNj3OxC2 qogTDOVy9yP0VPKVdLa4XXNXYs5LMYHl6+3d6mtBWI01dVVIjO30Yc0mfvi4 pfuI1u5Fz8geIjcHcz/ruz51RgyEOeL2eEQsb0s/M7w6jPDhRQrZ42JS69Mg 0o48HXkxJRjy2kBd+h6sXd2wXgQwKTsse6Fy+cKU5xCuGYuT/RS6SxjKadqp E4Oswi
Re: [ceph-users] debian repositories path change?
On Sat, Sep 19, 2015 at 7:54 PM, Lindsay Mathieson wrote: > I'm getting: > > W: GPG error: http://download.ceph.com wheezy Release: The following > signatures couldn't be verified because the public key is not available: > NO_PUBKEY E84AC2C0460F3994 > > > Trying to update from there Hi Lindsay, did you add the new release key? As described at http://ceph.com/releases/important-security-notice-regarding-signing-key-and-binary-downloads-of-ceph/ sudo apt-key del 17ED316D curl https://git.ceph.com/release.asc | sudo apt-key add - sudo apt-get update - Ken ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] lttng duplicate registration problem when using librados2 and libradosstriper
This is usually indicative of the same tracepoint event being included by both a static and dynamic library. See the following thread regarding this issue within Ceph when LTTng-ust was first integrated [1]. Since I don't have any insight into your application, are you somehow linking against Ceph static libraries? [1] http://comments.gmane.org/gmane.comp.file-systems.ceph.devel/20353 - Original Message - > From: "Nick Fisk" > To: "Paul Mansfield" , > ceph-users@lists.ceph.com > Sent: Saturday, September 19, 2015 3:10:02 AM > Subject: Re: [ceph-users] lttng duplicate registration problem when using > librados2 and libradosstriper > > Hi Paul, > > I hit the same problem here (see last post): > > https://groups.google.com/forum/#!topic/bareos-users/mEzJ7IbDxvA > > If I ever get to the bottom of it, I will let you know. Sorry I can't be of > any more help. > > Nick > > > -Original Message- > > From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of > > Paul Mansfield > > Sent: 18 September 2015 17:16 > > To: ceph-users@lists.ceph.com > > Subject: [ceph-users] lttng duplicate registration problem when using > > librados2 and libradosstriper > > > > Hello, > > thanks for your attention. > > > > I have started using rados striper library, calling the functions from a C > > program. > > > > As soon as I add libradosstriper to the linking process, I get this error > when > > the program runs, even though I am not calling any functions from the > rados > > striper library (I commented them out). > > > > LTTng-UST: Error (-17) while registering tracepoint probe. Duplicate > > registration of tracepoint probes having the same name is not allowed. > > /bin/sh: line 1: 61001 Aborted (core dumped) ./$test > > > > > > I had been using lttng in my program but removed it to ensure it wasn't > > causing the problem. > > > > I have tried running the program using gdb but the calls to initialise > lttng occur > > before main() is called and so I cannot add a break point to see what is > > happening. > > > > > > thanks > > Paul > > ___ > > ceph-users mailing list > > ceph-users@lists.ceph.com > > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > > > ___ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] mds0: Client client008 failing to respond to capability release
On 21/09/15 16:32, John Spray wrote: On Mon, Sep 21, 2015 at 2:33 PM, Kenneth Waegeman wrote: Hi all! A quick question: We are syncing data over cephfs , and we are seeing messages in our output like: mds0: Client client008 failing to respond to capability release What does this mean? I don't find information about this somewhere else. It means the MDS thinks that client is exhibiting a buggy behaviour in failing to respond to requests to release resources. We are running ceph 9.0.3 On earlier versions, we often saw messages like 'failing to respond to cache pressure', is this related? They're two different health checks that both indicate potential problems with the clients. What version of ceph-fuse or kernel client is in use? ceph-fuse is used, also 9.0.3 John ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] Uneven data distribution across OSDs
Hi ceph users, I am using CephFS for file storage and I have noticed that the data gets distributed very unevenly across OSDs. * I have about 90 OSDs across 8 hosts, and 4096 PGs for the cephfs_data pool with 2 replicas, which is in line with the total PG recommendation if "Total PGs = (OSDs * 100) / pool_size" from the docs. * CephFS distributes the data pretty much evenly across the PGs as shown by 'ceph pg dump' * However - the number of PGs assigned to various OSDs (per weight unit/terabyte) varies quite a lot. The fullest OSD has as many as 44 PGs per terabyte (weight unit), while the emptier ones have as few as 19 or 20. * Even if I consider the total number of PGs for all pools per OSD, the number varies similarly wildly (as with the cephfs_data pool only). As a result, when the whole CephFS file system is at 60% full, some of the OSDs already reach the 95% full condition, and no more data can be written to the system. Is there any way to force a more even distribution of PGs to OSDs? I am using the default crush map, with two levels (root/host). Can any changes to the crush map help? I would really like to be get higher disk utilization than 60% without 1 of 90 disks filling up so early. Thanks, Andras ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Uneven data distribution across OSDs
