Radically simplify create-pool pg_size check

mon/etcd_schema.js

@@ -56,6 +56,7 @@ const etcd_tree = {
             osd_out_time: 600, // seconds. min: 0
             placement_levels: { datacenter: 1, rack: 2, host: 3, osd: 4, ... },
             use_old_pg_combinator: false,
+            osd_backfillfull_ratio: 0.99,
             // client and osd
             tcp_header_buffer_size: 65536,
             use_sync_send_recv: false,

mon/mon.js

@@ -74,6 +74,7 @@ class Mon
         this.state = JSON.parse(JSON.stringify(etcd_tree));
         this.prev_stats = { osd_stats: {}, osd_diff: {} };
         this.recheck_pgs_active = false;
+        this.updating_total_stats = false;
         this.watcher_active = false;
         this.old_pg_config = false;
         this.old_pg_stats_seen = false;
@@ -658,7 +659,13 @@ class Mon
                 this.etcd_watch_revision, pool_id, up_osds, osd_tree, real_prev_pgs, pool_res.pgs, pg_history);
         }
         new_pg_config.hash = tree_hash;
-        return await this.save_pg_config(new_pg_config, etcd_request);
+        const { backfillfull_pools } = sum_object_counts({ ...this.state, pg: { ...this.state.pg, config: new_pg_config } }, this.config);
+        new_pg_config.backfillfull_pools = backfillfull_pools.length ? backfillfull_pools : undefined;
+        if (!await this.save_pg_config(new_pg_config, etcd_request))
+        {
+            return false;
+        }
+        return true;
     }
 
     async save_pg_config(new_pg_config, etcd_request = { compare: [], success: [] })
@@ -730,7 +737,7 @@ class Mon
     async update_total_stats()
     {
         const txn = [];
-        const { object_counts, object_bytes } = sum_object_counts(this.state, this.config);
+        const { object_counts, object_bytes, backfillfull_pools } = sum_object_counts(this.state, this.config);
         let stats = sum_op_stats(this.state.osd, this.prev_stats);
         let { inode_stats, seen_pools } = sum_inode_stats(this.state, this.prev_stats);
         stats.object_counts = object_counts;
@@ -783,6 +790,16 @@ class Mon
         {
             await this.etcd.etcd_call('/kv/txn', { success: txn }, this.config.etcd_mon_timeout, 0);
         }
+        if (!this.recheck_pgs_active &&
+            backfillfull_pools.join(',') != ((this.state.pg.config||{}).no_rebalance_pools||[]).join(','))
+        {
+            console.log(
+                (backfillfull_pools.length ? 'Pool(s) '+backfillfull_pools.join(', ') : 'No pools')+
+                ' are backfillfull, applying rebalance configuration'
+            );
+            const new_pg_config = { ...this.state.pg.config, backfillfull_pools: backfillfull_pools.length ? backfillfull_pools : undefined };
+            await this.save_pg_config(new_pg_config);
+        }
     }
 
     schedule_update_stats()
@@ -794,7 +811,21 @@ class Mon
         this.stats_timer = setTimeout(() =>
         {
             this.stats_timer = null;
+            if (this.updating_total_stats)
+            {
+                this.schedule_update_stats();
+                return;
+            }
+            this.updating_total_stats = true;
+            try
+            {
                 this.update_total_stats().catch(console.error);
+            }
+            catch (e)
+            {
+                console.error(e);
+            }
+            this.updating_total_stats = false;
         }, this.config.mon_stats_timeout);
     }
 

