The memory is measured after the agent reaches its control plane
Measuring it in the startup scan held every agent half a second or more before registering, which on a shared CI runner was past the failover tests' wait. Now it runs once a process, in the background, the first time it is asked for, and Heartbeat.mem_bandwidth_gbs carries it when known; the control plane keeps the last figure and a heartbeat without one leaves it. The agent's tests do not measure. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
84444e71c8
commit
e70d6caa2f
6 files changed
+83
-8
No files matched your search
@@ -2953,8 +2953,12 @@ type Heartbeat struct {
|
||||
// is not handed out. Empty from an agent that does not measure it, or from
|
||||
// one that could not this time.
|
||||
GpuForeignMemoryMb []int32 `protobuf:"varint,19,rep,packed,name=gpu_foreign_memory_mb,json=gpuForeignMemoryMb,proto3" json:"gpu_foreign_memory_mb,omitempty"`
|
||||
unknownFields protoimpl.UnknownFields
|
||||
sizeCache protoimpl.SizeCache
|
||||
// mem_bandwidth_gbs is how fast the node's memory reads, in GB/s, once
|
||||
// the agent has measured it — in the background after it starts, so a
|
||||
// registration usually has none yet. 0 means not measured.
|
||||
MemBandwidthGbs float64 `protobuf:"fixed64,20,opt,name=mem_bandwidth_gbs,json=memBandwidthGbs,proto3" json:"mem_bandwidth_gbs,omitempty"`
|
||||
unknownFields protoimpl.UnknownFields
|
||||
sizeCache protoimpl.SizeCache
|
||||
}
|
||||
|
||||
func (x *Heartbeat) Reset() {
|
||||
@@ -3120,6 +3124,13 @@ func (x *Heartbeat) GetGpuForeignMemoryMb() []int32 {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (x *Heartbeat) GetMemBandwidthGbs() float64 {
|
||||
if x != nil {
|
||||
return x.MemBandwidthGbs
|
||||
}
|
||||
return 0
|
||||
}
|
||||
|
||||
// Provision is the software a node should have: which engines, at which
|
||||
// versions. Nothing more.
|
||||
//
|
||||
@@ -5382,7 +5393,7 @@ const file_llmgw_v1_agent_proto_rawDesc = "" +
|
||||
"\x06status\x18\x03 \x01(\tR\x06status\x12!\n" +
|
||||
"\fcluster_uuid\x18\x04 \x01(\tR\vclusterUuid\x12\x1b\n" +
|
||||
"\tclique_id\x18\x05 \x01(\tR\bcliqueId\x12\x1c\n" +
|
||||
"\tbandwidth\x18\x06 \x01(\tR\tbandwidth\"\xa9\a\n" +
|
||||
"\tbandwidth\x18\x06 \x01(\tR\tbandwidth\"\xd5\a\n" +
|
||||
"\tHeartbeat\x12\x17\n" +
|
||||
"\anode_id\x18\x01 \x01(\tR\x06nodeId\x12+\n" +
|
||||
"\x12gpu_memory_used_mb\x18\x02 \x03(\x05R\x0fgpuMemoryUsedMb\x12!\n" +
|
||||
@@ -5404,7 +5415,8 @@ const file_llmgw_v1_agent_proto_rawDesc = "" +
|
||||
"gpu_fabric\x18\x10 \x03(\v2\x18.llmgw.v1.GPUFabricStateR\tgpuFabric\x12\"\n" +
|
||||
"\x04imex\x18\x11 \x01(\v2\x0e.llmgw.v1.IMEXR\x04imex\x12\x1b\n" +
|
||||
"\tcpu_count\x18\x12 \x01(\x05R\bcpuCount\x121\n" +
|
||||
"\x15gpu_foreign_memory_mb\x18\x13 \x03(\x05R\x12gpuForeignMemoryMb\x1aA\n" +
|
||||
"\x15gpu_foreign_memory_mb\x18\x13 \x03(\x05R\x12gpuForeignMemoryMb\x12*\n" +
|
||||
"\x11mem_bandwidth_gbs\x18\x14 \x01(\x01R\x0fmemBandwidthGbs\x1aA\n" +
|
||||
"\x13EngineVersionsEntry\x12\x10\n" +
|
||||
"\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n" +
|
||||
"\x05value\x18\x02 \x01(\tR\x05value:\x028\x01\";\n" +
|
||||
|
||||
@@ -591,6 +591,11 @@ message Heartbeat {
|
||||
// is not handed out. Empty from an agent that does not measure it, or from
|
||||
// one that could not this time.
|
||||
repeated int32 gpu_foreign_memory_mb = 19;
|
||||
|
||||
// mem_bandwidth_gbs is how fast the node's memory reads, in GB/s, once
|
||||
// the agent has measured it — in the background after it starts, so a
|
||||
// registration usually has none yet. 0 means not measured.
|
||||
double mem_bandwidth_gbs = 20;
|
||||
}
|
||||
|
||||
// Provision is the software a node should have: which engines, at which
|
||||
|
||||
+29
-3
@@ -514,14 +514,13 @@ func (a *Agent) scan(ctx context.Context) error {
|
||||
inv, err := discovery.Discover(ctx, opts, a.log)
|
||||
host := discovery.DiscoverHost()
|
||||
host.MinComputeCapability = discovery.MinComputeCapability(inv.GPUs)
|
||||
host.MemBandwidthGBs = discovery.MeasureMemoryBandwidth()
|
||||
host.MemBandwidthGBs = a.memBandwidth()
|
||||
a.mu.Lock()
|
||||
a.inv = inv
|
||||
a.prov.Host = host
|
||||
a.mu.Unlock()
|
||||
a.log.Info("this node", "os", host.OSID+" "+host.OSVersion, "arch", host.Arch,
|
||||
"cpu_flags", host.CPUFlags, "nvidia_driver", host.NVIDIADriver,
|
||||
"memory_gbs", math.Round(host.MemBandwidthGBs*10)/10)
|
||||
"cpu_flags", host.CPUFlags, "nvidia_driver", host.NVIDIADriver)
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -670,6 +669,7 @@ func (a *Agent) heartbeat() *llmgwv1.AgentMessage {
|
||||
// without anybody restarting anything.
