--- title: TigerBeetle vs PostgreSQL Performance: Benchmark... description: A follow-up benchmark compares TigerBeetle and PostgreSQL performance in a multinode cloud cluster setup on GCP, simulating double-entry bookkeeping transfers.... canonical: https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-harness-cloud-tests-fz3qlemyi twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: TigerBeetle vs PostgreSQL Performance: Benchmark Harness, Cloud Tests | daily.dev og:description: A follow-up benchmark compares TigerBeetle and PostgreSQL performance in a multinode cloud cluster setup on GCP, simulating double-entry bookkeeping transfers.... og:url: https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-harness-cloud-tests-fz3qlemyi og:image: https://api.daily.dev/og/posts/FZ3QLeMYi.png og:image:alt: TigerBeetle vs PostgreSQL Performance: Benchmark Harness, Cloud Tests og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # TigerBeetle vs PostgreSQL Performance: Benchmark Harness, Cloud Tests **[SoftwareMill](https://daily.dev/sources/softwaremill)** · 9 min read · 5 upvotes · 1 comments ## Summary A follow-up benchmark compares TigerBeetle and PostgreSQL performance in a multinode cloud cluster setup on GCP, simulating double-entry bookkeeping transfers. TigerBeetle consistently outperformed PostgreSQL's row-locking (FOR UPDATE) and atomic strategies across throughput and latency, with the gap widening dramatically under high account contention (Zipfian skew of 2.0). While PostgreSQL throughput dropped sharply under hotspot contention due to row locking, TigerBeetle maintained low latency and even improved. Pushing TigerBeetle further, the team scaled it to over 100k transfers per second while still keeping lower latency than PostgreSQL managed at just 5k TPS, demonstrating the benefits of TigerBeetle's specialized single-core sequential architecture for this workload. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does TigerBeetle's throughput compare to PostgreSQL for double-entry bookkeeping transfers under high account contention? TigerBeetle achieves roughly 4.6x higher throughput than the best PostgreSQL strategy under heavy hotspot skew (Zipfian exponent 2.0), reaching 4,461 TPS versus 977 TPS for PostgreSQL's atomic locking approach and 753 TPS for its FOR UPDATE approach, in a three-node cluster benchmark on Google Cloud Platform. _Comparing ledger database options under contention gets easier with benchmark writeups like this tracked on daily.dev._ ### What is the maximum throughput TigerBeetle can handle in a multinode cloud cluster before dropping requests? In a three-node GCP cluster test using n2-highmem-4 instances, TigerBeetle sustained up to roughly 101,497 TPS with zero dropped requests, and started dropping around 12% of offered load only once the target rate reached 120,000 TPS, with drops rising to about 34% at 160,000 TPS. _Engineers sizing high-throughput ledger infrastructure can follow benchmark deep dives like this on daily.dev._ ### Why does PostgreSQL's throughput degrade so much under high contention on hot accounts compared to TigerBeetle? PostgreSQL's row-locking strategies (FOR UPDATE and an atomic approach) force connections to wait when multiple transactions target the same account row, causing throughput to drop from around 2,890-3,068 TPS under moderate skew to just 753-977 TPS under heavy hotspot skew, with latency spiking as high as 2,916 ms at p999. TigerBeetle avoids this because a single core processes transfers sequentially, so there is nothing to contend over. _Teams debugging lock contention in financial systems can dig into comparisons like this on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@agustinbarrientos** · 0 upvotes > I suspect the Zipfian hotspot result matters because it exposes an architectural difference, not faster hardware. TigerBeetle's fixed ledger and ordered execution avoid relational and index work PostgreSQL still performs. That's strong specialized-ledger evidence, but a narrower win than the headline suggests. ## Similar posts on daily.dev - [TigerBeetle vs PostgreSQL Performance: Benchmark Setup, Local Tests](https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-setup-local-tests-dufn7d8ly) · SoftwareMill · 2 upvotes · 0 comments - [What’s Interesting About TigerBeetle?](https://daily.dev/posts/what-s-interesting-about-tigerbeetle--i5himi73k) · SoftwareMill · 2 upvotes · 0 comments --- Tags: [#database](https://daily.dev/tags/database), [#postgresql](https://daily.dev/tags/postgresql), [#distributed-systems](https://daily.dev/tags/distributed-systems) [View