mon/stats.js

@@ -109,6 +109,8 @@ function sum_object_counts(state, global_config)
             pgstats[pool_id] = { ...(state.pg.stats[pool_id] || {}), ...(pgstats[pool_id] || {}) };
         }
     }
+    const pool_per_osd = {};
+    const clean_per_osd = {};
     for (const pool_id in pgstats)
     {
         let object_size = 0;
@@ -143,10 +145,38 @@ function sum_object_counts(state, global_config)
                         object_bytes[k] += BigInt(st[k+'_count']) * object_size;
                     }
                 }
+                if (st.object_count)
+                {
+                    for (const pg_osd in (((state.pg.config.items||{})[pool_id]||{})[pg_num]||{}).osd_set||[])
+                    {
+                        if (!(pg_osd in clean_per_osd))
+                        {
+                            clean_per_osd[pg_osd] = 0n;
+                        }
+                        clean_per_osd[pg_osd] += BigInt(st.object_count);
+                        pool_per_osd[pg_osd] = pool_per_osd[pg_osd]||{};
+                        pool_per_osd[pg_osd][pool_id] = true;
                     }
                 }
             }
-    return { object_counts, object_bytes };
+        }
+    }
+    // If clean_per_osd[osd] is larger than osd capacity then it will fill up during rebalance
+    let backfillfull_pools = {};
+    for (const osd in clean_per_osd)
+    {
+        const st = state.osd.stats[osd];
+        if (st && st.size && st.data_block_size && (BigInt(st.size)/BigInt(st.data_block_size)*
+            BigInt((global_config.osd_backfillfull_ratio||0.99)*1000000)/1000000n) < clean_per_osd[osd])
+        {
+            for (const pool_id in pool_per_osd[osd])
+            {
+                backfillfull_pools[pool_id] = true;
+            }
+        }
+    }
+    backfillfull_pools = Object.keys(backfillfull_pools).sort();
+    return { object_counts, object_bytes, backfillfull_pools };
 }
 
 // sum_inode_stats(this.state, this.prev_stats)

src/client/etcd_state_client.cpp

@@ -785,7 +785,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
         }
         for (auto & pool_item: value.object_items())
         {
-            pool_config_t pc;
+            pool_config_t pc = {};
             // ID
             pool_id_t pool_id;
             char null_byte = 0;
@@ -931,12 +931,28 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
             // Ignore old key if the new one is present
             return;
         }
+        for (auto & pool_id_json: value["backfillfull_pools"].array_items())
+        {
+            auto pool_id = pool_id_json.uint64_value();
+            auto pool_it = this->pool_config.find(pool_id);
+            if (pool_it != this->pool_config.end())
+            {
+                pool_it->second.backfillfull |= 2;
+            }
+        }
         for (auto & pool_item: this->pool_config)
         {
             for (auto & pg_item: pool_item.second.pg_config)
             {
                 pg_item.second.config_exists = false;
             }
+            // 3 = was 1 and became 1, 0 = was 0 and became 0
+            if (pool_item.second.backfillfull == 2 || pool_item.second.backfillfull == 1)
+            {
+                if (on_change_backfillfull_hook)
+                    on_change_backfillfull_hook(pool_item.first);
+            }
+            pool_item.second.backfillfull = pool_item.second.backfillfull >> 1;
         }
         for (auto & pool_item: value["items"].object_items())
         {

src/client/etcd_state_client.h

@@ -62,6 +62,7 @@ struct pool_config_t
     std::map<pg_num_t, pg_config_t> pg_config;
     uint64_t scrub_interval;
     std::string used_for_fs;
+    int backfillfull;
 };
 
 struct inode_config_t
@@ -131,6 +132,7 @@ public:
     std::function<json11::Json()> load_pgs_checks_hook;
     std::function<void(bool)> on_load_pgs_hook;
     std::function<void()> on_change_pool_config_hook;
+    std::function<void(pool_id_t)> on_change_backfillfull_hook;
     std::function<void(pool_id_t, pg_num_t, osd_num_t)> on_change_pg_state_hook;
     std::function<void(pool_id_t, pg_num_t)> on_change_pg_history_hook;
     std::function<void(osd_num_t)> on_change_osd_state_hook;

src/cmd/cli_pool_create.cpp

@@ -35,6 +35,7 @@ struct pool_creator_t
     uint64_t new_pools_mod_rev;
     json11::Json state_node_tree;
     json11::Json new_pools;
+    std::map<osd_num_t, json11::Json> osd_stats;
 
