PCIe/CXL Deep Dive · All levels
Host-Device Coherency Contracts: Interview Drills
Interview Drills for Host-Device Coherency Contracts.
Interview drills
Interview Drills for Host-Device Coherency Contracts focuses on Coherency miss rate, snoop stall cycles, and fence-to-visible latency. The purpose is to turn memory observations into mechanism-backed actions with explicit owners and release-safe validation.
PROMPT
You observe Coherency miss rate, snoop stall cycles, and fence-to-visible latency on Host-Device Coherency Contracts. Explain root cause and release decision.
STRONG ANSWER
1. Defines failing traffic context and first transition loss.
2. Explains mechanism: Host CPUs and CXL devices share a coherency domain defined by snoop filters, directories, and invalidation paths. Contracts specify which agent owns lines, how evictions propagate, and when stores become globally visible.
3. Requests proving artifact: Coherency contract doc, snoop latency histogram, and fence benchmark
4. Proposes bounded fix + owner + rollback-safe validation.
WEAK ANSWER
Gives generic PCIe tuning ideas without command evidence, owner accountability, or risk controls.Interview evidence matrix
PCIe/CXL EVIDENCE MATRIX - Host-Device Coherency Contracts
+-------------------------------+--------------------------------+--------------------------------+---------------------------+
| Evidence | Tells you | Does not prove | Next action |
+-------------------------------+--------------------------------+--------------------------------+---------------------------+
| TLP type mix + credit stall counters | protocol-layer stall cost | link integrity and replay behavior | inspect training margins |
| queue age + class breakdown | fairness and starvation risk | command legality details | parse command timeline |
| LTSSM timeline + ordered set progression | timing-window pressure | root cause by itself | correlate with topology map|
| eye / Vref / skew snapshots | PHY margin and drift behavior | controller policy quality | pair with schedule logs |
| CE/UE + scrub telemetry | reliability trajectory | immediate perf bottleneck only | map to hotspot apcieesses |
+-------------------------------+--------------------------------+--------------------------------+---------------------------+PCIe/CXL deep dive
Memory expansion and coherency require HDM windows, ownership discipline, and NUMA-aware software policies.
Concept diagram
COHERENCY + HDM
CPU caches <-> CXL.cache <-> device memory (CXL.mem/HDM)Metric graph
EXPANSION BOTTLENECK SHARE
remote latency ██████
ownership retry ████
interleave skew ███Reports and artifacts
HDM decode table
ownership transition trace
NUMA distance profile
RAS region policy
Mini case study
Fabric-attached memory increased capacity but p99 regressed until page placement respected NUMA distance.
Debug branches
Map HDM windows and interleave groups
Run ownership litmus under contention
Correlate RAS events with region offline policy
Senior review question
Ask: which latency, bandwidth, and reliability evidence proves this PCIe/CXL topic is closed under real traffic?
Key takeaways
Always tie controller and PHY counter shifts to application latency and throughput outcomes.
Lock firmware timing profile, thermal condition, and DIMM state before comparing PCIe/CXL captures.
Common pitfalls
Chasing peak bandwidth while ignoring p99 latency and fairness tails.
Changing timing guardbands without separating SI noise from scheduling issues.
Declaring closure without reliability gates, fault injection, and regression replay.
Interview answer expansion
Strong interview answers for Host-Device Coherency Contracts start with workload framing and metric framing, then explain mechanism plainly: Host CPUs and CXL devices share a coherency domain defined by snoop filters, directories, and invalidation paths. Contracts specify which agent owns lines, how evictions propagate, and when stores become globally visible.
Then propose a measurement plan: TLP routing, credit dynamics, turnaround cost, RAS interference, and PHY margin where relevant.
Finally, present one bounded fix plus regression risk. PCIe/CXL interviews reward explicit tradeoff ownership, not generic tuning slogans.