NVMe Self-Study Bank: Index · Q1–328
read more
NVMe Self-Study Bank: Index · Q1–328
NVMe · Q1–328
NVM Express Base 2.4NVM Command Set 1.3NVMe over PCIe Transport 1.4
NVMe Base 2.4 Self-Study Question Bank
Questions 1–328 in 27 volumes: from controller enable, queues and commands to capability discovery and configuration. Learn both the mechanisms and how to judge observations against the specification.
Controller initialization and disable
Understand controller state transitions before commands. Discovering capabilities is not enabling; setting EN is not readiness; RDY=1 need not establish readiness of every media operation. This volume connects timing, state and permitted actions.
Admin and I/O queues
Queue memory, allocated queue counts and successfully created queues are distinct. Learn SQ/CQ dependencies before size, identifiers, deletion and reset so memory can be reclaimed at the right time.
- SQ
- Submission Queue
- CQ
- Completion Queue
Doorbells, full queues and wrap-around
Doorbells communicate pointer positions; phase tells the host whether a CQ slot belongs to the next completion generation. Together they distinguish wrap-around from an invalid movement and new completions from stale ones.
- CQ
- Completion Queue
Commands, completions and processing order
Follow submission, consumption, processing, completion and host reclamation to learn what each field proves. Ordering, arbitration, fairness and interrupts answer different questions; completion order alone cannot establish them all.
Identify and capability discovery
Treat Identify as several distinct query interfaces. Choose the object and structure before CNS, CSI, NSID and other selectors. Separate capability, current configuration and changing lists to find real contradictions.
- CNS
- Controller or Namespace Structure, selecting Identify data
- CSI
- Command Set Identifier
- NSID
- Namespace Identifier
Get Features and Set Features
Establish scope, changeability and saveability before Set. Completion, Current readback, actual behavior and restoration after reset are separate observations; a successful CQE does not replace them.
- CQE
- Completion Queue Entry
Get Log Page and data consistency
Logs expose state, history or capability, with different lifetimes and read effects. Choose the view and scope before length, pagination, acknowledgment and consistency.
Asynchronous Event Request
AER preposts requests that complete on events. Connect requests, events, logs and acknowledgment before concurrency and rearming.
Error status and Error Information
Start with one failed command, classify it and correlate completion with supplemental records and recovery evidence.
Abort, timeout and recovery
A timeout is an observation, not a location. Follow submission through consumption before choosing abort or reset.
Format and sanitize
Format changes namespace format; sanitize removes data. Compare scope, completion and reset behavior across the operation lifecycle.
Firmware update and boot partitions
Separate download, commit and activation, then compare boot-image access and selection.
Device self-test
Establish supported tests, then distinguish progress, final results and valid failure details.
Namespace management, attachment and protection
Creation, attachment and write protection are separate states connected through a namespace lifecycle.
Reset and shutdown
Reset rebuilds an operating context while shutdown prepares stopping; compare scope, completion and retained operations.
Power, thermal and health monitoring
Power states, thermal control and health counters are related but answer different questions. Learn state and timing before warnings and workload.
Persistent Event Log and Timestamp
Retrieve a consistent PEL before interpreting variable lengths, event types and changing time bases.
Keep Alive
Optional PCIe Keep Alive detects host liveness through command-based or traffic-based timing.
HMB, CMB and PMR
- HMB
- Host Memory Buffer
- CMB
- Controller Memory Buffer
- PMR
- Persistent Memory Region
Compare location, ownership, lifetime and persistence rather than treating all memory facilities alike.
Security and Lockdown
Security commands transport protocol data; Lockdown prohibits selected operations. Separate protocol results, prohibition scope and persistence.
Multi-controller and virtualization
Separate multipath, shared storage and virtualization before combining topology, attachment, ANA and resources.
NVM sets, endurance groups and capacity
Establish ownership before interpreting layer-specific capacity and group-scoped health.
