After a major crushmap reconfiguration, OSDs needed some help to speed
up recovery, freeing up space on nearly-full OSDs earlier than the
cluster would on its own, in some cases temporarily sacrificing some
redundancy.
Unfortunately, ceph_filestore_dump may take a long time to remove even
a single PG, let alone several PGs, and the OSD had to remain down for
the duration of the removal.
Part of the solution was enabling ceph_filestore_dump to just start
the removal of a PG, dropping the metadata and renaming the collection
so that the OSD will pick it up and complete the removal. This patch
introduces --type=premove in ceph_filestore_dump to do this.
Another part of the solution was avoiding the huge startup overhead of
ceph_filestore_dump: mounting the filestore was taking longer than
removing the files proper, and I had more than a handful of PGs to
remove at once. So, I arranged for premove to accept a list of PGs
instead of a single one, also in this patch.
The OSD would still clean everything up before it would join the
cluster; this was addressed in a separate patch.
Signed-off-by: Alexandre Oliva <ol...@gnu.org>
---
src/tools/ceph_filestore_dump.cc | 67 ++++++++++++++++++++++++++++++++++++--
1 file changed, 63 insertions(+), 4 deletions(-)
diff --git a/src/tools/ceph_filestore_dump.cc b/src/tools/ceph_filestore_dump.cc
index 87a8387..1149622 100644
--- a/src/tools/ceph_filestore_dump.cc
+++ b/src/tools/ceph_filestore_dump.cc
@@ -482,6 +482,40 @@ int finish_remove_pgs(ObjectStore *store, uint64_t
*next_removal_seq)
return 0;
}
+//Based on part of OSD::load_pgs()
+int compute_next_removal_seq(ObjectStore *store, uint64_t *next_removal_seq)
+{
+ vector<coll_t> ls;
+ int r = store->list_collections(ls);
+ if (r < 0) {
+ cout << "finish_remove_pgs: failed to list pgs: " << cpp_strerror(-r)
+ << std::endl;
+ return r;
+ }
+
+ for (vector<coll_t>::iterator it = ls.begin();
+ it != ls.end();
+ ++it) {
+ spg_t pgid;
+ snapid_t snap;
+
+ if (it->is_temp(pgid) ||
+ it->is_pg(pgid, snap)) {
+ continue;
+ }
+
+ uint64_t seq;
+ if (it->is_removal(&seq, &pgid)) {
+ if (seq >= *next_removal_seq)
+ *next_removal_seq = seq + 1;
+ continue;
+ }
+
+ //cout << "finish_remove_pgs ignoring unrecognized " << *it << std::endl;
+ }
+ return 0;
+}
+
int initiate_new_remove_pg(ObjectStore *store, spg_t r_pgid,
uint64_t *next_removal_seq)
{
@@ -1088,7 +1122,7 @@ int main(int argc, char **argv)
("pgid", po::value<string>(&pgidstr),
"PG id, mandatory except for import")
("type", po::value<string>(&type),
- "Arg is one of [info, log, remove, export, or import], mandatory")
+ "Arg is one of [info, log, remove, premove, export, or import],
mandatory")
("file", po::value<string>(&file),
"path of file to export or import")
("debug", "Enable diagnostic output to stderr")
@@ -1122,7 +1156,7 @@ int main(int argc, char **argv)
return 1;
}
if (!vm.count("type")) {
- cout << "Must provide type (info, log, remove, export, import)"
+ cout << "Must provide type (info, log, remove, premove, export, import)"
<< std::endl << desc << std::endl;
return 1;
}
@@ -1158,8 +1192,9 @@ int main(int argc, char **argv)
}
if ((fspath.length() == 0 || jpath.length() == 0) ||
- (type != "info" && type != "log" && type != "remove" && type != "export"
- && type != "import") ||
+ (type != "info" && type != "log" &&
+ type != "remove" && type != "premove" &&
+ type != "export" && type != "import") ||
(type != "import" && pgidstr.length() == 0)) {
cerr << "Invalid params" << std::endl;
exit(1);
@@ -1332,6 +1367,30 @@ int main(int argc, char **argv)
goto out;
}
+ if (type == "premove") {
+ uint64_t next_removal_seq = 0; //My local seq
+ compute_next_removal_seq(fs, &next_removal_seq);
+ for (const char *next = pgidstr.c_str(); *next;) {
+ int r = initiate_new_remove_pg(fs, pgid, &next_removal_seq);
+ if (r) {
+ cout << "PG '" << pgid << "' not found" << std::endl;
+ ret = 1;
+ } else
+ cout << "Remove initiated" << std::endl;
+
+ while (*next && *next != ' ' && *next != '\n' && *next != ',')
+ next++;
+ while (*next && !(*next != ' ' && *next != '\n' && *next != ','))
+ next++;
+
+ if (*next && !pgid.parse(next))
+ break;
+ log_oid = OSD::make_pg_log_oid(pgid);
+ biginfo_oid = OSD::make_pg_biginfo_oid(pgid);
+ }
+ goto out;
+ }
+
r = fs->list_collections(ls);
if (r < 0) {
cout << "failed to list pgs: " << cpp_strerror(-r) << std::endl;
--
Alexandre Oliva, freedom fighter http://FSFLA.org/~lxoliva/
You must be the change you wish to see in the world. -- Gandhi
Be Free! -- http://FSFLA.org/ FSF Latin America board member
Free Software Evangelist|Red Hat Brasil GNU Toolchain Engineer
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
