January 2020 - ceph-users

MDS rejects clients causing hanging mountpoint on linux kernel client

by Florian Pritz

Hi, We are running a ceph cluster on Ubuntu 18.04 machines with ceph 14.2.4. Our cephfs clients are using the kernel module and we have noticed that some of them are sometimes (at least once) hanging after an MDS restart. The only way to resolve this is to unmount and remount the mountpoint, or reboot the machine if unmounting is not possible. After some investigation, the problem seems to be that the MDS denies reconnect attempts from some clients during restart even though the reconnect interval is not yet reached. In particular, I see the following log entries. Note that there are supposedly 9 sessions. 9 clients reconnect (one client has two mountpoints) and then two more clients reconnect after the MDS already logged "reconnect_done". These two clients were hanging after the event. The kernel log of one of them is shown below too. Running `ceph tell mds.0 client ls` after the clients have been rebooted/remounted also shows 11 clients instead of 9. Do you have any ideas what is wrong here and how it could be fixed? I'm guessing that the issue is that the MDS apparently has an incorrect session count and stops the reconnect process to soon. Is this indeed a bug and if so, do you know what is broken? Regardless, I also think that the kernel should be able to deal with a denied reconnect and that it should try again later. Yet, even after 10 minutes, the kernel does not attempt to reconnect. Is this a known issue or maybe fixed in newer kernels? If not, is there a chance to get this fixed? Thanks, Florian MDS log: > 2019-09-26 16:08:27.479 7f9fdde99700 1 mds.0.server reconnect_clients -- 9 sessions > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.24197043 v1:10.1.4.203:0/990008521 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.30487144 v1:10.1.4.146:0/483747473 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.21019865 v1:10.1.7.22:0/3752632657 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.21020717 v1:10.1.7.115:0/2841046616 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.24171153 v1:10.1.7.243:0/1127767158 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.23978093 v1:10.1.4.71:0/824226283 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.24209569 v1:10.1.4.157:0/1271865906 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.20190930 v1:10.1.4.240:0/3195698606 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 0 log_channel(cluster) log [DBG] : reconnect by client.20190912 v1:10.1.4.146:0/852604154 after 0 > 2019-09-26 16:08:27.479 7f9fdde99700 1 mds.0.59 reconnect_done > 2019-09-26 16:08:27.483 7f9fdde99700 1 mds.0.server no longer in reconnect state, ignoring reconnect, sending close > 2019-09-26 16:08:27.483 7f9fdde99700 0 log_channel(cluster) log [INF] : denied reconnect attempt (mds is up:reconnect) from client.24167394 v1:10.1.67.49:0/1483641729 after 0.00400002 (allowed interval 45) > 2019-09-26 16:08:27.483 7f9fe1087700 0 --1- [v2:10.1.4.203:6800/806949107,v1:10.1.4.203:6801/806949107] >> v1:10.1.67.49:0/1483641729 conn(0x55af50053f80 0x55af50140800 :6801 s=OPENED pgs=21 cs=1 l=0).fault server, going to standby > 2019-09-26 16:08:27.483 7f9fdde99700 1 mds.0.server no longer in reconnect state, ignoring reconnect, sending close > 2019-09-26 16:08:27.483 7f9fdde99700 0 log_channel(cluster) log [INF] : denied reconnect attempt (mds is up:reconnect) from client.30586072 v1:10.1.67.140:0/3664284158 after 0.00400002 (allowed interval 45) > 2019-09-26 16:08:27.483 7f9fe1888700 0 --1- [v2:10.1.4.203:6800/806949107,v1:10.1.4.203:6801/806949107] >> v1:10.1.67.140:0/3664284158 conn(0x55af50055600 0x55af50143000 :6801 s=OPENED pgs=8 cs=1 l=0).fault server, going to standby Hanging client (10.1.67.49) kernel log: > 2019-09-26T16:08:27.481676+02:00 hostnamefoo kernel: [708596.227148] ceph: mds0 reconnect start > 2019-09-26T16:08:27.488943+02:00 hostnamefoo kernel: [708596.233145] ceph: mds0 reconnect denied > 2019-09-26T16:16:17.541041+02:00 hostnamefoo kernel: [709066.287601] libceph: mds0 10.1.4.203:6801 socket closed (con state NEGOTIATING) > 2019-09-26T16:16:18.068934+02:00 hostnamefoo kernel: [709066.813064] ceph: mds0 rejected session > 2019-09-26T16:16:18.068955+02:00 hostnamefoo kernel: [709066.814843] ceph: get_quota_realm: ino (10000000008.fffffffffffffffe) null i_snap_realm