Domains, reclaim groups and media units
Distinguish ownership from FDP placement, then follow identifiers to an RU and interpret media-report limits.
- FDP
- Flexible Data Placement
PRP and SGL
- PRP
- Physical Region Page, a data-page pointer
- SGL
- Scatter Gather List
Learn memory layout through PRP boundary calculations, SGL descriptor relationships and distinct error classes.
- PRP
- Physical Region Page, a data-page pointer
- SGL
- Scatter Gather List
Interrupt configuration and completion delivery
Establish CQE posting before diagnosing routing, aggregation, masks and host consumption.
- CQE
- Completion Queue Entry
Integrated validation and evidence correlation
Apply prior mechanisms to apparent contradictions, matching identity and time before judging evidence.
Data I/O: size, persistence and integrity
This supplement develops data-I/O reasoning not previously covered in depth: request validity, completion guarantees, content verification and partial failure effects. Derive answers from concrete field values while linking back to existing feature, queue and pointer lessons.
How to use this bank
- Explain purpose, affected objects and sequence before selecting query fields.
- Answers follow the question: trace evidence for lookups, dependencies for operations and distinctions for comparisons. Events, errors and resets appear when relevant. Conditions and wait points in the flows are part of the explanation.
- Establish preconditions before judging firmware. Shall is a requirement, should a recommendation, may permission. Undefined behavior does not supply a fixed expected status.
All numerical examples are hypothetical, not hardware measurements. The scope is the three specifications as used by PCIe SSDs, excluding NVMe over Fabrics and PCIe link/packet details while retaining necessary PCIe configuration, interrupts, registers and doorbells.
All questions
- Q01 · How does a host discover version, queue limits, timeouts, doorbell stride, page sizes and command sets from CAP and VS?
- Q02 · In what order are AQA, ASQ, ACQ and CC programmed, and what happens if they are wrong?
- Q03 · How does a host judge enable completion using CC.EN, CSTS.RDY and the timeout fields?
- Q04 · How is disable completion detected, and may the host re-enable before it completes?
- Q05 · May a host submit commands or update doorbells while CSTS.RDY is zero?
- Q06 · What does CSTS.CFS mean, and how should the host recover from initialization failure or a fatal state?
- Q07 · Which ready modes exist, and how should the host handle limited readiness?
- Q08 · How do Enable, Disable, Controller Reset, NVM Subsystem Reset and Shutdown differ?
- Q09 · What must be reinitialized after Controller Reset?
- Q10 · How are the Admin Submission and Completion Queues established through AQA, ASQ and ACQ?
- Q11 · What are the size, base-address and page-alignment requirements for Admin and I/O queues?
- Q12 · How are I/O CQs and SQs created, and why must the CQ be created first?
- Q13 · How does sharing a CQ differ from giving every SQ its own CQ?
- Q14 · How does the host determine supported queue memory layouts?
- Q15 · Which statuses apply to duplicate/zero QIDs, missing CQIDs, oversized queues and invalid vectors?
- Q16 · How do Number of Queues results relate to queues that can actually be created?
- Q17 · Why must associated SQs be deleted before their CQ?
- Q18 · What happens when deleting a missing queue, a referenced CQ or an SQ with outstanding commands?
- Q19 · May the controller access deleted queue memory or post completions for its old commands?
- Q20 · What is the scope of Queue Level Reset, and how is outstanding work handled?
- Q21 · Are old I/O queues valid after Controller Reset, and what must the host do again?
- Q22 · When should the host update SQ Tail and CQ Head doorbells?
- Q23 · What happens with repeated, apparently backward, out-of-range or wrong-QID doorbells?
- Q24 · How are SQ/CQ doorbell addresses calculated from CAP.DSTRD?
- Q25 · May the host access doorbells of uncreated/deleted queues or a disabled controller?
- Q26 · How should SQ Tail and CQ Head wrap around?
- Q27 · How does the CQ phase change across wrap, and how does the host identify a new completion?
