[pve-devel] [PATCH manager 4/4] ceph pools: allow to create erasure code pools

[Aaron Lauterer <a.lauterer@proxmox.com>]

When using erasure coded pools for RBD storages, the main use case in
this patch, we need a replicated pool that will hold the RBD omap and
other metadata. The EC pool itself will only hold the data objects.

The coupling happens when an RBD image is created by adding the
--data-pool parameter. This is why we have the 'data-pool' parameter in
the storage configuration.

To follow already established semantics, once the 'ecprofile' parameter
is provided, we will create a 'X-metadata' and 'X-data' pool. The
storage configuration is always added as it is the only thing that links
the two together (besides naming schemes).

Different pg_num defaults are chosen for the replicated metadata pool as
it will not hold a lot of data.

Signed-off-by: Aaron Lauterer <a.lauterer@proxmox.com>
---
At first I though that we should add another API endpoint just to create
EC pools, but that then brings the problem with it, that we need a new
(sub)path for the new POST endpoint.

Since we do not actually change that much in the existing one to support
ec pools, I went for that now. We do need to copy over the pool params
for the ec pool and change defaults a bit for the meta and data pool.


 PVE/API2/Ceph/Pools.pm | 46 ++++++++++++++++++++++++++++++++++++++----
 PVE/Ceph/Tools.pm      | 11 +++++++---
 2 files changed, 50 insertions(+), 7 deletions(-)

diff --git a/PVE/API2/Ceph/Pools.pm b/PVE/API2/Ceph/Pools.pm
index 05855e15..1a6a346b 100644
--- a/PVE/API2/Ceph/Pools.pm
+++ b/PVE/API2/Ceph/Pools.pm
@@ -280,7 +280,7 @@ my $ceph_pool_common_options = sub {
 
 
 my $add_storage = sub {
-    my ($pool, $storeid) = @_;
+    my ($pool, $storeid, $data_pool) = @_;
 
     my $storage_params = {
 	type => 'rbd',
@@ -290,6 +290,8 @@ my $add_storage = sub {
 	content => 'rootdir,images',
     };
 
+    $storage_params->{'data-pool'} = $data_pool if $data_pool;
+
     PVE::API2::Storage::Config->create($storage_params);
 };
 
@@ -334,6 +336,13 @@ __PACKAGE__->register_method ({
 		type => 'boolean',
 		optional => 1,
 	    },
+	    ecprofile => {
+		description => "Erasure code profile to use. This will create a replicated ".
+			       "metadata pool, an erasure coded metadata pool and the storage ".
+			       "configuration.",
+		type => 'string',
+		optional => 1,
+	    },
 	    %{ $ceph_pool_common_options->() },
 	},
     },
@@ -344,10 +353,17 @@ __PACKAGE__->register_method ({
 	PVE::Cluster::check_cfs_quorum();
 	PVE::Ceph::Tools::check_ceph_configured();
 
-	my $pool = extract_param($param, 'name');
+	my $name = extract_param($param, 'name');
+	my $pool = $name;
 	my $node = extract_param($param, 'node');
 	my $add_storages = extract_param($param, 'add_storages');
 
+	my $ecprofile = extract_param($param, 'ecprofile');
+	die "Erasure code profile '$ecprofile' does not exist.\n"
+	    if $ecprofile && !PVE::Ceph::Tools::ecprofile_exists($ecprofile);
+
+	$add_storages = 1 if $ecprofile;
+
 	my $rpcenv = PVE::RPCEnvironment::get();
 	my $user = $rpcenv->get_user();
 
@@ -370,13 +386,35 @@ __PACKAGE__->register_method ({
 	$param->{application} //= 'rbd';
 	$param->{pg_autoscale_mode} //= 'warn';
 
+	my $data_param = {};
+	my $data_pool = '';
+
+	if ($ecprofile) {
+	    # copy all params, should be a flat hash
+	    $data_param = { map { $_ => $param->{$_} } keys %$param };
+
+	    $data_param->{pool_type} = 'erasure';
+	    $data_param->{allow_ec_overwrites} = 'true';
+	    $data_param->{erasure_code_profile} = $ecprofile;
+	    delete $data_param->{size};
+	    delete $data_param->{min_size};
+
+	    # metadata pool should be ok with 32 PGs
+	    $param->{pg_num} = 32;
+
+	    $pool = "${name}-metadata";
+	    $data_pool = "${name}-data";
+	}
+
 	my $worker = sub {
 
 	    PVE::Ceph::Tools::create_pool($pool, $param);
 
+	    PVE::Ceph::Tools::create_pool($data_pool, $data_param) if $ecprofile;
+
 	    if ($add_storages) {
-		eval { $add_storage->($pool, "${pool}") };
-		die "adding PVE storage for ceph pool '$pool' failed: $@\n" if $@;
+		eval { $add_storage->($pool, "${name}", $data_pool) };
+		die "adding PVE storage for ceph pool '$name' failed: $@\n" if $@;
 	    }
 	};
 
diff --git a/PVE/Ceph/Tools.pm b/PVE/Ceph/Tools.pm
index 91aa6ce5..18051e06 100644
--- a/PVE/Ceph/Tools.pm
+++ b/PVE/Ceph/Tools.pm
@@ -8,7 +8,7 @@ use File::Basename;
 use IO::File;
 use JSON;
 
-use PVE::Tools qw(run_command dir_glob_foreach);
+use PVE::Tools qw(run_command dir_glob_foreach extract_param);
 use PVE::Cluster qw(cfs_read_file);
 use PVE::RADOS;
 use PVE::Ceph::Services;
@@ -264,12 +264,17 @@ sub create_pool {
 
     my $pg_num = $param->{pg_num} || 128;
 
-    $rados->mon_command({
+    my $mon_params = {
 	prefix => "osd pool create",
 	pool => $pool,
 	pg_num => int($pg_num),
 	format => 'plain',
-    });
+    };
+    $mon_params->{pool_type} = extract_param($param, 'pool_type') if $param->{pool_type};
+    $mon_params->{erasure_code_profile} = extract_param($param, 'erasure_code_profile')
+	if $param->{erasure_code_profile};
+
+    $rados->mon_command($mon_params);
 
     set_pool($pool, $param);
 
-- 
2.30.2