     bool is_done() { return state == 100; }
 
@@ -46,8 +47,6 @@ struct pool_creator_t
             goto resume_2;
         else if (state == 3)
             goto resume_3;
-        else if (state == 4)
-            goto resume_4;
         else if (state == 5)
             goto resume_5;
         else if (state == 6)
@@ -121,15 +120,15 @@ resume_2:
             // Get state_node_tree based on node_placement and osd stats
             {
                 auto node_placement_kv = parent->cli->st_cli.parse_etcd_kv(parent->etcd_result["responses"][0]["response_range"]["kvs"][0]);
-                std::map<osd_num_t, json11::Json> osd_stats;
                 timespec tv_now;
                 clock_gettime(CLOCK_REALTIME, &tv_now);
                 uint64_t osd_out_time = parent->cli->config["osd_out_time"].uint64_value();
                 if (!osd_out_time)
                     osd_out_time = 600;
+                osd_stats.clear();
                 parent->iterate_kvs_1(parent->etcd_result["responses"][1]["response_range"]["kvs"], "/osd/stats/", [&](uint64_t cur_osd, json11::Json value)
                 {
-                    if (value["time"].uint64_value()+osd_out_time >= tv_now.tv_sec)
+                    if ((uint64_t)value["time"].number_value()+osd_out_time >= tv_now.tv_sec)
                         osd_stats[cur_osd] = value;
                 });
                 state_node_tree = get_state_node_tree(node_placement_kv.value.object_items(), osd_stats);
@@ -175,42 +174,18 @@ resume_3:
                 }
             }
 
-            // Get stats (for block_size, bitmap_granularity, ...) of osds in state_node_tree
-            {
-                json11::Json::array osd_stats;
-
-                for (auto osd_num: state_node_tree["osds"].array_items())
-                {
-                    osd_stats.push_back(json11::Json::object {
-                        { "request_range", json11::Json::object {
-                            { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/osd/stats/"+osd_num.as_string()) },
-                        } }
-                    });
-                }
-
-                parent->etcd_txn(json11::Json::object{ { "success", osd_stats } });
-            }
-
-            state = 4;
-resume_4:
-            if (parent->waiting > 0)
-                return;
-            if (parent->etcd_err.err)
-            {
-                result = parent->etcd_err;
-                state = 100;
-                return;
-            }
-
             // Filter osds from state_node_tree based on pool parameters and osd stats
             {
-                std::vector<json11::Json> osd_stats;
-                for (auto & ocr: parent->etcd_result["responses"].array_items())
+                std::vector<json11::Json> filtered_osd_stats;
+                for (auto & osd_num: state_node_tree["osds"].array_items())
                 {
-                    auto kv = parent->cli->st_cli.parse_etcd_kv(ocr["response_range"]["kvs"][0]);
-                    osd_stats.push_back(kv.value);
+                    auto st_it = osd_stats.find(osd_num.uint64_value());
+                    if (st_it != osd_stats.end())
+                    {
+                        filtered_osd_stats.push_back(st_it->second);
                     }
-                guess_block_size(osd_stats);
+                }
+                guess_block_size(filtered_osd_stats);
                 state_node_tree = filter_state_node_tree_by_stats(state_node_tree, osd_stats);
             }
 
@@ -218,8 +193,7 @@ resume_4:
             {
                 auto failure_domain = cfg["failure_domain"].string_value() == ""
                     ? "host" : cfg["failure_domain"].string_value();
-                uint64_t max_pg_size = get_max_pg_size(state_node_tree["nodes"].object_items(),
-                    failure_domain, cfg["root_node"].string_value());
+                uint64_t max_pg_size = get_max_pg_size(state_node_tree, failure_domain, cfg["root_node"].string_value());
 
                 if (cfg["pg_size"].uint64_value() > max_pg_size)
                 {
@@ -411,14 +385,12 @@ resume_8:
                 };
             }
 
-            // Add osd if necessary
-            if (node_placement.find(osd_num) == node_placement.end())
-            {
+            // Add osd
             node_placement[osd_num] = json11::Json::object {
-                    { "parent", osd_host }
+                { "parent", node_placement[osd_num]["parent"].is_null() ? osd_host : node_placement[osd_num]["parent"] },
+                { "level", "osd" },
             };
         }
-        }
 
         return json11::Json::object { { "osds", existing_osds }, { "nodes", node_placement } };
     }
@@ -547,15 +519,13 @@ resume_8:
     // filtered out by stats parameters (block_size, bitmap_granularity) in
     // given osd_stats and current pool config.
     // Requires: state_node_tree["osds"] must match osd_stats 1-1
-    json11::Json filter_state_node_tree_by_stats(const json11::Json & state_node_tree, std::vector<json11::Json> & osd_stats)
+    json11::Json filter_state_node_tree_by_stats(const json11::Json & state_node_tree, std::map<osd_num_t, json11::Json> & osd_stats)
     {
-        auto & osds = state_node_tree["osds"].array_items();
-
         // Accepted state_node_tree nodes
         auto accepted_nodes = state_node_tree["nodes"].object_items();
 