- Q28 · How does CQ Full arise, and may related SQ processing continue?
- Q29 · How does processing resume when the host releases CQ space?
- Q30 · How does the host identify completions from SQs sharing a CQ?
- Q31 · What do Opcode, CID, NSID, Data Pointer and command dwords mean?
- Q32 · How are nonzero reserved fields, illegal field combinations and unsupported opcodes handled?
- Q33 · Which statuses apply to invalid, inactive, unused and improperly broadcast NSIDs?
- Q34 · What are SQHD, SQID, CID, phase and status used for in a CQE?
- Q35 · How should Status Code Type and Status Code be decoded?
- Q36 · What do More and DNR mean, and does DNR=0 guarantee an immediate safe retry?
- Q37 · Why might a posted completion remain unprocessed by the host?
- Q38 · Must outstanding commands complete in submission order?
- Q39 · Which commands have ordering dependencies, and why is universal ordered completion unsafe to assume?
- Q40 · How do outstanding limits and CQ Full constrain further command handling?
- Q41 · How do Round Robin and Weighted Round Robin arbitration differ?
- Q42 · When do Urgent, High, Medium and Low queue priorities take effect?
- Q43 · How can arbitration be evaluated when multiple queues compete?
- Q44 · What important information is provided by Identify Controller and Identify Namespace?
- Q45 · How do active, allocated and namespace descriptor lists differ?
- Q46 · What are Controller Lists, the UUID List and I/O Command Set Identify data used for?
- Q47 · Which Identify structures describe NVM Sets, Endurance Groups, Domains and Secondary Controllers?
- Q48 · How should unsupported or invalid CNS, CSI, NSID and UUID Index values be handled?
- Q49 · How are SN, MN, FR, MDTS and optional Admin capability fields interpreted?
- Q50 · How can advertised Identify support be cross-checked against commands and the Commands Supported and Effects Log?
- Q51 · Which Identify data and lists change after namespace creation, deletion, attachment, detachment or format?
- Q52 · Which Identify data may change after firmware activation, reset or power cycling?
- Q53 · How should inconsistencies among Identify, features, logs and command behavior be investigated?
- Q54 · What do Current, Default, Saved and Supported Capabilities mean?
- Q55 · How does Set Features.Save affect values after reset and power cycling?
- Q56 · Which errors apply to unsupported features, invalid values and unsupported Save?
- Q57 · How does the host determine whether a feature requires NSID?
- Q58 · How are Arbitration, Number of Queues and I/O Command Set Profile configured and checked?
- Q59 · How are interrupt coalescing and vector configuration set and verified?
- Q60 · What do Volatile Write Cache and Write Atomicity Normal control?
- Q61 · How does Asynchronous Event Configuration select reported events?
- Q62 · How do Power Management, APST and Host Controlled Thermal Management differ?
- Q63 · How are Timestamp, Keep Alive Timer and Host Memory Buffer configured and verified?
- Q64 · What do Host Behavior Support, Error Recovery and Read Recovery Level do?
- Q65 · How is namespace write protection configured, and which modes survive reset or power cycling?
- Q66 · Why read Get Features after a successful Set Features?
- Q67 · How should features change after activation, namespace deletion, reset and power cycling?
- Q68 · How should supported-feature claims be checked when Get, Set and behavior appear inconsistent?
- Q69 · What does Supported Log Pages provide, and how should support be checked before reading another log?
- Q70 · What do Error Information and SMART/Health Information record?
- Q71 · What do Firmware Slot, Changed Namespace and Commands Supported and Effects logs establish?
- Q72 · When should Device Self-test, Persistent Event and Sanitize Status logs be used?
- Q73 · What do Endurance Group, Predictable Latency, Lockdown, Boot Partition and Media Unit Status logs contain?
- Q74 · How should NSID and other selectors follow a log’s scope?
- Q75 · How are large logs read in chunks, including offsets, lengths, overlaps and gaps?
