ceph Vol 45 Issue 3

1.Crash in ceph_readdir.


I’ve been investigating the following crash with cephfs:
According to the state of the ceph_inoide_info this means that
ceph_dir_is_complete_ordered would return true and the second condition
should also be true since ptr_pos is held in r12 and the dir size is 26496.
So the dentry being passed should be the 2953 % 512 = 393 in the
cache_ctl.dentries array.
Unfortunately my crashdump excldues the page cache pages and I cannot really see
what are the contents of the dentries array.

Could you provide any info on how to further debug this


Yan, Zheng已经对这个bug进行了修复


但是这个是提交到Linux kernel的4.6的分支里面去了的,所以目前从官方版本来说是4.6或者更新的版本才会解决


2.Can’t activate OSD

Hello all,

Over the past few weeks I’ve been trying to go through the Quick Ceph Deploy
tutorial at:

ceph-deploy osd activate ceph02:/dev/sdc ceph03:/dev/sdc

part. It never actually seems to activate the OSD and eventually times out:

[ceph03][INFO ] Running command: sudo /usr/sbin/ceph-disk -v activate —mark-init systemd —mount /dev/sdc
[ceph03][WARNIN] main_activate: path = /dev/sdc
[ceph03][WARNIN] No data was received after 300 seconds, disconnecting…

作者在部署osd的时候出现无法激活osd的问题,最后在别人的帮助下发现了问题,在交换机上创建了 VLAN ,但没允许jumbo packets,所以出现了问题

另外一个人也出现了类似的问题,通过升级了parted解决问题(from 3.1 from the CentOS7 base)

rpm -Uhv

这个一般没什么问题,确实定位到这里再升级了,一般情况下很少出现不能activate osd的情况


Why Who When
创建 武汉-运维-磨渣 2016-11-08
完成Issue 3 武汉-运维-磨渣 2016-11-08