1 year, 12 months

3
6
0 0

Provide more documentation for MDS performance tuning on large file systems

by Janek Bevendorff

Hello, Over the last week I have tried optimising the performance of our MDS nodes for the large amount of files and concurrent clients we have. It turns out that despite various stability fixes in recent releases, the default configuration still doesn't appear to be optimal for keeping the cache size under control and avoid intermittent I/O blocks. Unfortunately, it is very hard to tweak the configuration to something that works, because the tuning parameters needed are largely undocumented or only described in very technical terms in the source code making them quite unapproachable for administrators not familiar with all the CephFS internals. I would therefore like to ask if it were possible to document the "advanced" MDS settings more clearly as to what they do and in what direction they have to be tuned for more or less aggressive cap recall, for instance (sometimes it is not clear if a threshold is a min or a max threshold). I am am in the very (un)fortunate situation to have folders with a several 100K direct sub folders or files (and one extreme case with almost 7 million dentries), which is a pretty good benchmark for measuring cap growth while performing operations on them. For the time being, I came up with this configuration, which seems to work for me, but is still far from optimal: mds basic mds_cache_memory_limit 10737418240 mds advanced mds_cache_trim_threshold 131072 mds advanced mds_max_caps_per_client 500000 mds advanced mds_recall_max_caps 17408 mds advanced mds_recall_max_decay_rate 2.000000 The parameters I am least sure about---because I understand the least how they actually work---are mds_cache_trim_threshold and mds_recall_max_decay_rate. Despite reading the description in src/common/options.cc, I understand only half of what they're doing and I am also not quite sure in which direction to tune them for optimal results. Another point where I am struggling is the correct configuration of mds_recall_max_caps. The default of 5K doesn't work too well for me, but values above 20K also don't seem to be a good choice. While high values result in fewer blocked ops and better performance without destabilising the MDS, they also lead to slow but unbounded cache growth, which seems counter-intuitive. 17K was the maximum I could go. Higher values work for most use cases, but when listing very large folders with millions of dentries, the MDS cache size slowly starts to exceed the limit after a few hours, since the MDSs are failing to keep clients below mds_max_caps_per_client despite not showing any "failing to respond to cache pressure" warnings. With the configuration above, I do not have cache size issues any more, but it comes at the cost of performance and slow/blocked ops. A few hints as to how I could optimise my settings for better client performance would be much appreciated and so would be additional documentation for all the "advanced" MDS settings. Thanks a lot Janek

2 years, 1 month

3
13
0 0

atime with cephfs

by Oliver Freyermuth

Dear Cephers, we are currently mounting CephFS with relatime, using the FUSE client (version 13.2.6): ceph-fuse on /cephfs type fuse.ceph-fuse (rw,relatime,user_id=0,group_id=0,allow_other) For the first time, I wanted to use atime to identify old unused data. My expectation with "relatime" was that the access time stamp would be updated less often, for example, only if the last file access was >24 hours ago. However, that does not seem to be the case: ---------------------------------------------- $ stat /cephfs/grid/atlas/atlaslocalgroupdisk/rucio/group/phys-higgs/ed/cb/group.phys-higgs.17620861._000004.HSM_common.root ... Access: 2019-04-10 15:50:04.975959159 +0200 Modify: 2019-04-10 15:50:05.651613843 +0200 Change: 2019-04-10 15:50:06.141006962 +0200 ... $ cat /cephfs/grid/atlas/atlaslocalgroupdisk/rucio/group/phys-higgs/ed/cb/group.phys-higgs.17620861._000004.HSM_common.root > /dev/null $ sync $ stat /cephfs/grid/atlas/atlaslocalgroupdisk/rucio/group/phys-higgs/ed/cb/group.phys-higgs.17620861._000004.HSM_common.root ... Access: 2019-04-10 15:50:04.975959159 +0200 Modify: 2019-04-10 15:50:05.651613843 +0200 Change: 2019-04-10 15:50:06.141006962 +0200 ... ---------------------------------------------- I also tried this via an nfs-ganesha mount, and via a ceph-fuse mount with admin caps, but atime never changes. Is atime really never updated with CephFS, or is this configurable? Something as coarse as "update at maximum once per day only" would be perfectly fine for the use case. Cheers, Oliver