Hello Andras, Some initial observations and questions: The total PG recommendation for this cluster would actually be 8192 PGs per the formula. Total PG's = (90 * 100) / 2 = 4500 Next power of 2 = 8192. The result should be rounded up to the nearest power of two. Rounding up is optional, but recommended for CRUSH to evenly balance the number of objects among placement groups. How many data pools are being used for storing objects? 'ceph osd dump |grep pool' Also how are these 90 OSD's laid out across the 8 hosts and is there any discrepancy between disk sizes and weight? 'ceph osd tree' Also what are you using for CRUSH tunables and what Ceph release? 'ceph osd crush show-tunables' 'ceph -v' Thanks, - Original Message - From: "Andras Pataki" To: ceph-users@lists.ceph.com Sent: Monday, September 21, 2015 2:00:29 PM Subject: [ceph-users] Uneven data distribution across OSDs Hi ceph users, I am using CephFS for file storage and I have noticed that the data gets distributed very unevenly across OSDs. * I have about 90 OSDs across 8 hosts, and 4096 PGs for the cephfs_data pool with 2 replicas, which is in line with the total PG recommendation if “Total PGs = (OSDs * 100) / pool_size” from the docs. * CephFS distributes the data pretty much evenly across the PGs as shown by ‘ceph pg dump’ * However – the number of PGs assigned to various OSDs (per weight unit/terabyte) varies quite a lot. The fullest OSD has as many as 44 PGs per terabyte (weight unit), while the emptier ones have as few as 19 or 20. * Even if I consider the total number of PGs for all pools per OSD, the number varies similarly wildly (as with the cephfs_data pool only). As a result, when the whole CephFS file system is at 60% full, some of the OSDs already reach the 95% full condition, and no more data can be written to the system. Is there any way to force a more even distribution of PGs to OSDs? I am using the default crush map, with two levels (root/host). Can any changes to the crush map help? I would really like to be get higher disk utilization than 60% without 1 of 90 disks filling up so early. Thanks, Andras ___ 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] Uneven data distribution across OSDs
Hi Michael, I could certainly double the total PG count, but and it probably will reduce the discrepancies somewhat, but I wonder if it would be all that different. I could of course be very wrong. ceph osd dump |grep pool output: pool 0 'rbd' replicated size 2 min_size 1 crush_ruleset 0 object_hash rjenkins pg_num 64 pgp_num 64 last_change 1 flags hashpspool stripe_width 0 pool 1 'data' replicated size 2 min_size 1 crush_ruleset 0 object_hash rjenkins pg_num 512 pgp_num 512 last_change 3347 flags hashpspool stripe_width 0 pool 2 'cephfs_data' replicated size 2 min_size 1 crush_ruleset 0 object_hash rjenkins pg_num 4096 pgp_num 4096 last_change 4288 flags hashpspool crash_replay_interval 45 stripe_width 0 pool 3 'cephfs_metadata' replicated size 2 min_size 1 crush_ruleset 0 object_hash rjenkins pg_num 512 pgp_num 512 last_change 3349 flags hashpspool stripe_width 0 Only pool 2 has significant amount of data in it (99.9% of the data is there) (from ceph df): POOLS: NAMEID USED %USED MAX AVAIL OBJECTS rbd 0 0 018234G0 data1 0 018234G0 cephfs_data 2 92083G 29.7018234G 24155210 cephfs_metadata 3 60839k 018234G36448 As for disk sizes, yes there are discrepancies, we have 1TB, 2TB and 6TB disks on various hosts (7 hosts not 8 as I said before). Two exceptions (osd.84 I reduced the weight because it filled up, osd.57 is a 5TB partition of a 6TB disk). All others are just the three disk sizes. The weights were set automatically accordingly at installation. The OSD tree: -1 295.55994 root default -6 21.84000 host scda002 0 0.90999 osd.0 up 1.0 1.0 10 0.90999 osd.10 up 1.0 1.0 11 0.90999 osd.11 up 1.0 1.0 12 0.90999 osd.12 up 1.0 1.0 13 0.90999 osd.13 up 1.0 1.0 14 0.90999 osd.14 up 1.0 1.0 15 0.90999 osd.15 up 1.0 1.0 16 0.90999 osd.16 up 1.0 1.0 32 1.81999 osd.32 up 1.0 1.0 33 1.81999 osd.33 up 1.0 1.0 34 1.81999 osd.34 up 1.0 1.0 35 1.81999 osd.35 up 1.0 1.0 36 1.81999 osd.36 up 1.0 1.0 37 1.81999 osd.37 up 1.0 1.0 38 1.81999 osd.38 up 1.0 1.0 39 1.81999 osd.39 up 1.0 1.0 -3 29.01999 host scda006 84 0.81000 osd.84 up 1.0 1.0 85 0.90999 osd.85 up 1.0 1.0 86 0.90999 osd.86 up 1.0 1.0 87 0.90999 osd.87 up 1.0 1.0 88 0.90999 osd.88 up 1.0 1.0 89 0.90999 osd.89 up 1.0 1.0 90 0.90999 osd.90 up 1.0 1.0 91 0.90999 osd.91 up 1.0 1.0 9 0.90999 osd.9 up 1.0 1.0 17 0.90999 osd.17 up 1.0 1.0 18 0.90999 osd.18 up 1.0 1.0 19 0.90999 osd.19 up 1.0 1.0 20 0.90999 osd.20 up 1.0 1.0 21 0.90999 osd.21 up 1.0 1.0 22 0.90999 osd.22 up 1.0 1.0 23 0.90999 osd.23 up 1.0 1.0 49 1.81999 osd.49 up 1.0 1.0 50 1.81999 osd.50 up 1.0 1.0 51 1.81999 osd.51 up 1.0 1.0 52 1.81999 osd.52 up 1.0 1.0 53 1.81999 osd.53 up 1.0 1.0 54 1.81999 osd.54 up 1.0 1.0 55 1.81999 osd.55 up 1.0 1.0 56 1.81999 osd.56 up 1.0 1.0 -2 70.98000 host scda005 79 5.45999 osd.79 up 1.0 1.0 80 5.45999 osd.80 up 1.0 1.0 81 5.45999 osd.81 up 1.0 1.0 82 5.45999 osd.82 up 1.0 1.0 83 5.45999 osd.83