- Q76 · What are LSI, UUID Index and Retain Asynchronous Event used for?
- Q77 · How can a host detect inconsistent log chunks when content changes?
- Q78 · How are old records handled when Error Information or PEL reaches capacity?
- Q79 · Which log data survives controller reset, subsystem reset or power cycling?
- Q80 · How should advertised log/command support be checked against actual behavior?
- Q81 · How does Commands Supported and Effects describe opcode support and impact?
- Q82 · Why post Asynchronous Event Requests before events, and why do they remain outstanding?
- Q83 · How does AER completion identify the event and its log?
- Q84 · Why read the associated log and post another AER after an event?
- Q85 · What happens when outstanding AERs exceed the controller limit?
- Q86 · How are events handled when no AER is outstanding?
- Q87 · How can concurrent identical or different events be combined and reported?
- Q88 · How does Asynchronous Event Configuration enable or disable notifications?
- Q89 · What notification conditions apply to SMART, namespaces, firmware, telemetry, sanitize, self-test and PEL?
- Q90 · How does reading a log clear or retain an event?
- Q91 · Can AER be aborted, and what happens to pending requests during reset?
- Q92 · How should an AER be investigated when the associated log lacks expected information?
- Q93 · How do opcode, field, CID and sequence errors differ?
- Q94 · How are namespace, log, queue, size and vector errors located?
- Q95 · Why must firmware, format and capacity errors be tied to their commands?
- Q96 · How do transfer, internal and namespace-readiness errors differ?
- Q97 · How do power loss, abort, SQ deletion and fused failures appear?
- Q98 · How do status, More, DNR and CRD guide recovery?
- Q99 · Which errors require Error Information?
- Q100 · How is an error entry correlated with its command and parameter?
- Q101 · Must an error entry match every CQE status bit?
- Q102 · How do concurrent errors, log capacity and Error Count interact?
- Q103 · Is a non-success CQE without a new error entry always nonconforming?
- Q104 · Can other commands continue after an ordinary command error?
- Q105 · When may serious failures set CFS, and how should the host interpret it?
- Q106 · How are CQEs, Error Information and persistent events correlated?
- Q107 · How does Abort identify its target with SQID and CID?
- Q108 · What happens when Abort targets a completed or missing command?
- Q109 · How does ACL apply to repeated and concurrent Abort commands?
- Q110 · Does successful Abort prove that the target never executed?
- Q111 · Can a target complete normally if Abort did not immediately cancel it?
- Q112 · How does the host handle racing Abort and target completions?
- Q113 · Must every timeout follow Abort, queue reset, then controller reset?
- Q114 · How should the host recover when Abort itself times out?
- Q115 · How are old commands, completions and queues handled after reset?
- Q116 · How do command, ready and long-operation timeouts differ?
- Q117 · How is a timeout located along submission, execution and completion?
- Q118 · How is support for Format, Sanitize and Sanitize Namespace discovered?
- Q119 · How do Format, secure erase and the two sanitize targets differ?
- Q120 · How are Format data format, metadata, PI and SES selected?
- Q121 · How are invalid Format parameters and states reported?
- Q122 · Which Admin operations can continue during Format?
- Q123 · How is interrupted Format assessed after reset or power loss?
- Q124 · Which namespace data must be refreshed after Format?
- Q125 · How are Format failures checked using CQE, Error Log and PEL?
- Q126 · How does SANICAP advertise sanitize methods?
- Q127 · How do NDAS, overwrite pattern, passes and inversion work?
- Q128 · How are progress, status, state and erased-data flags interpreted together?
- Q129 · Which commands are permitted during subsystem sanitization?
- Q130 · Does sanitization continue across reset or power loss?
- Q131 · How do success, failure and failure mode differ in the log?
- Q132 · What does Exit Failure Mode accomplish?
- Q133 · When are sanitize AERs and persistent events generated?
- Q134 · How is namespace sanitization targeted and isolated?