2 years, 2 months

4
6
0 0

Choosing suitable SSD for Ceph cluster

by Hermann Himmelbauer

Hi, I am running a nice ceph (proxmox 4 / debian-8 / ceph 0.94.3) cluster on 3 nodes (supermicro X8DTT-HIBQF), 2 OSD each (2TB SATA harddisks), interconnected via Infiniband 40. Problem is that the ceph performance is quite bad (approx. 30MiB/s reading, 3-4 MiB/s writing ), so I thought about plugging into each node a PCIe to NVMe/M.2 adapter and install SSD harddisks. The idea is to have a faster ceph storage and also some storage extension. The question is now which SSDs I should use. If I understand it right, not every SSD is suitable for ceph, as is denoted at the links below: https://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test-if-your-ssd-i… or here: https://www.proxmox.com/en/downloads/item/proxmox-ve-ceph-benchmark In the first link, the Samsung SSD 950 PRO 512GB NVMe is listed as a fast SSD for ceph. As the 950 is not available anymore, I ordered a Samsung 970 1TB for testing, unfortunately, the "EVO" instead of PRO. Before equipping all nodes with these SSDs, I did some tests with "fio" as recommended, e.g. like this: fio --filename=/dev/DEVICE --direct=1 --sync=1 --rw=write --bs=4k --numjobs=1 --iodepth=1 --runtime=60 --time_based --group_reporting --name=journal-test The results are as the following: ----------------------- 1) Samsung 970 EVO NVMe M.2 mit PCIe Adapter Jobs: 1: read : io=26706MB, bw=445MiB/s, iops=113945, runt= 60001msec write: io=252576KB, bw=4.1MiB/s, iops=1052, runt= 60001msec Jobs: 4: read : io=21805MB, bw=432.7MiB/s, iops=93034, runt= 60001msec write: io=422204KB, bw=6.8MiB/s, iops=1759, runt= 60002msec Jobs: 10: read : io=26921MB, bw=448MiB/s, iops=114859, runt= 60001msec write: io=435644KB, bw=7MiB/s, iops=1815, runt= 60004msec ----------------------- So the read speed is impressive, but the write speed is really bad. Therefore I ordered the Samsung 970 PRO (1TB) as it has faster NAND chips (MLC instead of TLC). The results are, however even worse for writing: ----------------------- Samsung 970 PRO NVMe M.2 mit PCIe Adapter Jobs: 1: read : io=15570MB, bw=259.4MiB/s, iops=66430, runt= 60001msec write: io=199436KB, bw=3.2MiB/s, iops=830, runt= 60001msec Jobs: 4: read : io=48982MB, bw=816.3MiB/s, iops=208986, runt= 60001msec write: io=327800KB, bw=5.3MiB/s, iops=1365, runt= 60002msec Jobs: 10: read : io=91753MB, bw=1529.3MiB/s, iops=391474, runt= 60001msec write: io=343368KB, bw=5.6MiB/s, iops=1430, runt= 60005msec ----------------------- I did some research and found out, that the "--sync" flag sets the flag "O_DSYNC" which seems to disable the SSD cache which leads to these horrid write speeds. It seems that this relates to the fact that the write cache is only not disabled for SSDs which implement some kind of battery buffer that guarantees a data flush to the flash in case of a powerloss. However, It seems impossible to find out which SSDs do have this powerloss protection, moreover, these enterprise SSDs are crazy expensive compared to the SSDs above - moreover it's unclear if powerloss protection is even available in the NVMe form factor. So building a 1 or 2 TB cluster seems not really affordable/viable. So, can please anyone give me hints what to do? Is it possible to ensure that the write cache is not disabled in some way (my server is situated in a data center, so there will probably never be loss of power). Or is the link above already outdated as newer ceph releases somehow deal with this problem? Or maybe a later Debian release (10) will handle the O_DSYNC flag differently? Perhaps I should simply invest in faster (and bigger) harddisks and forget the SSD-cluster idea? Thank you in advance for any help, Best Regards, Hermann -- hermann(a)qwer.tk PGP/GPG: 299893C7 (on keyservers)