[ceph-users] Client Local SSD Caching
Hi, I'm looking for recommended client local SSD caching startegy on OpenStack Compute where the backend storage is CEPH cluster. The target is for reducing Compute to Storage traffic. I have not known that librbd support local SSD caching. Beside, I'm not sure if block SSD caching of local mounted RBD volume (VM images/block as local files) will be good enough when more than one Compute access the same RBD volume. Any idea? Best regards, ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[ceph-users] CephFS Fuse Issue
I was rsyncing files to ceph from an older machine and I ran into a ceph-fuse crash. OpenSUSE 12.1, 3.1.10-1.29-desktop ceph-fuse 0.94.3 The rsync was running for about 48 hours then crashed somewhere along the way. I added the log, and can run more if you like, I am not sure how to reproduce it easily except run it again, which will take a while to see with any results. ceph.log.bz2 Description: application/bzip ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Receiving "failed to parse date for auth header"
Am 04.09.2015 um 11:42 schrieb Ramon Marco Navarro: Good day everyone! I'm having a problem using aws-java-sdk to connect to Ceph using radosgw. I am reading a " NOTICE: failed to parse date for auth header" message in the logs. HTTP_DATE is "Fri, 04 Sep 2015 09:25:33 +00:00", which is I think a valid rfc 1123 date... Here's a link to the related lines in the log file: https://gist.github.com/ramonmaruko/96e841167eda907f768b Thank you for any help in advance! ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com I had the same problem today. The date has to be rfc 822 (no colons) but the pattern ("EEE, dd MMM HH:mm:ss z") at com.amazonaws.util.DateUtils#L55 has a "z" which can give "GMT" but also "+00:00". I couldn't figure out yet why I always get "+00:00" with my recent project but not with others (same Java 8, same SDK version) ... I create a ticket and provided a fix: https://github.com/aws/aws-sdk-java/issues/514 because to my understanding it should always be GMT. Cheers, Jens ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] Potential OSD deadlock?
So it sounds like you've got two different things here: 1) You get a lot of slow operations that show up as warnings. 2) Rarely, you get blocked op warnings that don't seem to go away until the cluster state changes somehow. (2) is the interesting one. Since you say the cluster is under heavy load, I presume (1) is just you overloading your servers and getting some hot spots that take time to clear up. There have been bugs in the past where slow op warnings weren't getting removed when they should have. I don't *think* any are in .94.3 but could be wrong. Have you observed these from the other direction, where a client has blocked operations? If you want to go through the logs yourself, you should try and find all the lines about one of the operations which seems to be blocked. They aren't the most readable but if you grep for the operation ID (client.4267090.0:3510311) and then once you're in the right area look for what the threads processing it are doing you should get some idea of where things are going wrong you can share. -Greg On Sun, Sep 20, 2015 at 10:43 PM, Robert LeBlanc wrote: > We set the logging on an OSD that had problems pretty frequently, but > cleared up in less than 30 seconds. The logs are at > http://162.144.87.113/files/ceph-osd.112.log.xz and are uncompressed > at 8.6GB. Some of the messages we were seeing in ceph -w are: > > 2015-09-20 20:55:44.029041 osd.112 [WRN] 10 slow requests, 10 included > below; oldest blocked for > 30.132696 secs > 2015-09-20 20:55:44.029047 osd.112 [WRN] slow request 30.132696 > seconds old, received at 2015-09-20 20:55:13.896286: > osd_op(client.3289538.0:62497509 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 2588672~4096] 17.118f0c67 > ack+ondisk+write+known_if_redirected e57590) currently reached_pg > 2015-09-20 20:55:44.029051 osd.112 [WRN] slow request 30.132619 > seconds old, received at 2015-09-20 20:55:13.896363: > osd_op(client.3289538.0:62497510 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 2908160~12288] > 17.118f0c67 ack+ondisk+write+known_if_redirected e57590) currently > waiting for rw locks > 2015-09-20 20:55:44.029054 osd.112 [WRN] slow request 30.132520 > seconds old, received at 2015-09-20 20:55:13.896462: > osd_op(client.3289538.0:62497511 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 2949120~4096] 17.118f0c67 > ack+ondisk+write+known_if_redirected e57590) currently waiting for rw > locks > 2015-09-20 20:55:44.029058 osd.112 [WRN] slow request 30.132415 > seconds old, received at 2015-09-20 20:55:13.896567: > osd_op(client.3289538.0:62497512 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 2957312~4096] 17.118f0c67 > ack+ondisk+write+known_if_redirected e57590) currently waiting for rw > locks > 2015-09-20 20:55:44.029061 osd.112 [WRN] slow request 30.132302 > seconds old, received at 2015-09-20 20:55:13.896680: > osd_op(client.3289538.0:62497513 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 2998272~4096] 17.118f0c67 > ack+ondisk+write+known_if_redirected e57590) currently waiting for rw > locks > 2015-09-20 20:55:45.029290 osd.112 [WRN] 9 slow requests, 5 included > below; oldest blocked for > 31.132843 secs > 2015-09-20 20:55:45.029298 osd.112 [WRN] slow request 31.132447 > seconds old, received at 2015-09-20 20:55:13.896759: > osd_op(client.3289538.0:62497514 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 3035136~4096] 17.118f0c67 > ack+ondisk+write+known_if_redirected e57590) currently waiting for rw > locks > 2015-09-20 20:55:45.029303 osd.112 [WRN] slow request 31.132362 > seconds old, received at 2015-09-20 20:55:13.896845: > osd_op(client.3289538.0:62497515 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 3047424~4096] 17.118f0c67 > ack+ondisk+write+known_if_redirected e57590) currently waiting for rw > locks > 2015-09-20 20:55:45.029309 osd.112 [WRN] slow request 31.132276 > seconds old, received at 2015-09-20 20:55:13.896931: > osd_op(client.3289538.0:62497516 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 3072000~4096] 17.118f0c67 > ack+ondisk+write+known_if_redirected e57590) currently waiting for rw > locks > 2015-09-20 20:55:45.029315 osd.112 [WRN] slow request 31.132199 > seconds old, received at 2015-09-20 20:55:13.897008: > osd_op(client.3289538.0:62497517 > rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint > object_size 8388608 write_size 8388608,write 3211264~4096] 17.118f0c67 > ack+ondisk+write+known_if_redirected e57590) currently waiting for rw > locks > 2015-09-20 20:55:45.029326 osd.112 [WRN] sl
Re: [ceph-users] Potential OSD deadlock?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 In my lab cluster I can saturate the disks and I'm not seeing any of the blocked I/Os from the Ceph side, although the client shows that I/O stops for a while. I'm not convinced that it is load related. I was looking through the logs using the technique you described as well as looking for the associated PG. There is a lot of data to go through and it is taking me some time. We are rolling some of the backports for 0.94.4 into a build, one for the PG split problem, and 5 others that might help. One that I'm really hopeful about is http://tracker.ceph.com/issues/12843, but I'm not sure the messages we are seeing are exactly related. We are planning to roll the new binaries tomorrow night. I'll update this thread after the new code has been rolled. Thanks, -BEGIN PGP SIGNATURE- Version: Mailvelope v1.1.0 Comment: https://www.mailvelope.com wsFcBAEBCAAQBQJWAIE9CRDmVDuy+mK58QAAyS8P/21+0Y+QhsByqgu/bTiS 3dG6hNMyElXFyuWXievqqvyvaak7Y/nkVhC+oII1glujWFRRTL+61K4Qq8oo abFBtFVSRkkQpg0BCuHH0LsbXwyK7bmiSTZted2/XzZfJdcuQcDCVXZ0K3En LLWn0PvDj7OBnLexAAKAMF91a8gCnjuKq3AJnEYxQBeI/Fv58cpfERAiYa+W Fl6jBKPboJr8sgbQ87k6hu4aLuHGepliFJlUO3XPTvuD4WQ6Ak1HAD+KtmXd i8GYOZK9ukMQs8YavO8GqVAiZvUcuIGHVf502fP0v+7SR/s/9OY6Loo00/kK QdG0+mgV0o60AZ4r/setlsd7Uo3l9u4ra9n3D2RUtSJZRvcBK2HweeMiit4u FgA5dcx0lRFd6IluxZstgZlQiyxggIWHUgoQYFashtNWu/bl8bXn+gzK0GxO mWZqaeKBMauBWwLADIX1Q+VYBSvZWqFCfKGUawQ4bRnyz7zlHXQANlL1t7iF /QakoriydMW3l2WPftk4kDt4egFGhxxrCRZfA0TnVNx1DOLE9vRBKXKgTr0j miB0Ca9v9DQzVnTWhPCTfb8UdEHzozMTMEv30V3nskafPolsRJmjO04C1K7e 61R+cawG02J0RQqFMMNj3X2Gnbp/CC6JzUpQ5JPvNrvO34lcTYBWkdfwtolg 9ExB =hAcJ -END PGP SIGNATURE- Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 On Mon, Sep 21, 2015 at 4:00 PM, Gregory Farnum wrote: > So it sounds like you've got two different things here: > 1) You get a lot of slow operations that show up as warnings. > > 2) Rarely, you get blocked op warnings that don't seem to go away > until the cluster state changes somehow. > > (2) is the interesting one. Since you say the cluster is under heavy > load, I presume (1) is just you overloading your servers and getting > some hot spots that take time to clear up. > > There have been bugs in the past where slow op warnings weren't > getting removed when they should have. I don't *think* any are in > .94.3 but could be wrong. Have you observed these from the other > direction, where a client has blocked operations? > If you want to go through the logs yourself, you should try and find > all the lines about one of the operations which seems to be blocked. > They aren't the most readable but if you grep for the operation ID > (client.4267090.0:3510311) and then once you're in the right area look > for what the threads processing it are doing you should get some idea > of where things are going wrong you can share. > -Greg > > On Sun, Sep 20, 2015 at 10:43 PM, Robert LeBlanc wrote: >> We set the logging on an OSD that had problems pretty frequently, but >> cleared up in less than 30 seconds. The logs