- Q135 · How are invalid or unsupported namespace sanitize requests handled?
- Q136 · Where are firmware slot count, protection and usage reported?
- Q137 · How do OFST and NUMD describe firmware download pieces?
- Q138 · How are overlap, gaps, order and invalid images handled?
- Q139 · How are Firmware Commit slot and action selected?
- Q140 · How do immediate and reset-triggered activation differ?
- Q141 · When is Firmware Activation Starting reported?
- Q142 · How are firmware-update interruptions recovered?
- Q143 · How does firmware-load failure recovery work?
- Q144 · How is completed activation verified?
- Q145 · What should persist or be rediscovered after activation?
- Q146 · How are boot partition support, state and active ID discovered?
- Q147 · How are boot images downloaded, committed and selected?
- Q148 · How do boot and controller-firmware updates differ?
- Q149 · How are self-test support and coverage established?
- Q150 · How do short and extended self-tests differ?
- Q151 · What happens when self-test is restarted or cancelled?
- Q152 · How are current operation and completion percentage interpreted?
- Q153 · How are self-test outcomes and interruption effects interpreted?
- Q154 · Does every self-test completion generate an AER?
- Q155 · When are segment, diagnostic and failing-LBA fields valid?
- Q156 · How are the 20 self-test results ordered and replaced?
- Q157 · How are namespace management and attachment supported?
- Q158 · How are size, capacity, format and thin provisioning selected?
- Q159 · How are namespace-creation resource and parameter errors reported?
- Q160 · How does creation change the allocated namespace list?
- Q161 · How are controllers selected for attachment changes?
- Q162 · How are active and controller lists cross-checked?
- Q163 · How are attachment relationship errors reported?
- Q164 · What happens to outstanding commands during detach?
- Q165 · How are commands handled after namespace detach?
- Q166 · How are nonexistent or attached namespace deletions handled?
- Q167 · Which events and logs follow namespace changes?
- Q168 · How does changed-namespace overflow work?
- Q169 · Do namespace configuration and attachment survive resets?
- Q170 · How do private and shared namespaces differ?
- Q171 · How do write-protection modes and entry controls differ?
- Q172 · How does write protection persist across reset and power?
- Q173 · How does protection affect format, sanitize and namespace management?
- Q174 · How do controller, subsystem and queue resets differ?
- Q175 · How do PCIe reset types affect NVMe?
- Q176 · How do reset outcomes depend on ongoing activity?
- Q177 · How does RDY behave during reset?
- Q178 · What needs rebuilding after reset?
- Q179 · How are old outstanding commands handled after reset?
- Q180 · How is state revalidated after reset?
- Q181 · What if reset times out or CFS remains?
- Q182 · How is normal shutdown requested?
- Q183 · When is power removal appropriate?
- Q184 · How do normal, abrupt and unannounced loss differ?
- Q185 · What may remain outstanding during shutdown?
- Q186 · How do shutdown modes affect the former Unsafe Shutdowns counter?
- Q187 · Why inspect health, errors and persistent events after loss?
- Q188 · What does a Power State Descriptor tell the host?
- Q189 · How do operational and non-operational power states differ?
- Q190 · How do entry and exit latency affect command waits?
- Q191 · How is APST configured, triggered and disabled?
- Q192 · How should an apparent EXLAT violation be evaluated?
- Q193 · How should HCTM TMT1 and TMT2 be configured?
- Q194 · When does thermal management start and stop?
- Q195 · How are power and thermal settings restored?
- Q196 · What do SMART Critical Warning bits mean?
- Q197 · How are spare capacity and percentage used interpreted?
- Q198 · How do SMART workload and uptime counters accumulate?
- Q199 · How do unexpected power-loss and error counters accumulate?
- Q200 · How are warning and critical temperature times counted?
- Q201 · How do sensor temperatures relate to Composite Temperature?
- Q202 · Which health changes generate asynchronous events?
- Q203 · How is SMART data scope determined?