2 years, 4 months

12
18
0 0

add debian buster stable support for ceph-deploy

by Jelle de Jong

Hello everybody, Can somebody add support for Debian buster and ceph-deploy: https://tracker.ceph.com/issues/42870 Highly appreciated, Regards, Jelle de Jong

2 years, 5 months

6
8
0 0

bluestore_default_buffered_write = true

by Adam Koczarski

Has anyone ever tried using this feature? I've added it to the [global] section of the ceph.conf on my POC cluster but I'm not sure how to tell if it's actually working. I did find a reference to this feature via Google and they had it in their [OSD] section?? I've tried that too.. TIA Adam

2 years, 6 months

2
1
0 0

RBD logs

by 陈旭

Hi guys, I deploy an efk cluster and use ceph as block storage in kubernetes, but RBD write iops sometimes becomes zero and last for a few minutes. I want to check logs about RBD so I add some config to ceph.conf and restart ceph. Here is my ceph.conf: [global] fsid = 53f4e1d5-32ce-4e9c-bf36-f6b54b009962 mon_initial_members = db-16-4-hzxs, db-16-5-hzxs, db-16-6-hzxs mon_host = 10.25.16.4,10.25.16.5,10.25.16.6 auth_cluster_required = cephx auth_service_required = cephx auth_client_required = cephx osd pool default size = 3 [client] debug rbd = 20 debug rbd mirror = 20 debug rbd replay = 20 log file = /var/log/ceph/client_rbd.log I can not get any logs in /var/log/ceph/client_rbd.log. I also try to execute 'ceph daemon osd.* config set debug_rbd 20’ and there is also no related logs in ceph-osd.log. How can I get useful logs about this question or How can I analyze this problem? Look forward to your reply. Thanks ////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////// 声明：此邮件可能包含依图公司保密或特权信息，并且仅应发送至有权接收该邮件的收件人。如果您无权收取该邮件，您应当立即删除该邮件并通知发件人，您并被禁止传播、分发或复制此邮件以及附件。对于此邮件可能携带的病毒引起的任何损害，本公司不承担任何责任。此外，本公司不保证已正确和完整地传输此信息，也不接受任何延迟收件的赔偿责任。 ////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////// Notice: This email may contain confidential or privileged information of Yitu and was sent solely to the intended recipients. If you are unauthorized to receive this email, you should delete the email and contact the sender immediately. Any unauthorized disclosing, distribution, or copying of this email and attachment thereto is prohibited. Yitu does not accept any liability for any loss caused by possibly viruses in this email. E-mail transmission cannot be guaranteed to be secure or error-free and Yitu is not responsible for any delayed transmission.

