Report slow ops in OSD stats in etcd and show them in vitastor-cli status
This commit is contained in:
@@ -216,7 +216,7 @@ resume_1:
|
||||
for (uint64_t osd_num: node.child_osds)
|
||||
{
|
||||
auto & osd = placement_tree->osds.at(osd_num);
|
||||
fmt_items.push_back(json11::Json::object{
|
||||
auto json_osd = json11::Json::object{
|
||||
{ "type", "osd" },
|
||||
{ "name", osd.num },
|
||||
{ "parent", node.name },
|
||||
@@ -230,7 +230,16 @@ resume_1:
|
||||
{ "bitmap", (uint64_t)osd.bitmap_granularity },
|
||||
{ "commit", osd.immediate_commit == IMMEDIATE_NONE ? "none" : (osd.immediate_commit == IMMEDIATE_ALL ? "all" : "small") },
|
||||
{ "op_stats", osd_stats[osd_num]["op_stats"] },
|
||||
});
|
||||
};
|
||||
if (osd_stats[osd_num]["slow_ops_primary"].uint64_value() > 0)
|
||||
{
|
||||
json_osd["slow_ops_primary"] = osd_stats[osd_num]["slow_ops_primary"];
|
||||
}
|
||||
if (osd_stats[osd_num]["slow_ops_secondary"].uint64_value() > 0)
|
||||
{
|
||||
json_osd["slow_ops_secondary"] = osd_stats[osd_num]["slow_ops_secondary"];
|
||||
}
|
||||
fmt_items.push_back(json_osd);
|
||||
}
|
||||
}
|
||||
result.data = fmt_items;
|
||||
|
||||
@@ -134,6 +134,7 @@ resume_2:
|
||||
}
|
||||
int osd_count = 0, osd_up = 0;
|
||||
uint64_t total_raw = 0, free_raw = 0, free_down_raw = 0, down_raw = 0;
|
||||
std::vector<uint64_t> slow_op_primary_osds, slow_op_secondary_osds;
|
||||
parent->iterate_kvs_1(osd_stats, "/osd/stats/", [&](uint64_t stat_osd_num, json11::Json value)
|
||||
{
|
||||
osd_count++;
|
||||
@@ -153,6 +154,14 @@ resume_2:
|
||||
if (peer_it != parent->cli->st_cli.peer_states.end())
|
||||
{
|
||||
osd_up++;
|
||||
if (value["slow_ops_primary"].uint64_value() > 0)
|
||||
{
|
||||
slow_op_primary_osds.push_back(stat_osd_num);
|
||||
}
|
||||
if (value["slow_ops_secondary"].uint64_value() > 0)
|
||||
{
|
||||
slow_op_secondary_osds.push_back(stat_osd_num);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -216,6 +225,10 @@ resume_2:
|
||||
{ "mon_master", mon_master },
|
||||
{ "osd_up", osd_up },
|
||||
{ "osd_count", osd_count },
|
||||
{ "osds_full", osds_full },
|
||||
{ "osds_nearfull", osds_nearfull },
|
||||
{ "osds_primary_slow_ops", slow_op_primary_osds },
|
||||
{ "osds_secondary_slow_ops", slow_op_secondary_osds },
|
||||
{ "total_raw", total_raw },
|
||||
{ "free_raw", free_raw },
|
||||
{ "down_raw", down_raw },
|
||||
@@ -300,6 +313,26 @@ resume_2:
|
||||
warning_str += " "+std::to_string(osds_nearfull)+
|
||||
(osds_nearfull > 1 ? " osds are almost full\n" : " osd is almost full\n");
|
||||
}
|
||||
if (slow_op_primary_osds.size() > 0)
|
||||
{
|
||||
warning_str += " "+std::to_string(slow_op_primary_osds.size());
|
||||
warning_str += (slow_op_primary_osds.size() > 1 ? " osds have" : " osd has");
|
||||
warning_str += " slow client ops: ";
|
||||
for (int i = 0; i < slow_op_primary_osds.size(); i++)
|
||||
{
|
||||
warning_str += (i > 0 ? ", " : "")+std::to_string(slow_op_primary_osds[i])+"\n";
|
||||
}
|
||||
}
|
||||
if (slow_op_secondary_osds.size() > 0)
