mirror of
https://github.com/ceph/ceph
synced 2025-01-07 11:41:48 +00:00
21a3a940e4
Sure, the MDS will always send it to us, but if we've already seen it, we'll ignore the message. Make the reconnect check more robust. |
||
|---|---|---|
| .. | ||
| active | ||
| auth | ||
| client | ||
| common | ||
| crush | ||
| crush.old | ||
| doc | ||
| ebofs | ||
| include | ||
| jobs | ||
| kernel | ||
| mds | ||
| messages | ||
| mon | ||
| msg | ||
| objclass | ||
| os | ||
| osbdb | ||
| osd | ||
| osdc | ||
| s3 | ||
| script | ||
| test | ||
| .gitignore | ||
| barclass.cc | ||
| cconf.cc | ||
| ceph_common.sh | ||
| ceph_ver.c | ||
| ceph.cc | ||
| cfuse.cc | ||
| cls_acl.cc | ||
| cls_crypto.cc | ||
| cm.txt | ||
| cmds.cc | ||
| cmon.cc | ||
| cmonctl | ||
| config.cc | ||
| config.h | ||
| cosd.cc | ||
| cosd.ceph.conf | ||
| crun | ||
| crushtool.cc | ||
| csyn.cc | ||
| dumpjournal.cc | ||
| dupstore.cc | ||
| extractosdmaps.cc | ||
| fakefuse.cc | ||
| fakesyn.cc | ||
| fooclass.cc | ||
| init-ceph | ||
| librados.cc | ||
| loadclass.sh | ||
| make_version | ||
| Makefile.am | ||
| Makefile.old | ||
| Makefile.orig | ||
| mkcephfs | ||
| mkmonfs.cc | ||
| monmaptool.cc | ||
| mount.ceph.c | ||
| osdmaptool.cc | ||
| psim.cc | ||
| rados.cc | ||
| radosacl.cc | ||
| README | ||
| sample.ceph.conf | ||
| stop.sh | ||
| streamtest.cc | ||
| testclass.cc | ||
| testmsgr.cc | ||
| testrados.c | ||
| testradospp.cc | ||
| TODO | ||
| valgrind.supp | ||
| verify-mds-journal.sh | ||
| vstart.sh | ||
A few helper scripts:
mkcephfs.sh -- initialize a new, empty ceph filesystem (by creating a
fresh monfs)
mkfs.sh -- same, but also initialize empty object stores. assumes
all osds are on the same node, with dev/osd# for storage.
stop.sh -- stop/kill all daemons.
restart.sh -- stop everything, then restart everything. (does not mkfs.)
startnew.sh -- stop everything, initialize new ceph fs, and start it.
assumes everything is on one node. for ease of testing.