are at >> http://162.144.87.113/files/ceph-osd.112.log.xz and are uncompressed >> at 8.6GB. Some of the messages we were seeing in ceph -w are: >> >> 2015-09-20 20:55:44.029041 osd.112 [WRN] 10 slow requests, 10 included >> below; oldest blocked for > 30.132696 secs >> 2015-09-20 20:55:44.029047 osd.112 [WRN] slow request 30.132696 >> seconds old, received at 2015-09-20 20:55:13.896286: >> osd_op(client.3289538.0:62497509 >> rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint >> object_size 8388608 write_size 8388608,write 2588672~4096] 17.118f0c67 >> ack+ondisk+write+known_if_redirected e57590) currently reached_pg >> 2015-09-20 20:55:44.029051 osd.112 [WRN] slow request 30.132619 >> seconds old, received at 2015-09-20 20:55:13.896363: >> osd_op(client.3289538.0:62497510 >> rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint >> object_size 8388608 write_size 8388608,write 2908160~12288] >> 17.118f0c67 ack+ondisk+write+known_if_redirected e57590) currently >> waiting for rw locks >> 2015-09-20 20:55:44.029054 osd.112 [WRN] slow request 30.132520 >> seconds old, received at 2015-09-20 20:55:13.896462: >> osd_op(client.3289538.0:62497511 >> rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint >> object_size 8388608 write_size 8388608,write 2949120~4096] 17.118f0c67 >> ack+ondisk+write+known_if_redirected e57590) currently waiting for rw >> locks >> 2015-09-20 20:55:44.029058 osd.112 [WRN] slow request 30.132415 >> seconds old, received at 2015-09-20 20:55:13.896567: >> osd_op(client.3289538.0:62497512 >> rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint >> object_size 8388608 write_size 8388608,write 2957312~4096] 17.118f0c67 >> ack+ondisk+write+known_if_redirected e57590) currently waiting for rw >> locks >> 2015-09-20 20:55:44.029061 osd.112 [WRN] slow request 30.132302 >> seconds old, received at 2015-09-20 20:55
Re: [ceph-users] multi-datacenter crush map
On Mon, Sep 21, 2015 at 7:07 AM, Robert LeBlanc wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA256 > > > > > On Mon, Sep 21, 2015 at 3:02 AM, Wouter De Borger wrote: >> Thank you for your answer! We will use size=4 and min_size=2, which should >> do the trick. >> >> For the monitor issue, we have a third datacenter (with higher latency, but >> that shouldn't be a problem for the monitors) > > Just be sure that the IP address in the third DC is higher than the > other two. Ceph chooses the lowest IP address as the primary monitor. > Having the monitor with the highest latency as your primary is sure to > give you grief. > >> We had also considered the locality issue. Our WAN round trip latency is 1.5 >> ms (now) and we should get a dedicated light path in the near future (<0.1 >> ms). >> So we hope to get acceptable latency without additional tweaking. >> The plan B is to make two pools, with different weights for the different >> DC's. VM's in DC 1 will get high weight for DC 1, VM's in DC 2 will get high >> weight for DC 2. > > You don't want to mess with weights or else you will get stuck PGs > because there isn't enough storage at the remote DC to hold all your > data or the local DC fills up faster or CRUSH can't figure out how to > distribute balanced data in an unbalanced way. You will probably want > to look at primary affinity. This talks about SSD, but the same > principle applies > http://www.sebastien-han.fr/blog/2015/08/06/ceph-get-the-best-of-your-ssd-with-primary-affinity/ Keep in mind that primary affinity is per-OSD and applies to all pools. If you have separate pools for each DC, you can construct custom CRUSH rules for each one that always picks one or two OSDs out of the "local" DC and then one or two out of the secondary. Of course if you lose the primary DC you might want to edit the CRUSH rules — things should keep working but I'd expect the CRUSH calculations to start taking longer as it repeatedly tries and fails to get the OSDs out of the first list. ;) But if you can get a <.1ms link I wouldn't expect you to need to worry about it. -Greg > > - > Robert LeBlanc > PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 > -BEGIN PGP SIGNATURE- > Version: Mailvelope v1.1.0 > Comment: https://www.mailvelope.com > > wsFcBAEBCAAQBQJWAA80CRDmVDuy+mK58QAAK2UQAIadviUNo+hybghYO2de > 0Ayqy1SQ9hPjpwJUTWt0VKIgIoDMMbp1+LVd6EiPRNXPPwalDZen8z1ARW5F > o0g0nxMkJIJWxY2U3ch4s3oE85Hl5NqyPZIdaLfqQv7PXfFsRTM7rZDMRuLn > X9PWcxzZ3lvXj6WA/jiN42zXlhTlhLhtKV153poCtd/iCkytJUEPZF/c+Pr+ > /mIVVbbtzPDh5XC/Il/KEI1W+fZzPG27EL6N2YoskYWTEpUr0auBH7jTLm8B > kk4HKZToBsakP/j/LEhrh+MMW/ZNwuUaigWe351YQrkmlUBXxKVtnlgfJpDL > KIGvVDICRMwe6e3ubU7umsiFVchYPBlXFN3OoRmx3UfPp3WlfKong+PG9X8+ > JoukMyj630jmaDy7KPH5sKv+LUaLpWlWv6271bVUDlSMjPNHqVMlk/HsOGit > QYaWQQygQ+D/YedLP66xz+O6A8qfmrYfWBZZDdG9C49erw6Q6Ihzp6u+Hj1O > zt96JsmBjHcq27AfK1jSbZDGOHchL78/Ok3O4O01tC00HwRvQLy/ofppOzgn > KHnuLMs/9fZpSqh5sZ1BxWSgKBnYzc3npFloaOZLoVPT4Dv+hM8kL9lF0mHm > 3j1D4ZmysVaSU+zVw0WsWaNVQyrrPn+i9ivT6U/3VHiaS2Nz+BQTQeq0oMqQ > awOM > =sl/W > -END PGP SIGNATURE- > ___ > 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] Potential OSD deadlock?
