Hesela / Research library
Research & analyses
Storage engineering, examined through sources, measurements and reproducible methods.
133 analyses · Page 3 of 5
Newest firstLSM tombstones: deleted is not yet reclaimed
Separate delete visibility, crash durability and space reclamation: snapshots, Lethe's delete-aware compaction and RocksDB's range-tombstone safeguards.
NFS stable writes: what COMMIT, flush and FUA actually promise
NFSv3 stability, COMMIT verifiers and Linux flush/FUA, with NFSv4.1 lease, grace and reclaim boundaries for server restart recovery.
NVMe FDP: placement handles are not physical addresses
How reclaim units, handles and placement identifiers fit together, why FDP differs from ZNS, and what a credible write-amplification comparison must measure.
Object ETags: checksums and conditional writes are different
S3 ETags, full-object and composite checksums, version IDs and write preconditions: what each validates, and how to avoid checking download metadata instead of bytes.
Optical disc rot: what public ageing studies measured, which error counters (BLER, PI sum 8) warn first, and what they cannot predict
Recordable discs fail mainly because the organic dye layer breaks down or, on discs with a silver reflective layer, the metal corrodes, and the public tell-tale is a rising correctable-error counter before data is lost: block error rate (BLER, counted at the first CD decoder) against a specified maximum of 220 per second on CD, and parity-inner errors summed over eight blocks (PI sum 8) against a maximum of 280 on DVD. In the NIST and Library of Congress study of discs bought in 2005, all 7 CD-R products reached an estimated life of more than 30 years at 25 C and 50% relative humidity (5 of 7 more than 45 years), while the 15 DVD products spread from under 15 years (2 products) to more than 45 years (7 products). Canada's conservation institute ranks a gold-layer phthalocyanine CD-R above 100 years and a dye or non-dye single-layer Blu-ray recordable at 5 to 10 years, and says discs recorded with poor technique can fail in as little as 2 to 10 years. These are accelerated-ageing estimates of temperature and humidity effects only, for disc products of 2005 or earlier, so they rank media and set expectations but are not a failure rate for any disc in use today.
Replication acknowledgements: received, durable, applied
Compare replication acknowledgements, WAL retention and logical failover readiness; distinguish durable writes, replay and missing or unusable slots.
Slow RAID hours are not request tail latency
Slow-drive hours and request percentiles count different events. Source review and exact examples distinguish fan-out, hedged reads, cancellation work and replica dependence.
SSD mapping caches: why DRAM size is not a speed rating
Separate SSD maps from data buffers, explain cache admission and HMB, and reproduce memory, scan and request-versus-byte hit examples.
SSD over-provisioning: the denominator changes the answer
Convert SSD reserve percentages, compare TRIM occupancy, and see why block placement and pooled counters change write-amplification calculations.
SSD read reclaim: why read-only workloads can cause writes
Separate read disturb, read retry and data relocation; compare device measurements with simulations, and handle zero-host-write intervals without inventing a WAF.
SSD steady state is not a timer
Why SSD warm-up duration is not proof of steady state: source review, two independent stability checks and six reproducible synthetic counterexamples.
Storage consistency: ordering is not a transaction or a durability promise
Linearizability, transactions, four session guarantees and compare-and-swap: identify the scope of a storage guarantee before relying on it for correctness.
Storage latency: when the benchmark stops asking
A completion-driven load generator can hide queueing during a stall. A reproducible synthetic example explains coordinated omission, timing boundaries and why p99 values cannot be averaged.
WAL, checkpoints and torn pages: three different recovery guarantees
WAL recovery boundaries: PostgreSQL hint-bit writes, page-image compression and statistics traps, plus InnoDB doublewrite and SQLite commit semantics.
3D NAND retention: layer count is not a reliability rating
Separate NAND architecture, dwell, thermal annealing and read conditions before interpreting raw error rates or claims of restored SSD endurance.
Atomic rename is not a durable commit
File contents, directory entries and commit acknowledgements have different persistence boundaries. Linux documentation and two USENIX studies explain what a rename does not guarantee.
BCH, LDPC and the RBER aggregation trap
A drive-wide raw error rate cannot reveal the hardest codeword. How to compare BCH and LDPC evidence without confusing fleet telemetry with decoder limits.
Correlated SSD failures: what the Alibaba measurements count
Han et al. (FAST 2021) report that 12.9% of failures were intra-node and 18.3% intra-rack at a 30-minute grouping threshold. These are shares of recorded failures, not percentages of all installed drives. Reading the analysis code also separates a group-size statistic from a prediction of the next drive failure.
Datacenter failure tickets are not failed-device counts
A hardware ticket, a failed device and a service outage are different counting units. Review the reported fleet figures, separate response time from repair time, and reproduce why a 120-second failure-burst rule need not limit a burst to 120 seconds.
Deduplication ratio does not predict restore cost
A cold-cache trace separates container rereads from unused fetched bytes, with six reproducible examples and a review of two USENIX papers.
Discard is not zeroing: what TRIM, UNMAP and fstrim actually promise
A discard request, zero-filled readback and reclaimed physical space are different observations. Protocol and Linux documentation show how to interpret each without false assurances.
Disk scrubbing: detection time is not a durability guarantee
How scan order, sampling design and irregular inspection intervals change what a storage integrity check can detect, with reproducible examples.
Eleven nines: assumptions behind cloud durability estimates
A durability target is not a measured loss rate. Recomputing a historical 20-shard example gives about 1.06e-11 per year with a Poisson event model and 7.72e-12 with a distinct-shard binomial model. The difference is a modeling choice, not evidence that one cloud provider is safer.
HDD mechanical faults: evidence and diagnostic limits
Shock models, vibration tests and vendor counters reveal different parts of HDD mechanics. They do not provide a universal damage threshold or a failure forecast.
In an 18-month Berkeley study of 368 disks, 7 data disks failed against 13 enclosure backplane failures; disks were 90% of parts but about 4% of errors
In Talagala and Patterson (UC Berkeley, 1999), 18 months of operation of a prototype with 20 PCs and 368 SCSI data disks, 34 components were replaced. Only 7 of the 368 data disks (1.9%) failed, the lowest percentage of any failing component, against 13 of 46 disk enclosures (28.3%, backplane faults) and 6 of 24 IDE system disks (25.0%). Disks were about 90% of the components but only around 4% of 688 logged error instances, while SCSI timeouts and parity errors were 49% (87% without network errors), and no restart was caused by a data disk. Ford et al. (OSDI 2010) later found a disk MTTF of 10 to 50 years against 4.3 months for a node, and Schroeder and Gibson (FAST 2007) found disks were 20% to 50% of hardware replacements, a count not a rate.
LDPC in NAND: the read cost of confidence
How soft information is acquired, why decoder structure changes the result, and which error-rate denominators an SSD reliability claim must disclose.
Local repair is not whole-node repair
Repair-cost accounting for LRC and MSR codes: separate helper count, data reads, network payload and whole-node repair, with reproducible examples.
Missing SMART ages and the limits of drive-age comparisons
A full Q4 2025 raw-data audit finds 18 TB drives in a mislabeled capacity group and shows why excluding 106 missing-age drive-days also excludes 19 failures.
NAND copyback: faster relocation is not fewer writes
Why on-chip page relocation can bypass controller ECC, why destination placement matters, and why lower NAND-channel traffic is not lower write amplification.
NAND erase blocks: geometry is not write amplification
More pages per erase block can increase work per collection, but the live-data fraction, mapping policy and workload determine the write cost. Separate historical chip parameters, simulated SSD results and a reproducible accounting example.
Looking for a technology? Browse technology cards or open the knowledge corpus.