DBScholar

Back to papers

Scribe: How Meta transports terabytes per second in real time

Summary: Scribe: Meta’s multi-tenant, low-latency message queue ingesting >15 TB/s and delivering >110 TB/s to consumers for massive real-time streams. Key innovations: a multi-hop write path with opportunistic placement to maximize write availability, and an adaptive read path that tunes replica placement/representation per workload while exposing tunable delivery guarantees. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
14275
Venue
VLDB
Year
2025
Pagerank
5.093636e-05
Overall Rank
10,996 | 24.56%
DOI
10.14778/3750601.3750607

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{karpathiotakis_vldb25,
        title = {{Scribe: How Meta transports terabytes per second in real time}},
        author = {Karpathiotakis, Manos and Rizopoulos, Vlassios and Kahveci, Basri and Carotti, Tiziano and Gelum, Artem and Nada, Hazem and Dolgov, Yuri},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {12},
        pages = {4817--4830},
        doi = {10.14778/3750601.3750607},
        url = {https://doi.org/10.14778/3750601.3750607},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 14 of 14 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers