ceph/src
2009-10-09 10:55:32 -07:00
..
active
auth use sockaddr_storage; and some ipv6 support groundwork 2009-10-02 13:39:17 -07:00
client libceph: move to main dir with other main .cc files 2009-10-08 10:42:11 -07:00
common conf: also skip utf8 encoded characters that are not printable in current locale 2009-10-06 12:35:54 -07:00
crush crush: zero weight items get 0 length straws 2009-10-07 11:55:49 -07:00
crush.old
doc
ebofs strerror -> strerror_r 2009-09-18 16:17:04 -07:00
include byteorder: braces! 2009-10-09 10:55:32 -07:00
jobs
mds mds: validate file layouts on file creation, setlayout 2009-10-08 09:21:39 -07:00
messages libceph: move to main dir with other main .cc files 2009-10-08 10:42:11 -07:00
mon mon: fix session close races 2009-10-08 11:45:27 -07:00
mount mount.ceph: block same signals as /sbin/mount 2009-08-21 11:00:33 -07:00
msg msgr: reset session state on lossy_tx fault 2009-10-08 21:20:22 -07:00
objclass osd: name args in ceph_osd_op union 2009-09-30 12:47:40 -07:00
os filestore: be less excited about btrfs version 2009-10-07 16:45:02 -07:00
osbdb
osd osd: check is_dup earlier; do not set osdop version if it's a noop 2009-10-09 10:53:37 -07:00
osdc objecter: don't send duplicate onetime sub requests 2009-10-08 11:44:17 -07:00
radosgw rgw: fix build errors on i386 2009-10-06 10:30:26 -07:00
script check_mds_request_latency: fix parsing for current debug output 2009-09-14 15:07:30 -07:00
test move tests around 2009-10-06 14:00:54 -07:00
.gitignore
barclass.cc
cconf.cc
ceph_common.sh initscripts: do what we can to run as user specified in the conf 2009-07-13 10:38:23 -07:00
ceph_ver.c
ceph.cc msgr: do not require bind() on client apps 2009-10-08 10:02:22 -07:00
cfuse.cc osd: use fast_fail() policy to connect to osd 2009-10-08 10:34:09 -07:00
cls_acl.cc
cls_crypto.cc
cm.txt
cmds.cc osd: use fast_fail() policy to connect to osd 2009-10-08 10:34:09 -07:00
cmon.cc use sockaddr_storage; and some ipv6 support groundwork 2009-10-02 13:39:17 -07:00
cmonctl
config.cc use sockaddr_storage; and some ipv6 support groundwork 2009-10-02 13:39:17 -07:00
config.h mds: kill old rdcaps_ttl business 2009-09-30 12:24:31 -07:00
cosd.cc osd: don't manually set rank addr 2009-10-08 11:43:43 -07:00
cosd.ceph.conf cosd: 3 monitors 2009-09-29 11:09:38 -07:00
crun
crushtool.cc crushtool: show zero weight items in crush map decode/dump 2009-10-07 11:55:54 -07:00
csyn.cc osd: use fast_fail() policy to connect to osd 2009-10-08 10:34:09 -07:00
dumpjournal.cc msgr: pass Connection* to msgr error handlers 2009-09-21 14:24:35 -07:00
dupstore.cc
extractosdmaps.cc
fakefuse.cc
fakesyn.cc
fooclass.cc
init-ceph.in init-ceph: fix pre/post commands 2009-09-08 14:13:04 -07:00
libceph.cc libceph: move to main dir with other main .cc files 2009-10-08 10:42:11 -07:00
librados.cc osd: use fast_fail() policy to connect to osd 2009-10-08 10:34:09 -07:00
loadclass.sh
make_version version: git rev-parse, not git-rev-parse 2009-10-07 15:36:16 -07:00
Makefile.am libceph: move to main dir with other main .cc files 2009-10-08 10:42:11 -07:00
Makefile.old
Makefile.orig
mkcephfs.in initscripts: /etc, not /usr/etc 2009-07-15 14:07:37 -07:00
mkmonfs.cc
monmaptool.cc strerror -> strerror_r 2009-09-18 16:17:04 -07:00
osdmaptool.cc osdmaptool: more usage 2009-09-28 10:09:26 -07:00
psim.cc psim: ifdef out dead code 2009-08-11 16:14:41 -07:00
push_to_kclient.pl push_to_kclient: fix dest tree check 2009-10-07 10:33:08 -07:00
rados.cc strerror -> strerror_r 2009-09-18 16:17:04 -07:00
radosacl.cc
README
sample.ceph.conf
stop.sh
streamtest.cc
testclass.cc
testmsgr.cc msgr: pass Connection* to msgr error handlers 2009-09-21 14:24:35 -07:00
testrados.c
testradospp.cc s3gw: interface changes, preparing grounds for user metadata 2009-07-14 16:09:37 -07:00
TODO todo 2009-10-06 14:00:54 -07:00
valgrind.supp
verify-mds-journal.sh
vstart.sh vstart: be quiet 2009-08-31 16:33:45 -07:00

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.