Ilker ManapandClaude Opus 5.5
0fd55a862b
Discovery reports a card in MIG mode as its instances instead of the whole card, on both paths: nvidia-smi (-L names them, -q -x gives their memory, ids and processes) and NVML (GetMigMode, GetMaxMigDeviceCount, GetMigDeviceHandleByIndex, behind an interface so it is tested with a fake). Each instance has its MIG UUID, its own memory, and a class from the card's and the profile: a100-80g-mig-3g.40gb. Placement numbers instances 1000 + 100 x card + instance and every view shows them as card/migN. A replica on MIG runs on exactly one instance: a process opens one MIG device and instances have no NVLink between them, so tp, pp, gpus or nodes above one on a MIG class are refused in catalog validation and again in placement, and the planner offers one instance or none. The agent gives the engine CUDA_VISIBLE_DEVICES=MIG-<uuid> (no Vulkan device variable on MIG). Memory and processes are per instance; heat, power and wear the card's; utilisation is left out rather than reported as zero. A card in MIG mode with nothing carved stays out of placement with the reason, and llmgw doctor reports each card's mode and instances and warns of the states in which nothing can run. ctl nodes, ctl status, the console and the plan count devices by class. docs/install.md has a MIG section. Written against fakes of nvidia-smi and NVML output; not yet run on MIG hardware. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
81 lines
3.1 KiB
Go
81 lines
3.1 KiB
Go
package doctor
|
|
|
|
import (
|
|
"strings"
|
|
"testing"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/agent/discovery"
|
|
)
|
|
|
|
// migFacts is the healthy node with card 0 in MIG mode, as given.
|
|
func migFacts(card discovery.MIGCard) Facts {
|
|
f := healthy()
|
|
f.MIG = []discovery.MIGCard{card}
|
|
return f
|
|
}
|
|
|
|
func TestTheDoctorListsACardsMIGInstances(t *testing.T) {
|
|
fs := Evaluate(migFacts(discovery.MIGCard{Index: 0, Name: "NVIDIA A100-SXM4-80GB", Enabled: true, PendingEnabled: true,
|
|
Instances: []discovery.MIGListed{{Device: 0, Profile: "3g.40gb", UUID: "MIG-aaa"}, {Device: 1, Profile: "3g.40gb", UUID: "MIG-bbb"}},
|
|
GPUInstances: []discovery.MIGInstance{{GPU: 0, Profile: "3g.40gb", GPUInstance: 1, ComputeInstance: -1},
|
|
{GPU: 0, Profile: "3g.40gb", GPUInstance: 2, ComputeInstance: -1}},
|
|
ComputeInstances: []discovery.MIGInstance{{GPU: 0, Profile: "3g.40gb", GPUInstance: 1},
|
|
{GPU: 0, Profile: "3g.40gb", GPUInstance: 2}},
|
|
}))
|
|
has(t, fs, OK, "GPU 0 (NVIDIA A100-SXM4-80GB) is in MIG mode with 2 instance(s)")
|
|
has(t, fs, OK, "1: 3g.40gb MIG-bbb")
|
|
for _, f := range fs {
|
|
if f.Area == "mig" && f.Level != OK {
|
|
t.Errorf("a card with its instances made was warned of: %+v", f)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestTheDoctorWarnsOfMIGEnabledWithNoInstances(t *testing.T) {
|
|
// The state a card is left in by nvidia-smi -mig 1 alone: in MIG mode,
|
|
// so CUDA will not open it whole, and nothing carved to open instead.
|
|
fs := Evaluate(migFacts(discovery.MIGCard{Index: 0, Name: "NVIDIA A100-SXM4-80GB", Enabled: true, PendingEnabled: true}))
|
|
has(t, fs, Warn, "is in MIG mode with no instances created")
|
|
for _, f := range fs {
|
|
if f.Area == "mig" && f.Level == Warn && !strings.Contains(f.Fix, "nvidia-smi mig -i 0 -cgi") {
|
|
t.Errorf("the fix does not say how to create them: %q", f.Fix)
|
|
}
|
|
}
|
|
|
|
// GPU instances with no compute instance in them are not devices either.
|
|
fs = Evaluate(migFacts(discovery.MIGCard{Index: 0, Name: "A100", Enabled: true, PendingEnabled: true,
|
|
GPUInstances: []discovery.MIGInstance{{GPU: 0, Profile: "7g.80gb", GPUInstance: 0, ComputeInstance: -1}}}))
|
|
has(t, fs, Warn, "GPU instances 0 (7g.80gb) but no compute instances")
|
|
|
|
// A mode change waiting for a reset.
|
|
fs = Evaluate(migFacts(discovery.MIGCard{Index: 0, Name: "A100", Enabled: false, PendingEnabled: true}))
|
|
has(t, fs, Warn, "MIG turning on at its next reset")
|
|
}
|
|
|
|
func TestACardWithMIGOffIsNotMentioned(t *testing.T) {
|
|
fs := Evaluate(migFacts(discovery.MIGCard{Index: 0, Name: "A100"}))
|
|
for _, f := range fs {
|
|
if f.Area == "mig" {
|
|
t.Errorf("a card with MIG off was reported: %+v", f)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestNVLinkIsJudgedBetweenWholeCardsOnly(t *testing.T) {
|
|
// Every card of the node in MIG mode: the instances have no NVLink, and
|
|
// that is not a node "without NVLink" to warn about.
|
|
f := healthy()
|
|
f.GPUs = nil
|
|
for card := range 2 {
|
|
for dev := range 2 {
|
|
f.GPUs = append(f.GPUs, discovery.GPU{Index: discovery.MIGIndex(card, dev), Name: "A100 MIG 3g.40gb",
|
|
MIG: &discovery.MIGDevice{ParentIndex: card, Device: dev, Profile: "3g.40gb"}})
|
|
}
|
|
}
|
|
for _, x := range Evaluate(f) {
|
|
if x.Area == "nvlink" && x.Level != OK {
|
|
t.Errorf("MIG instances were judged for NVLink: %+v", x)
|
|
}
|
|
}
|
|
}
|