2 years, 8 months

2
1
0 0

Help! ceph-mon is blocked after shutting down and ip address changed

by occj＠qq.com

ceph version 14.2.4 (75f4de193b3ea58512f204623e6c5a16e6c1e1ba) nautilus (stable) os :CentOS Linux release 7.7.1908 (Core) single node ceph cluster with 1 mon,1mgr,1 mds,1rgw and 12osds , but only cephfs is used. ceph -s is blocked after shutting down the machine (192.168.0.104), then ip address changed to 192.168.1.6 I created the monmap with monmap tool and update the ceph.conf , hosts file and then start ceph-mon. and the ceph-mon log: ... 2019-12-11 08:57:45.170 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1285.14s 2019-12-11 08:57:50.170 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1290.14s 2019-12-11 08:57:55.171 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1295.14s 2019-12-11 08:58:00.171 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1300.14s 2019-12-11 08:58:05.172 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1305.14s 2019-12-11 08:58:10.171 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1310.14s 2019-12-11 08:58:15.173 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1315.14s 2019-12-11 08:58:20.173 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1320.14s 2019-12-11 08:58:25.174 7f952cdac700 1 mon.ceph-node1 at 0(leader).mds e34 no beacon from mds.0.10 (gid: 4384 addr: [v2:192.168.0.104:6898/4084823750,v1:192.168.0.104:6899/4084823750] state: up:active) since 1325.14s ... I changed IP back to 192.168.0.104 yeasterday, but all the same. # cat /etc/ceph/ceph.conf [client.libvirt] admin socket = /var/run/ceph/$cluster-$type.$id.$pid.$cctid.asok # must be writable by QEMU and allowed by SELinux or AppArmor log file = /var/log/ceph/qemu-guest-$pid.log # must be writable by QEMU and allowed by SELinux or AppArmor [client.rgw.ceph-node1.rgw0] host = ceph-node1 keyring = /var/lib/ceph/radosgw/ceph-rgw.ceph-node1.rgw0/keyring log file = /var/log/ceph/ceph-rgw-ceph-node1.rgw0.log rgw frontends = beast endpoint=192.168.1.6:8080 rgw thread pool size = 512 # Please do not change this file directly since it is managed by Ansible and will be overwritten [global] cluster network = 192.168.1.0/24 fsid = e384e8e6-94d5-4812-bfbb-d1b0468bdef5 mon host = [v2:192.168.1.6:3300,v1:192.168.1.6:6789] mon initial members = ceph-node1 osd crush chooseleaf type = 0 osd pool default crush rule = -1 public network = 192.168.1.0/24 [osd] osd memory target = 7870655146

2 years, 8 months

2
1
0 0

Radosgw PubSub Traffic

by Dustin Guerrero

Hey all, We’ve been running some benchmarks against Ceph which we deployed using the Rook operator in Kubernetes. Everything seemed to scale linearly until a point where I see a single OSD receiving much higher CPU load than the other OSDs (nearly 100% saturation). After some investigation we noticed a ton of pubsub traffic in the strace coming from the RGW pods like so: [pid 22561] sendmsg(77, {msg_name(0)=NULL, msg_iov(3)=[{"\21\2)\0\0\0\10\0:\1\0\0\10\0\0\0\0\0\10\0\0\0\0\0\0\20\0\0-\321\211K"..., 73}, {"\200\0\0\0pubsub.user.ceph-user-wwITOk"..., 314}, {"\0\303\34[\360\314\233\2138\377\377\377\377\377\377\377\377", 17}], msg_controllen=0, msg_flags=0}, MSG_NOSIGNAL|MSG_MORE <unfinished …> I’ve checked other OSDs and only a single OSD receives these messages. I suspect its creating a bottleneck. Does anyone have an idea on why these are being generated or how to stop them? The pubsub sync module doesn’t appear to be enabled, and our benchmark is doing simple gets/puts/deletes. We’re running Ceph 14.2.5 nautilus Thank you!

2 years, 8 months

2
2
0 0

General question CephFS or RBD

by Willi Schiegel

Hello All, I have a HW RAID based 240 TB data pool with about 200 million files for users in a scientific institution. Data sizes range from tiny parameter files for scientific calculations and experiments to huge images of brain scans. There are group directories, home directories, Windows roaming profile directories organized in ZFS pools on Solaris operating systems, exported via NFS and Samba to Linux, macOS, and Windows clients. I would like to switch to CephFS because of the flexibility and expandability but I cannot find any recommendations for which storage backend would be suitable for all the functionality we have. Since I like the features of ZFS like immediate snapshots of very large data pools, quotas for each file system within hierarchical data trees and dynamic expandability by simply adding new disks or disk images without manual resizing would it be a good idea to create RBD images, map them onto the file servers and create zpools on the mapped images? I know that ZFS best works with raw disks but maybe a RBD image is close enough to a raw disk? Or would CephFS be the way to go? Can there be multiple CephFS pools for the group data folders and for the user's home directory folders for example or do I have to have everything in one single file space? Maybe someone can share his or her field experience? Thank you very much. Best regards Willi

2 years, 8 months

2
1
0 0

2023

2022

2021

2020

2019

ceph-users January 2020