         // List of accepted osds
-        std::vector<std::string> accepted_osds;
+        json11::Json::array accepted_osds;
 
         block_size = cfg["block_size"].uint64_value()
             ? cfg["block_size"].uint64_value()
@@ -567,21 +537,25 @@ resume_8:
             ? etcd_state_client_t::parse_immediate_commit(cfg["immediate_commit"].string_value(), IMMEDIATE_ALL)
             : parent->cli->st_cli.global_immediate_commit;
 
-        for (size_t i = 0; i < osd_stats.size(); i++)
+        for (auto osd_num_json: state_node_tree["osds"].array_items())
         {
-            auto & os = osd_stats[i];
-            // Get osd number
-            auto osd_num = osds[i].as_string();
+            auto osd_num = osd_num_json.uint64_value();
+            auto os_it = osd_stats.find(osd_num);
+            if (os_it == osd_stats.end())
+            {
+                continue;
+            }
+            auto & os = os_it->second;
             if (!os["data_block_size"].is_null() && os["data_block_size"] != block_size ||
                 !os["bitmap_granularity"].is_null() && os["bitmap_granularity"] != bitmap_granularity ||
                 !os["immediate_commit"].is_null() &&
                 etcd_state_client_t::parse_immediate_commit(os["immediate_commit"].string_value(), IMMEDIATE_NONE) < immediate_commit)
             {
-                accepted_nodes.erase(osd_num);
+                accepted_nodes.erase(osd_num_json.as_string());
             }
             else
             {
-                accepted_osds.push_back(osd_num);
+                accepted_osds.push_back(osd_num_json);
             }
         }
 
@@ -589,81 +563,28 @@ resume_8:
     }
 
     // Returns maximum pg_size possible for given node_tree and failure_domain, starting at parent_node
-    uint64_t get_max_pg_size(json11::Json::object node_tree, const std::string & level, const std::string & parent_node)
+    uint64_t get_max_pg_size(json11::Json state_node_tree, const std::string & level, const std::string & root_node)
     {
-        uint64_t max_pg_sz = 0;
-
-        std::vector<std::string> nodes;
-
-        // Check if parent node is an osd (numeric)
-        if (parent_node != "" && stoull_full(parent_node))
+        std::set<std::string> level_seen;
+        for (auto & osd: state_node_tree["osds"].array_items())
         {
-            // Add it to node list if osd is in node tree
-            if (node_tree.find(parent_node) != node_tree.end())
-                nodes.push_back(parent_node);
-        }
-        // If parent node given, ...
-        else if (parent_node != "")
+            // find OSD parent at <level>, but stop at <root_node>
+            auto cur_id = osd.string_value();
+            auto cur = state_node_tree["nodes"][cur_id];
+            while (!cur.is_null())
             {
-            // ... look for child nodes of this parent
-            for (auto & sn: node_tree)
+                if (cur["level"] == level)
                 {
-                if (sn.second["parent"] == parent_node)
-                {
-                    nodes.push_back(sn.first);
-
-                    // If we're not looking for all osds, we only need a single
-                    // child osd node
-                    if (level != "osd" && stoull_full(sn.first))
+                    level_seen.insert(cur_id);
                     break;
                 }
+                if (cur_id == root_node)
+                    break;
+                cur_id = cur["parent"].string_value();
+                cur = state_node_tree["nodes"][cur_id];
             }
         }
-        // No parent node given, and we're not looking for all osds
-        else if (level != "osd")
-        {
-            // ... look for all level nodes
-            for (auto & sn: node_tree)
-            {
-                if (sn.second["level"] == level)
-                {
-                    nodes.push_back(sn.first);
-                }
-            }
-        }
-        // Otherwise, ...
-        else
-        {
-            // ... we're looking for osd nodes only
-            for (auto & sn: node_tree)
-            {
-                if (stoull_full(sn.first))
-                {
-                    nodes.push_back(sn.first);
-                }
-            }
-        }
-
-        // Process gathered nodes
-        for (auto & node: nodes)
-        {
-            // Check for osd node, return constant max size
-            if (stoull_full(node))
-            {
-                max_pg_sz += 1;
-            }
-            // Otherwise, ...
-            else
-            {
-                // ... exclude parent node from tree, and ...
-                node_tree.erase(parent_node);
-
-                // ... descend onto the resulting tree
-                max_pg_sz += get_max_pg_size(node_tree, level, node);
-            }
-        }
-
-        return max_pg_sz;
+        return level_seen.size();
     }
 