|
||||
{
|
||||
warning_str += " "+std::to_string(slow_op_secondary_osds.size());
|
||||
warning_str += (slow_op_secondary_osds.size() > 1 ? " osds have" : " osd has");
|
||||
warning_str += " slow replication ops: ";
|
||||
for (int i = 0; i < slow_op_secondary_osds.size(); i++)
|
||||
{
|
||||
warning_str += (i > 0 ? ", " : "")+std::to_string(slow_op_secondary_osds[i])+"\n";
|
||||
}
|
||||
}
|
||||
if (warning_str != "")
|
||||
{
|
||||
warning_str = "\n warning:\n"+warning_str;
|
||||
|
||||
+10
-3
@@ -535,10 +535,12 @@ void osd_t::print_stats()
|
||||
|
||||
void osd_t::print_slow()
|
||||
{
|
||||
bool has_slow = false;
|
||||
cur_slow_op_primary = 0;
|
||||
cur_slow_op_secondary = 0;
|
||||
char alloc[1024];
|
||||
timespec now;
|
||||
clock_gettime(CLOCK_REALTIME, &now);
|
||||
// FIXME: Also track slow local blockstore ops and recovery/flush/scrub ops
|
||||
for (auto & kv: msgr.clients)
|
||||
{
|
||||
for (auto op: kv.second->received_ops)
|
||||
@@ -608,6 +610,7 @@ void osd_t::print_slow()
|
||||
op->req.hdr.opcode == OSD_OP_SEC_STABILIZE || op->req.hdr.opcode == OSD_OP_SEC_ROLLBACK ||
|
||||
op->req.hdr.opcode == OSD_OP_SEC_READ_BMP)
|
||||
{
|
||||
cur_slow_op_secondary++;
|
||||
bufprintf(" state=%d", op->bs_op ? PRIV(op->bs_op)->op_state : -1);
|
||||
int wait_for = op->bs_op ? PRIV(op->bs_op)->wait_for : 0;
|
||||
if (wait_for)
|
||||
@@ -618,15 +621,19 @@ void osd_t::print_slow()
|
||||
else if (op->req.hdr.opcode == OSD_OP_READ || op->req.hdr.opcode == OSD_OP_WRITE ||
|
||||
op->req.hdr.opcode == OSD_OP_SYNC || op->req.hdr.opcode == OSD_OP_DELETE)
|
||||
{
|
||||
cur_slow_op_primary++;
|
||||
bufprintf(" state=%d", !op->op_data ? -1 : op->op_data->st);
|
||||
}
|
||||
else
|
||||
{
|
||||
cur_slow_op_primary++;
|
||||
}
|
||||
#undef bufprintf
|
||||
printf("%s\n", alloc);
|
||||
has_slow = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (has_slow && bs)
|
||||
if ((cur_slow_op_primary+cur_slow_op_secondary) > 0 && bs)
|
||||
{
|
||||
bs->dump_diagnostics();
|
||||
}
|
||||
|
||||
@@ -151,6 +151,8 @@ class osd_t
|
||||
bool etcd_reporting_pg_state = false;
|
||||
bool etcd_reporting_stats = false;
|
||||
int print_stats_timer_id = -1, slow_log_timer_id = -1;
|
||||
uint64_t cur_slow_op_primary = 0;
|
||||
uint64_t cur_slow_op_secondary = 0;
|
||||
|
||||
// peers and PGs
|
||||
|
||||
|
||||
@@ -201,6 +201,14 @@ json11::Json osd_t::get_statistics()
|
||||
st["immediate_commit"] = immediate_commit == IMMEDIATE_ALL ? "all" : (immediate_commit == IMMEDIATE_SMALL ? "small" : "none");
|
||||
st["host"] = self_state["host"];
|
||||
st["version"] = VITASTOR_VERSION;
|
||||
if (cur_slow_op_primary > 0)
|
||||
{
|
||||
st["slow_ops_primary"] = cur_slow_op_primary;
|
||||
}
|
||||
if (cur_slow_op_secondary > 0)
|
||||
{
|
||||
st["slow_ops_secondary"] = cur_slow_op_secondary;
|
||||
}
|
||||
json11::Json::object op_stats, subop_stats;
|
||||
for (int i = OSD_OP_MIN; i <= OSD_OP_MAX; i++)
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user