- Q204 · How are SMART, operations, errors and PEL cross-checked?
- Q205 · How is PEL and individual event support established?
- Q206 · How is a PEL context established, read and released?
- Q207 · What happens for absent or duplicate PEL contexts?
- Q208 · How are key PEL event classes recorded?
- Q209 · Which persistent events describe namespace, format and sanitize operations?
- Q210 · How are events removed when PEL reaches its limits?
- Q211 · Does a new PEL event require an asynchronous notification?
- Q212 · What persists in PEL across resets and power cycles?
- Q213 · How are PEL headers, lengths and ordering validated?
- Q214 · How is Timestamp set and verified?
- Q215 · How do Timestamp counting, wrap-around, Origin and SYNC work?
- Q216 · How are Timestamp changes and reset outcomes interpreted?
- Q217 · How does a PCIe host discover Keep Alive support?
- Q218 · How is the timer configured, adjusted and disabled?
- Q219 · How does the host maintain liveness before expiry?
- Q220 · What cleanup is required after Keep Alive Timeout?
- Q221 · Must Keep Alive be reconfigured after reset?
- Q222 · How do command-based and traffic-based Keep Alive differ?
- Q223 · What problems do HMB, CMB and PMR solve?
- Q224 · How are HMB size and descriptor lists configured?
- Q225 · How are malformed HMB allocations handled?
- Q226 · How is HMB enabled, disabled and returned after reset?
- Q227 · What happens if the host prematurely reclaims HMB?
- Q228 · How are CMB location, size and uses discovered?
- Q229 · Which queues, buffers and lists may reside in CMB?
- Q230 · How are out-of-range or unsupported CMB uses handled?
- Q231 · Do CMB configuration and contents survive reset?
- Q232 · How is PMR discovered, enabled and made ready?
- Q233 · What happens for not-ready or unhealthy PMR accesses?
- Q234 · How is PMR safely disabled?
- Q235 · How do resets and power cycles affect PMR state and data?
- Q236 · How do host memory, HMB, CMB and PMR lifetimes compare?
- Q237 · How are Security Send/Receive and protocols discovered?
- Q238 · How are invalid security selectors or lengths handled?
- Q239 · How are security transfer and protocol failures distinguished?
- Q240 · How can security state affect other Admin commands?
- Q241 · Does security state survive reset or power cycle?
- Q242 · How does Lockdown restrict commands or features?
- Q243 · What response is required for a prohibited command or feature?
- Q244 · How are normal and enhanced Lockdown logs interpreted?
- Q245 · Does Lockdown survive resets and power cycles?
- Q246 · How are subsystems, primary and secondary controllers related?
- Q247 · How are private and shared namespaces attached?
- Q248 · How is a namespace’s attached-controller list retrieved?
- Q249 · Can other paths continue during one controller’s reset?
- Q250 · Which controllers are affected by subsystem reset?
- Q251 · How are namespace changes reported through other controllers?
- Q252 · How do asymmetric behavior and ANA guide path selection?
- Q253 · How does a secondary transition Online or Offline?
- Q254 · How are virtualization resources assigned and released?
- Q255 · How are virtualization resources restored after reset and power cycle?
- Q256 · How are NVM sets, endurance groups and namespaces related?
- Q257 · How are sets and groups discovered through Identify?
- Q258 · How is a namespace created in a selected set or group?
- Q259 · What happens when a set or group identifier does not exist?
- Q260 · What does the Endurance Group Information Log report?
- Q261 · How are group health warnings and events updated?
- Q262 · How are total and unallocated capacities determined?
- Q263 · How do namespace creation and deletion affect free capacity?
- Q264 · How does Capacity Management allocate and release groups and sets?
- Q265 · What happens when capacity or identifiers are exhausted?
- Q266 · Which views change after capacity reconfiguration?
- Q267 · How does storage configuration persist across reset and power cycle?
