From 3bd128d7a0d724dbd5ff27fc63923a05ee04d66c Mon Sep 17 00:00:00 2001 From: Aaron Lauterer Date: Thu, 28 Apr 2022 13:58:09 +0200 Subject: [PATCH] ceph pools: allow to create erasure code pools To use erasure coded (EC) pools for RBD storages, we need two pools. One regular replicated pool that will hold the RBD omap and other metadata and the EC pool which will hold the image data. 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, 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 --- PVE/API2/Ceph/Pools.pm | 120 ++++++++++++++++++++++++++++++++++++++--- PVE/Ceph/Tools.pm | 11 ++-- 2 files changed, 122 insertions(+), 9 deletions(-) diff --git a/PVE/API2/Ceph/Pools.pm b/PVE/API2/Ceph/Pools.pm index 05855e15..69cf0d1a 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); }; @@ -330,10 +332,41 @@ __PACKAGE__->register_method ({ properties => { node => get_standard_option('pve-node'), add_storages => { - description => "Configure VM and CT storage using the new pool.", + description => "Configure VM and CT storage using the new pool. ". + "Always enabled for erasure coded pools.", type => 'boolean', optional => 1, }, + k => { + type => 'integer', + description => "Number of data chunks. Will create an erasure coded pool plus a ". + "replicated pool for metadata.", + optional => 1, + }, + m => { + type => 'integer', + description => "Number of coding chunks. Will create an erasure coded pool plus a ". + "replicated pool for metadata.", + optional => 1, + }, + 'failure-domain' => { + type => 'string', + description => "CRUSH failure domain. Default is 'host'. Will create an erasure ". + "coded pool plus a replicated pool for metadata.", + optional => 1, + }, + 'device-class' => { + type => 'string', + description => "CRUSH device class. Will create an erasure coded pool plus a ". + "replicated pool for metadata.", + optional => 1, + }, + ecprofile => { + description => "Override the erasure code (EC) profile to use. Will create an ". + "erasure coded pool plus a replicated pool for metadata.", + type => 'string', + optional => 1, + }, %{ $ceph_pool_common_options->() }, }, }, @@ -344,10 +377,31 @@ __PACKAGE__->register_method ({ PVE::Cluster::check_cfs_quorum(); PVE::Ceph::Tools::check_ceph_configured(); - my $pool = extract_param($param, 'name'); + my $pool = my $name = extract_param($param, 'name'); my $node = extract_param($param, 'node'); my $add_storages = extract_param($param, 'add_storages'); + my $ec_k = extract_param($param, 'k'); + my $ec_m = extract_param($param, 'm'); + my $ec_failure_domain = extract_param($param, 'failure-domain'); + my $ec_device_class = extract_param($param, 'device-class'); + + my $is_ec = 0; + + my $ecprofile = extract_param($param, 'ecprofile'); + die "Erasure code profile '$ecprofile' does not exist.\n" + if $ecprofile && !PVE::Ceph::Tools::ecprofile_exists($ecprofile); + + if ($ec_k || $ec_m || $ec_failure_domain || $ec_device_class) { + die "'k' and 'm' parameters are needed for an erasure coded pool\n" + if !$ec_k || !$ec_m; + + $is_ec = 1; + } + + $is_ec = 1 if $ecprofile; + $add_storages = 1 if $is_ec; + my $rpcenv = PVE::RPCEnvironment::get(); my $user = $rpcenv->get_user(); @@ -370,13 +424,47 @@ __PACKAGE__->register_method ({ $param->{application} //= 'rbd'; $param->{pg_autoscale_mode} //= 'warn'; - my $worker = sub { + my $data_param = {}; + my $data_pool = ''; + if (!$ecprofile) { + $ecprofile = PVE::Ceph::Tools::get_ecprofile_name($pool); + eval { + PVE::Ceph::Tools::create_ecprofile( + $ecprofile, + $ec_k, + $ec_m, + $ec_failure_domain, + $ec_device_class, + ); + }; + die "could not create erasure code profile '$ecprofile': $@\n" if $@; + } + + if ($is_ec) { + # 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 $is_ec; + if ($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 $@; } }; @@ -414,6 +502,12 @@ __PACKAGE__->register_method ({ optional => 1, default => 0, }, + remove_ecprofile => { + description => "Remove the erasure code profile. Used for erasure code pools. Default is true", + type => 'boolean', + optional => 1, + default => 1, + }, }, }, returns => { type => 'string' }, @@ -428,6 +522,7 @@ __PACKAGE__->register_method ({ if $param->{remove_storages}; my $pool = $param->{name}; + my $remove_ecprofile = $param->{remove_ecprofile} // 1; my $worker = sub { my $storages = $get_storages->($pool); @@ -447,8 +542,21 @@ __PACKAGE__->register_method ({ } } + my $pool_properties = PVE::Ceph::Tools::get_pool_properties($pool); + PVE::Ceph::Tools::destroy_pool($pool); + if (my $ecprofile = $pool_properties->{erasure_code_profile}) { + my $crush_rule = $pool_properties->{crush_rule}; + eval { PVE::Ceph::Tools::destroy_crush_rule($crush_rule); }; + warn "removing crush rule '${crush_rule}' failed: $@\n" if $@; + + if ($remove_ecprofile) { + eval { PVE::Ceph::Tools::destroy_ecprofile($ecprofile) }; + warn "removing EC profile '${ecprofile}' failed: $@\n" if $@; + } + } + if ($param->{remove_storages}) { my $err; foreach my $storeid (keys %$storages) { diff --git a/PVE/Ceph/Tools.pm b/PVE/Ceph/Tools.pm index 2459e882..8a744497 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; @@ -274,12 +274,17 @@ 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); -- 2.39.2