On Mon, Sep 21, 2015 at 3:14 PM, Robert LeBlanc wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA256 > > In my lab cluster I can saturate the disks and I'm not seeing any of > the blocked I/Os from the Ceph side, although the client shows that > I/O stops for a while. I'm not convinced that it is load related. > > I was looking through the logs using the technique you described as > well as looking for the associated PG. There is a lot of data to go > through and it is taking me some time. > > We are rolling some of the backports for 0.94.4 into a build, one for > the PG split problem, and 5 others that might help. One that I'm > really hopeful about is http://tracker.ceph.com/issues/12843, but I'm > not sure the messages we are seeing are exactly related. We are > planning to roll the new binaries tomorrow night. I'll update this > thread after the new code has been rolled. Ah, yep, I didn't realize we still had any of those in hammer. That bug is indeed a good bet for what you're seeing. -Greg > > Thanks, > -BEGIN PGP SIGNATURE- > Version: Mailvelope v1.1.0 > Comment: https://www.mailvelope.com > > wsFcBAEBCAAQBQJWAIE9CRDmVDuy+mK58QAAyS8P/21+0Y+QhsByqgu/bTiS > 3dG6hNMyElXFyuWXievqqvyvaak7Y/nkVhC+oII1glujWFRRTL+61K4Qq8oo > abFBtFVSRkkQpg0BCuHH0LsbXwyK7bmiSTZted2/XzZfJdcuQcDCVXZ0K3En > LLWn0PvDj7OBnLexAAKAMF91a8gCnjuKq3AJnEYxQBeI/Fv58cpfERAiYa+W > Fl6jBKPboJr8sgbQ87k6hu4aLuHGepliFJlUO3XPTvuD4WQ6Ak1HAD+KtmXd > i8GYOZK9ukMQs8YavO8GqVAiZvUcuIGHVf502fP0v+7SR/s/9OY6Loo00/kK > QdG0+mgV0o60AZ4r/setlsd7Uo3l9u4ra9n3D2RUtSJZRvcBK2HweeMiit4u > FgA5dcx0lRFd6IluxZstgZlQiyxggIWHUgoQYFashtNWu/bl8bXn+gzK0GxO > mWZqaeKBMauBWwLADIX1Q+VYBSvZWqFCfKGUawQ4bRnyz7zlHXQANlL1t7iF > /QakoriydMW3l2WPftk4kDt4egFGhxxrCRZfA0TnVNx1DOLE9vRBKXKgTr0j > miB0Ca9v9DQzVnTWhPCTfb8UdEHzozMTMEv30V3nskafPolsRJmjO04C1K7e > 61R+cawG02J0RQqFMMNj3X2Gnbp/CC6JzUpQ5JPvNrvO34lcTYBWkdfwtolg > 9ExB > =hAcJ > -END PGP SIGNATURE- > > Robert LeBlanc > PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 > > > On Mon, Sep 21, 2015 at 4:00 PM, Gregory Farnum wrote: >> So it sounds like you've got two different things here: >> 1) You get a lot of slow operations that show up as warnings. >> >> 2) Rarely, you get blocked op warnings that don't seem to go away >> until the cluster state changes somehow. >> >> (2) is the interesting one. Since you say the cluster is under heavy >> load, I presume (1) is just you overloading your servers and getting >> some hot spots that take time to clear up. >> >> There have been bugs in the past where slow op warnings weren't >> getting removed when they should have. I don't *think* any are in >> .94.3 but could be wrong. Have you observed these from the other >> direction, where a client has blocked operations? >> If you want to go through the logs yourself, you should try and find >> all the lines about one of the operations which seems to be blocked. >> They aren't the most readable but if you grep for the operation ID >> (client.4267090.0:3510311) and then once you're in the right area look >> for what the threads processing it are doing you should get some idea >> of where things are going wrong you can share. >> -Greg >> >> On Sun, Sep 20, 2015 at 10:43 PM, Robert LeBlanc >> wrote: >>> We set the logging on an OSD that had problems pretty frequently, but >>> cleared up in less than 30 seconds. The logs are at >>> http://162.144.87.113/files/ceph-osd.112.log.xz and are uncompressed >>> at 8.6GB. Some of the messages we were seeing in ceph -w are: >>> >>> 2015-09-20 20:55:44.029041 osd.112 [WRN] 10 slow requests, 10 included >>> below; oldest blocked for > 30.132696 secs >>> 2015-09-20 20:55:44.029047 osd.112 [WRN] slow request 30.132696 >>> seconds old, received at 2015-09-20 20:55:13.896286: >>> osd_op(client.3289538.0:62497509 >>> rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint >>> object_size 8388608 write_size 8388608,write 2588672~4096] 17.118f0c67 >>> ack+ondisk+write+known_if_redirected e57590) currently reached_pg >>> 2015-09-20 20:55:44.029051 osd.112 [WRN] slow request 30.132619 >>> seconds old, received at 2015-09-20 20:55:13.896363: >>> osd_op(client.3289538.0:62497510 >>> rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint >>> object_size 8388608 write_size 8388608,write 2908160~12288] >>> 17.118f0c67 ack+ondisk+write+known_if_redirected e57590) currently >>> waiting for rw locks >>> 2015-09-20 20:55:44.029054 osd.112 [WRN] slow request 30.132520 >>> seconds old, received at 2015-09-20 20:55:13.896462: >>> osd_op(client.3289538.0:62497511 >>> rbd_data.29b9ae3f960770.0200 [stat,set-alloc-hint >>> object_size 8388608 write_size 8388608,write 2949120~4096] 17.118f0c67 >>> ack+ondisk+write+known_if_redirected e57590) currently waiting for rw >>> locks >>> 2015-09-20 20:55:44.029058 osd.112 [WRN] slow request 30.132415 >>> seconds old, received at 2015-09-20 20:55:13.896567: >>> osd_op(client.3289538.0:62497512 >>> rbd_data.