- Q268 · Do domains, sets, groups, media units and namespaces form one hierarchy?
- Q269 · How are domains and resource ownership discovered?
- Q270 · What are a reclaim group, reclaim unit and reclaim-unit handle?
- Q271 · How does a namespace select an RU through a placement handle?
- Q272 · What does Media Unit Status report and how are descriptors traversed?
- Q273 · Can Media Unit Status directly establish namespace unavailability?
- Q274 · Which notices and records can accompany media changes?
- Q275 · How are entity scopes distinguished without confusing identifiers?
- Q276 · How does PRP1 describe the first data page?
- Q277 · When is PRP2 a second-page address or a list pointer?
- Q278 · How are multiple PRP-list pages chained?
- Q279 · What alignment rules apply to PRPs and lists?
- Q280 · Do zero, invalid or broken-chain PRPs have one universal error?
- Q281 · How do SGL data, segment and last-segment descriptors work?
- Q282 · How are SGL address, length, count and type errors distinguished?
- Q283 · How do Identify SGL capabilities constrain usage?
- Q284 · How do pointer-format errors differ from Data Transfer Error?
- Q285 · How are pointer errors correlated with completion and Error Information?
- Q286 · How does a CQ select an interrupt vector?
- Q287 · How do shared and dedicated CQ vectors differ?
- Q288 · How do coalescing threshold and time work?
- Q289 · How is interrupt coalescing disabled?
- Q290 · Does FID 09h mask interrupts, and where are actual masks configured?
- Q291 · Can completions be posted while a vector is masked?
- Q292 · How are accumulated completions handled after unmasking?
- Q293 · Can an in-use vector be reconfigured?
- Q294 · How are interrupts restored after reset?
- Q295 · How are interrupt resources reclaimed after queue deletion?
- Q296 · How are interrupt settings, CQ state and completions cross-checked?
- Q297 · Where do you start when an advertised command fails?
- Q298 · Does success of an unadvertised command prove compliance?
- Q299 · How is a successful Set with different readback or behavior investigated?
- Q300 · Why might an AER completion have no matching visible log information?
- Q301 · Does every failed CQE require a new error entry?
- Q302 · When do differing CQE, Error Information and PEL records conflict?
- Q303 · How are unexpected feature retention or lost saved values assessed?
- Q304 · How are namespace changes reconciled across Identify, lists and AER?
- Q305 · How are unchanged firmware revision or slot fields assessed after activation?
- Q306 · Is an in-progress log after sanitize command success an error?
- Q307 · How is a missing result after self-test investigated?
- Q308 · How are unexpected unsafe-shutdown counts assessed?
- Q309 · Which settings explain a warning change without an AER?
- Q310 · How is apparent PEL event-order mismatch investigated?
- Q311 · What evidence remains when CFS is set with little diagnostic information?
- Q312 · How are two observed completions after Abort classified?
- Q313 · What is wrong with queue-memory access after completed deletion?
- Q314 · How should a CQE from before reset be handled?
- Q315 · When can command success after detach be reasonable?
- Q316 · How is apparent Lockdown bypass investigated?
- Q317 · How is excessive power-state recovery latency measured correctly?
- Q318 · How are three reset types compared for one feature?
- Q319 · How is an operation’s real scope established?
- Q320 · How are the interfaces combined into one conformance investigation?
- Q321 · Is a Read/Write length valid across MDTS, NLB and namespace bounds?
- Q322 · Does successful Write imply power-loss persistence, and what do Flush and FUA guarantee?
- Q323 · Why can a small Write lose whole-command atomicity when it crosses a boundary?
- Q324 · What do successful Read, Compare and Verify actually prove?
- Q325 · Must reads return zero after Write Zeroes or Deallocate?
- Q326 · Why did PI checking miss an error? A Type 1, 16-bit Guard example
- Q327 · What does CQE.DW0 establish after a Copy failure?
- Q328 · Does a read failure after Write Uncorrectable prove damaged media?
Comments