this post on daily.dev](https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-harness-cloud-tests-fz3qlemyi) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"TigerBeetle vs PostgreSQL Performance: Benchmark Harness, Cloud Tests","url":"https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-harness-cloud-tests-fz3qlemyi","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-harness-cloud-tests-fz3qlemyi"},"datePublished":"2026-08-31T10:09:43.313Z","dateModified":"2026-08-31T10:10:11.226Z","description":"A follow-up benchmark compares TigerBeetle and PostgreSQL performance in a multinode cloud cluster setup on GCP, simulating double-entry bookkeeping transfers....","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/dc23266018e21f88c375ce67cc8fbb5d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/dc23266018e21f88c375ce67cc8fbb5d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"SoftwareMill","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"SoftwareMill","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/30827c94697f47fcbc88ff9b59fa226f","url":"https://daily.dev/sources/softwaremill"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-harness-cloud-tests-fz3qlemyi","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":5},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"database,postgresql,distributed-systems","timeRequired":"PT9M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"SoftwareMill","item":"https://daily.dev/sources/softwaremill"},{"@type":"ListItem","position":3,"name":"TigerBeetle vs PostgreSQL Performance: Benchmark Harness, Cloud Tests"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-harness-cloud-tests-fz3qlemyi","comment":[{"@type":"Comment","text":"I suspect the Zipfian hotspot result matters because it exposes an architectural difference, not faster hardware. TigerBeetle’s fixed ledger and ordered execution avoid relational and index work PostgreSQL still performs. That’s strong specialized-ledger evidence, but a narrower win than the headline suggests.","datePublished":"2026-09-02T00:29:58.945Z","url":"https://daily.dev/posts/FZ3QLeMYi#c-284hjacV3","author":{"@type":"Person","name":"Agustin Barrientos","url":"https://daily.dev/agustinbarrientos","image":"https://media.daily.dev/image/upload/s--5ayxQnqn--/f_auto/v1788281802/avatars/avatar_wQYYVe5Tbj0NJ7C7qPoa8?_a=BAMAMicg0"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/tigerbeetle-vs-postgresql-performance-benchmark-harness-cloud-tests-fz3qlemyi#faq","mainEntity":[{"@type":"Question","name":"How does TigerBeetle's throughput compare to PostgreSQL for double-entry bookkeeping transfers under high account contention?","acceptedAnswer":{"@type":"Answer","text":"TigerBeetle achieves roughly 4.6x higher throughput than the best PostgreSQL strategy under heavy hotspot skew (Zipfian exponent 2.0), reaching 4,461 TPS versus 977 TPS for PostgreSQL's atomic locking approach and 753 TPS for its FOR UPDATE approach, in a three-node cluster benchmark on Google Cloud Platform. Comparing ledger database options under contention gets easier with benchmark writeups like this tracked on daily.dev."}},{"@type":"Question","name":"What is the maximum throughput TigerBeetle can handle in a multinode cloud cluster before dropping requests?","acceptedAnswer":{"@type":"Answer","text":"In a three-node GCP cluster test using n2-highmem-4 instances, TigerBeetle sustained up to roughly 101,497 TPS with zero dropped requests, and started dropping around 12% of offered load only once the target rate reached 120,000 TPS, with drops rising to about 34% at 160,000 TPS. Engineers sizing high-throughput ledger infrastructure can follow benchmark deep dives like this on daily.dev."}},{"@type":"Question","name":"Why does PostgreSQL's throughput degrade so much under high contention on hot accounts compared to TigerBeetle?","acceptedAnswer":{"@type":"Answer","text":"PostgreSQL's row-locking strategies (FOR UPDATE and an atomic approach) force connections to wait when multiple transactions target the same account row, causing throughput to drop from around 2,890-3,068 TPS under moderate skew to just 753-977 TPS under heavy hotspot skew, with latency spiking as high as 2,916 ms at p999. TigerBeetle avoids this because a single core processes transfers sequentially, so there is nothing to contend over. Teams debugging lock contention in financial systems can dig into comparisons like this on daily.dev."}}]} ```