Re: [ceph-users] CephFS Fuse Issue
Do you have a core file from the crash? If you do and can find out which pointers are invalid that would help...I think "cct" must be the broken one, but maybe it's just the Inode* or something. -Greg On Mon, Sep 21, 2015 at 2:03 PM, Scottix wrote: > I was rsyncing files to ceph from an older machine and I ran into a > ceph-fuse crash. > > OpenSUSE 12.1, 3.1.10-1.29-desktop > ceph-fuse 0.94.3 > > The rsync was running for about 48 hours then crashed somewhere along the > way. > > I added the log, and can run more if you like, I am not sure how to > reproduce it easily except run it again, which will take a while to see with > any results. > > ___ > 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] debian repositories path change?
On 19/09/15 03:28, Sage Weil wrote: > On Fri, 18 Sep 2015, Alfredo Deza wrote: >> The new locations are in: >> >> >> http://packages.ceph.com/ >> >> For debian this would be: >> >> http://packages.ceph.com/debian-{release} > > Make that download.ceph.com .. the packages url was temporary while we got > the new site ready and will go away shortly! > > (Also, HTTPS is enabled now.) Prior to the repository reshuffle eu.ceph.com supported rsync, which was a convenient way of us to maintain our own local (in New Zealand) mirror. Is there an intention to re-enable this on either download.ceph.com, or the EU equivalent? -- David Clarke signature.asc Description: OpenPGP digital signature ___ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
Re: [ceph-users] CephFS Fuse Issue
I didn't get the core dump. I set it up now and I'll try to see if I can get it to crash again. On Mon, Sep 21, 2015 at 3:40 PM Gregory Farnum wrote: > Do you have a core file from the crash? If you do and can find out > which pointers are invalid that would help...I think "cct" must be the > broken one, but maybe it's just the Inode* or something. > -Greg > > On Mon, Sep 21, 2015 at 2:03 PM, Scottix wrote: > > I was rsyncing files to ceph from an older machine and I ran into a > > ceph-fuse crash. > > > > OpenSUSE 12.1, 3.1.10-1.29-desktop > > ceph-fuse 0.94.3 > > > > The rsync was running for about 48 hours then crashed somewhere along the > > way. > > > > I added the log, and can run more if you like, I am not sure how to > > reproduce it easily except run it again, which will take a while to see > with > > any results. > > > > ___ > > 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] Potential OSD deadlock?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 I'm starting to wonder if this has to do with some OSDs getting full or the 0.94.3 code. Earlier this afternoon, I cleared out my test cluster so there was no pools. I created anew rbd pool and started filling it with 6 - 1TB fio jobs replication 3 with 6 spindles over six servers. It was running 0.94.2 at the time. After several hours of writes, we had the new patched 0.93.3 binaries ready for testing so I rolled the update on the test cluster while the fio jobs were running. There were a few blocked I/O as the services were restarted (nothing I'm concerned about). Now that the OSDs are about 60% full, the blocked I/O is becoming very frequent even with the backports. The write bandwidth was consistently at 200 MB/s until this point, now it is fluctuating between 200 MB/s and 75 MB/s mostly around about 100MB/s. Our production cluster is XFS on the OSDs, this test cluster is EXT4. I'll see if I can go back to 0.94.2 and fill the cluster up again Going back to 0.94.2 and 0.94.0 still has the issue (although I didn't refill the cluster, I didn't delete what was already there). I'm building the latest of hammer-backports now and see if