Created attachment 1179083 [details] rados output Description of problem: Pools cannot be used as storage. For smaller files a new object is created, but it seems to be empty. # echo "test file" > test.txt # rados put -p <pool_name> new_object test.txt # rados ls -p <pool_name> new_object # rados get -p <pool_name> new_object get_test.txt # cat back_test.txt # ls -l back_test.txt -rw-r--r--. 1 root root 0 Jul 13 08:59 back_test.txt For bigger files it crashes. # dd if=/dev/zero of=testfile count=1000 bs=1M # rados put -p <pool_name> new_object2 testfile ... Aborted (core dumped) Version-Release number of selected component (if applicable): rhscon-ceph-0.0.31-1.el7scon.x86_64 rhscon-core-selinux-0.0.32-1.el7scon.noarch rhscon-ui-0.0.46-1.el7scon.noarch rhscon-core-0.0.32-1.el7scon.x86_64 How reproducible: 100% Steps to Reproduce: 1. Create cluster 2. Create some pool 3. Try to create some object in the pool Actual results: Smaller files are not saved correctly, bigger ones fails. Expected results: Files are saved correctly in the pool Additional info: There's cli output, which happens during add of bigger file, in attachment.
Created attachment 1179125 [details] directory created by abort
ceph packages: ceph-mon-10.2.2-5.el7cp.x86_64 ceph-common-10.2.2-5.el7cp.x86_64 ceph-base-10.2.2-5.el7cp.x86_64 ceph-selinux-10.2.2-5.el7cp.x86_64 ceph-osd-10.2.2-5.el7cp.x86_64
Since rados command line tool crashed here, could a ceph team review debug data from abrt (attached to this BZ) to identify component responsible for the problem? (I'm raising needinfo from default contact of RADOS subcomponent of Ceph)
The problem with the small puts is probably a dup of https://bugzilla.redhat.com/show_bug.cgi?id=1350638 and has been fixed in the current packages. *** This bug has been marked as a duplicate of bug 1350638 ***