CloudDT: efficient tape resource management using deduplication in cloud backup and archival services
Bibliographic record
Abstract
Abstract—Cloud-based backup and archival services use large tape libraries as a cost-effective cold tier in their online storage hierarchy today. These services leverage deduplication to reduce the disk storage capacity required by their customer data sets, but they usually re-duplicate the data when moving it from disk to tape. Deduplication does not add significant I/O overhead when performed on disk storage pools. However, when deduplicated data is naively placed on tape storage, the high degree of data fragmentation caused by deduplication--combined with the high seek and mount times of today's tape technology--leads to high retrieval times. This negatively impacts the recovery time objectives (RTO) that the service provider has to meet as a part of the service level agreement (SLA). This work proposes CloudDT, an extension to Cloud backup and archival services to efficiently support deduplication on tape pools. This paper (i) details the main challenges to enable efficient deduplication on tape libraries, (ii) introduces a class of solutions based on graph-modeling of similarity between data items that enables efficient placement on tapes, and (iii) presents the design and initial evaluation of algorithms that alleviate tape mount time overhead and reduce on-tape data fragmentation. Using 4.5 TB of real-world workloads, our initial evaluations show that our algorithms retain at least 95 % of the deduplication storage efficiency, and offer up-to 40 % faster restore performance compared to the case of restoring non-deduplicated data. Therefore, our techniques allow the backup service provider to increase tape resource utilization using deduplication, while also improving the restore time performance for the enduser. I.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".