it resolves the issue. -BEGIN PGP SIGNATURE- Version: Mailvelope v1.1.0 Comment: https://www.mailvelope.com wsFcBAEBCAAQBQJWAPioCRDmVDuy+mK58QAAOIwP/3D86CWYlgozKBNlsuIv AT30S7ZrqDZmxygaJQ9PZgSyQlgQuXpDLL4CnVtbUNd+dgz91i7CVecVGj3h /jrFwrH063yPD1r3nMmSdc2GTTIahH1JhvzpWqcP9pkmuGHoYlWqteYnosfn ptOjJI57AFw/goxcJLUExLfdp+L/3GkHNoMMKtJXZX7OIEWdkMj1f9jBGEK6 tJ3AGbbpL6eZGB/KFDObHwCEjfwouTkRk0wNh0luDAU9QlBokmcKS134Ht2C kRtggOMlXxOKaQiXKZHZL7TUEgvlwldpS01rgDLnNOn3AHZMiAoaC2noFDDS 48ZnbkJgdqpMX2nMFcbwh4zdWOmRRcFqNXuA/t4m0UrZwRCWlSwcVPxDqbHr 00kjDMFtlbov1NWfDXfcMF32qSdsfVaDAwjCmMct1IEn3EXYKYeYA8GUePia +A9FvUezeYSELWxk59Hirk69A39wNsA40lrMbFzIOkp8CLLuKiHSKs8dTFtJ CaIPMwZDElcKJDKXPEMu260/GIcJmERUZXPayIQp2Attgx3/gvDpU3crWN7C 49dqnPOVqm6+f+ciUBVwIgQ7Xbbqom+yc1jxlvmpMW1C5iu9vjH/mvO42N/c e+R0/SgCJnDQU4tYppYadA8vKA/e9JyjMfBlbTW0urxHQlkNqohFY9G+edLW Zkxf =kYQ2 -END PGP SIGNATURE- Robert LeBlanc PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 On Mon, Sep 21, 2015 at 4:33 PM, Gregory Farnum wrote: > On Mon, Sep 21, 2015 at 3:14 PM, Robert LeBlanc wrote: >> -BEGIN PGP SIGNED MESSAGE- >> Hash: SHA256 >> >> In my lab cluster I can saturate the disks and I'm not seeing any of >> the blocked I/Os from the Ceph side, although the client shows that >> I/O stops for a while. I'm not convinced that it is load related. >> >> I was looking through the logs using the technique you described as >> well as looking for the associated PG. There is a lot of data to go >> through and it is taking me some time. >> >> We are rolling some of the backports for 0.94.4 into a build, one for >> the PG split problem, and 5 others that might help. One that I'm >> really hopeful about is http://tracker.ceph.com/issues/12843, but I'm >> not sure the messages we are seeing are exactly related. We are >> planning to roll the new binaries tomorrow night. I'll update this >> thread after the new code has been rolled. > > Ah, yep, I didn't realize we still had any of those in hammer. That > bug is indeed a good bet for what you're seeing. > -Greg > >> >> Thanks, >> -BEGIN PGP SIGNATURE- >> Version: Mailvelope v1.1.0 >> Comment: https://www.mailvelope.com >> >> wsFcBAEBCAAQBQJWAIE9CRDmVDuy+mK58QAAyS8P/21+0Y+QhsByqgu/bTiS >> 3dG6hNMyElXFyuWXievqqvyvaak7Y/nkVhC+oII1glujWFRRTL+61K4Qq8oo >> abFBtFVSRkkQpg0BCuHH0LsbXwyK7bmiSTZted2/XzZfJdcuQcDCVXZ0K3En >> LLWn0PvDj7OBnLexAAKAMF91a8gCnjuKq3AJnEYxQBeI/Fv58cpfERAiYa+W >> Fl6jBKPboJr8sgbQ87k6hu4aLuHGepliFJlUO3XPTvuD4WQ6Ak1HAD+KtmXd >> i8GYOZK9ukMQs8YavO8GqVAiZvUcuIGHVf502fP0v+7SR/s/9OY6Loo00/kK >> QdG0+mgV0o60AZ4r/setlsd7Uo3l9u4ra9n3D2RUtSJZRvcBK2HweeMiit4u >> FgA5dcx0lRFd6IluxZstgZlQiyxggIWHUgoQYFashtNWu/bl8bXn+gzK0GxO >> mWZqaeKBMauBWwLADIX1Q+VYBSvZWqFCfKGUawQ4bRnyz7zlHXQANlL1t7iF >> /QakoriydMW3l2WPftk4kDt4egFGhxxrCRZfA0TnVNx1DOLE9vRBKXKgTr0j >> miB0Ca9v9DQzVnTWhPCTfb8UdEHzozMTMEv30V3nskafPolsRJmjO04C1K7e >> 61R+cawG02J0RQqFMMNj3X2Gnbp/CC6JzUpQ5JPvNrvO34lcTYBWkdfwtolg >> 9ExB >> =hAcJ >> -END PGP SIGNATURE- >> >> Robert LeBlanc >> PGP Fingerprint 79A2 9CA4 6CC4 45DD A904 C70E E654 3BB2 FA62 B9F1 >> >> >> On Mon, Sep 21, 2015 at 4:00 PM, Gregory Farnum wrote: >>> So it sounds like you've got two different things here: >>> 1) You get a lot of slow operations that show up as warnings. >>> >>> 2) Rarely, you get blocked op warnings that don't seem to go away >>> until the cluster state changes somehow. >>> >>> (2) is the interesting one. Since you say the cluster is under heavy >>> load, I presume (1) is just you overloading your servers and getting >>> some hot spots that take time to clear up. >>> >>> There have been bugs in the past where slow op warnings weren't >>> getting removed when they should have. I don't *think* any are in >>> .94.3