|
||||
hb.MemoryTotalMb = int64(discovery.MemoryTotalMB())
|
||||
hb.CpuCount = int32(runtime.NumCPU())
|
||||
hb.MemBandwidthGbs = a.memBandwidth()
|
||||
|
||||
a.reprobeEngines()
|
||||
a.mu.Lock()
|
||||
@@ -1543,3 +1543,29 @@ func (a *Agent) reportCompute(ctx context.Context, out chan<- *llmgwv1.AgentMess
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// memBandwidth is the node's memory read rate in GB/s, 0 until measured.
|
||||
// Measured once a process, in the background, the first time it is asked
|
||||
// for: it reads half a gigabyte, which must not hold up an agent reaching
|
||||
// its control plane, and the heartbeat carries it when it is known. Once a
|
||||
// process rather than an agent, so tests running many agents in one read it
|
||||
// once.
|
||||
func (a *Agent) memBandwidth() float64 {
|
||||
bwOnce.Do(func() {
|
||||
go func() {
|
||||
bw := measureBandwidth()
|
||||
bwBits.Store(math.Float64bits(bw))
|
||||
if bw > 0 {
|
||||
a.log.Info("this node's memory", "read_gbs", math.Round(bw*10)/10)
|
||||
}
|
||||
}()
|
||||
})
|
||||
return math.Float64frombits(bwBits.Load())
|
||||
}
|
||||
|
||||
var (
|
||||
bwOnce sync.Once
|
||||
bwBits atomic.Uint64
|
||||
// measureBandwidth is replaced in tests, which have no use for it.
|
||||
measureBandwidth = discovery.MeasureMemoryBandwidth
|
||||
)
|
||||
@@ -0,0 +1,13 @@
|
||||
package agent
|
||||
|
||||
import (
|
||||
"os"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestMain(m *testing.M) {
|
||||
// Half a gigabyte read per test binary, and contending with the tests
|
||||
// for the CPUs: these never look at the figure.
|
||||
measureBandwidth = func() float64 { return 0 }
|
||||
os.Exit(m.Run())
|
||||
}
|
||||
@@ -325,3 +325,18 @@ func TestAProblemOnANodeWithoutGPUsDoesNotPanic(t *testing.T) {
|
||||
t.Fatal("the node is gone")
|
||||
}
|
||||
}
|
||||
|
||||
func TestAHeartbeatCarriesTheMemorysMeasuredSpeed(t *testing.T) {
|
||||
// Measured in the background after the agent starts, so it arrives in a
|
||||
// heartbeat, not in the registration.
|
||||
s := newTestService()
|
||||
nodeWith(s, inventory.Node{ID: "n1", State: inventory.Ready, MemoryTotalMB: 7 * 1024})
|
||||
s.applyHeartbeat("n1", &llmgwv1.Heartbeat{NodeId: "n1", MemBandwidthGbs: 41.9})
|
||||
if n, _ := s.inv.Get("n1"); n.Host.MemBandwidthGBs != 41.9 {
|
||||
t.Errorf("bandwidth %v, want 41.9", n.Host.MemBandwidthGBs)
|
||||
}
|
||||
s.applyHeartbeat("n1", &llmgwv1.Heartbeat{NodeId: "n1"})
|
||||
if n, _ := s.inv.Get("n1"); n.Host.MemBandwidthGBs != 41.9 {
|
||||
t.Errorf("a heartbeat without it erased it: %v", n.Host.MemBandwidthGBs)
|
||||
}
|
||||
}
|
||||
@@ -547,10 +547,11 @@ func (s *Service) applyHeartbeat(nodeID string, hb *llmgwv1.Heartbeat) {
|
||||
storage := hb.GetStorage()
|
||||
memMB := int(hb.GetMemoryTotalMb())
|
||||
cpus := int(hb.GetCpuCount())
|
||||
bw := hb.GetMemBandwidthGbs()
|
||||
if len(used) == 0 && len(foreign) == 0 && len(problems) == 0 && len(storage) == 0 &&
|
||||
!hb.GetWeightsChanged() && memMB == 0 && cpus == 0 && !hb.GetEnginesChanged() &&
|
||||
!hb.GetProvisionChanged() && hb.GetLoad() == nil && len(hb.GetIbPorts()) == 0 &&
|
||||
!hb.GetFabricsChanged() && len(hb.GetGpuFabric()) == 0 && hb.GetImex() == nil {
|
||||
!hb.GetFabricsChanged() && len(hb.GetGpuFabric()) == 0 && hb.GetImex() == nil && bw == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
@@ -622,6 +623,9 @@ func (s *Service) applyHeartbeat(nodeID string, hb *llmgwv1.Heartbeat) {
|
||||
"from_mb", n.MemoryTotalMB, "to_mb", memMB)
|
||||
n.MemoryTotalMB = memMB
|
||||
}
|
||||
if bw > 0 {
|
||||
n.Host.MemBandwidthGBs = bw
|
||||
}
|
||||
if cpus > 0 && cpus != n.CPUCount {
|
||||
if n.CPUCount > 0 {
|
||||
s.log.Info("node CPUs changed", "node", nodeID, "from", n.CPUCount, "to", cpus)
|
||||
|
||||
Reference in new issue
Block a user