     json11::Json create_pool(const etcd_kv_t & kv)

src/osd/osd.h

@@ -226,6 +226,7 @@ class osd_t
     void parse_config(bool init);
     void init_cluster();
     void on_change_osd_state_hook(osd_num_t peer_osd);
+    void on_change_backfillfull_hook(pool_id_t pool_id);
     void on_change_pg_history_hook(pool_id_t pool_id, pg_num_t pg_num);
     void on_change_etcd_state_hook(std::map<std::string, etcd_kv_t> & changes);
     void on_load_config_hook(json11::Json::object & changes);

src/osd/osd_cluster.cpp

@@ -65,6 +65,7 @@ void osd_t::init_cluster()
         st_cli.tfd = tfd;
         st_cli.log_level = log_level;
         st_cli.on_change_osd_state_hook = [this](osd_num_t peer_osd) { on_change_osd_state_hook(peer_osd); };
+        st_cli.on_change_backfillfull_hook = [this](pool_id_t pool_id) { on_change_backfillfull_hook(pool_id); };
         st_cli.on_change_pg_history_hook = [this](pool_id_t pool_id, pg_num_t pg_num) { on_change_pg_history_hook(pool_id, pg_num); };
         st_cli.on_change_hook = [this](std::map<std::string, etcd_kv_t> & changes) { on_change_etcd_state_hook(changes); };
         st_cli.on_load_config_hook = [this](json11::Json::object & cfg) { on_load_config_hook(cfg); };
@@ -414,6 +415,14 @@ void osd_t::on_change_osd_state_hook(osd_num_t peer_osd)
     }
 }
 
+void osd_t::on_change_backfillfull_hook(pool_id_t pool_id)
+{
+    if (!(peering_state & (OSD_RECOVERING | OSD_FLUSHING_PGS)))
+    {
+        peering_state = peering_state | OSD_RECOVERING;
+    }
+}
+
 void osd_t::on_change_etcd_state_hook(std::map<std::string, etcd_kv_t> & changes)
 {
     if (changes.find(st_cli.etcd_prefix+"/config/global") != changes.end())

src/osd/osd_flush.cpp

@@ -252,10 +252,18 @@ bool osd_t::pick_next_recovery(osd_recovery_op_t &op)
             auto mask = recovery_last_degraded ? (PG_ACTIVE | PG_HAS_DEGRADED) : (PG_ACTIVE | PG_DEGRADED | PG_HAS_MISPLACED);
             auto check = recovery_last_degraded ? (PG_ACTIVE | PG_HAS_DEGRADED) : (PG_ACTIVE | PG_HAS_MISPLACED);
             // Restart scanning from the same PG as the last time
+        restart:
             for (auto pg_it = pgs.lower_bound(recovery_last_pg); pg_it != pgs.end(); pg_it++)
             {
                 if ((pg_it->second.state & mask) == check)
                 {
+                    auto pool_it = st_cli.pool_config.find(pg_it->first.pool_id);
+                    if (pool_it != st_cli.pool_config.end() && pool_it->second.backfillfull)
+                    {
+                        // Skip the pool
+                        recovery_last_pg.pool_id++;
+                        goto restart;
+                    }
                     auto & src = recovery_last_degraded ? pg_it->second.degraded_objects : pg_it->second.misplaced_objects;
                     assert(src.size() > 0);
                     // Restart scanning from the next object