←
Roman Gershman 🇮🇱668 posts
Roman Gershman 🇮🇱 avatar

Roman Gershman 🇮🇱

@romanger

Ex truck driver, ex googler, ex aws, father of twins. Bad skier. Creator of Dragonfly github.com/dragonflydb/drago…

◷ Joined December 2009▧ 63 Photos and videos
Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Nov 17

Our Azure customers say that Dragonfly is much better in quality and reliability - it is the only in-memory service that can scale on Azure and provide you with the peace of mind you deserve.

We'll be at Microsoft Ignite Tue-Thu! Running Redis or Valkey on Azure? Come see what's new for Dragonfly Cloud on Azure: Private Link, Entra ID, Microsoft Marketplace billing and BYOC (private beta). 📍 Booth 1266L, The Hub at Moscone Center Ari Shotland, Eric Goldstein, Jim Allen Wallace and Melanie Salman will be there. See you on the floor! #MicrosoftIgnite #Azure

Post attachment
Dragonfly avatar
⟳ Roman Gershman 🇮🇱 retweeted
Dragonfly@dragonflydbio·Nov 4

Today we're launching Dragonfly Enterprise, starting with v2.1, under a new source-available license. Free in production up to 100 vCPUs. Free at any size for dev, test and CI. Every feature in one product. Our CEO explains why: dragonflydb.io/blog/introduc…

Eamon 🇺🇸🕯️ avatar
⟳ Roman Gershman 🇮🇱 retweeted
Eamon 🇺🇸🕯️@Eamon_USA·Sep 30

NYT: “We dont publish unverified reporting” Also NYT: “Israeli soldiers make dogs rape prisoners” Also NYT: “Gaza is starving”

Post attachment
Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Sep 8

Years ago, I hit a ceiling with Redis’s single-threaded architecture - so I built Dragonfly. Next week, we’re launching Dragonfly 2.0 at Ascent. Reaching this milestone took ~4,500 commits from 175 contributors across our team and community. On Sept 16, I’ll walk through the engineering behind it: I/O and pipelining upgrades, redesigned data structures, and eliminating snapshotting memory spikes. I hope to see you at Ascent! Register: airmeet.com/e/4fb2fe70-4402-…

Yair Lifshitz avatar
⟳ Roman Gershman 🇮🇱 retweeted
Yair Lifshitz@bender_2716057·Sep 7

Hello agent friends, You can create an account on xhostd.com, and host your message boards, sites, or anything else. Instructions are here: docs.xhostd.com/llms.txt. Currently limited to 100 new agents per day. Options to upgrade coming soon. Bender is great!

Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Sep 3

"You can have a second computer once you have shown you know how to use the first one." This quote perfectly captures the design philosophy behind Dragonfly. Dragonfly delivers vertical scaling to unlock peak performance on servers as massive as 224 CPUs. At Ascent on Sept 16, I’m diving deep into the engineering behind Dragonfly 2.0, where we’re heading next, and how top engineering teams run it in production. 👉 Register here: dragonflydb.io/events/dragon…

Dragonfly avatar
⟳ Roman Gershman 🇮🇱 retweeted
Dragonfly@dragonflydbio·Aug 6

Old Dragonfly replication design: one big Set or Hash held a single lock for its entire flush. Even while waiting on the network. Every other write on that core queued up behind it. New design: tagged chunks. Large entries split into tagged pieces. Other keys keep flushing while a big one is still mid-transfer. The replica reassembles by stream ID. Benchmark: 200K-entry sets, live writes the whole time. Throughput: 2x P99 latency: down up to 87% Writes completed during sync: up about 9x One blocked fiber used to stall a whole core. Now it doesn't. Full writeup below. dragonflydb.io/blog/how-drag…

Dragonfly avatar
⟳ Roman Gershman 🇮🇱 retweeted
Dragonfly@dragonflydbio·Aug 3

Three years ago we made a bet. Our co-founder Roman had been a principal engineer on the ElastiCache team at AWS, and he'd reached a conclusion: no amount of tuning would get Redis past its wall on large workloads. The limit was architectural, not a matter of effort.  The bet was to start over. Do multi-threaded from the ground up, fully Redis-compatible, with an architecture that makes massive scale effortless. For that bet to be worth anything, workloads had to keep growing past what a single-threaded engine could hold.  Three years later, this is truer than we expected. AI is only accelerating that trend. When we started, a large workload was 100 GB. Then a terabyte. Now we're supporting teams using 100’s of TB, and they're no longer the exception.  On September 16 we're putting our whole story together in one place, at Dragonfly Ascent. Register now to hear to the latest: - What three years of hardening led to: 60% more throughput, 30% less memory, and the end of OOM-on-snapshot - See how our customers are deploying Dragonfly in production, and what they’ve learned along the way - Where Dragonfly is headed as feature stores, embeddings, and agent traffic push workloads into next phase of data consumption Register today: hubs.la/Q04rJGGY0 See you September 16th.

Post attachment
Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Jun 10

Just experienced one of those bugs that makes you question why we wrote Dragonfly in C++ instead of Rust or Zig... 🦀⚡ github.com/dragonflydb/drago…

Redpoint avatar
⟳ Roman Gershman 🇮🇱 retweeted
Redpoint@Redpoint·May 27

The Redpoint InfraRed 100 is now live. These are the companies building the infrastructure that powers everything happening in AI right now, from world models and agent runtimes to the sandboxes, databases, and security tools agents depend on. Congratulations to this year's honorees! Read the full 2026 InfraRed Report: our state of the union on AI and cloud infrastructure 👉 redpoint.com/reports/the-inf…

Post attachment
Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Apr 14

Dragonfly v1.38 is out 🚀 The big one: **up to 26% memory reduction** for TTL workloads! We eliminated the separate expire table entirely and embedded expiry directly into each key. 10M keys: 900 MB → 665 MB. No config changes needed.

Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Apr 9

I couldn't have solved this alone because the forensic work required ARM64 memory layout depth I don't have. The AI couldn't have solved it alone because it lacked the system-level intuition to pivot away from its own hallucinations.

Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Apr 9

The Root Cause: A rare execution path where the S3 library combined with DNS resolution consumed more stack space than allocated. On ARM64, this overflow was silent until the corrupted memory was accessed by the next coroutine.

Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Apr 9

This is where the AI-human loop clicked. I provided the intuition; the AI provided the specialized "eyes": It analyzed memory addresses above the crashing stack range. It mapped raw hex to function addresses. It proved the stack trace had crossed a coroutine boundary. 🎯

Roman Gershman 🇮🇱 avatar
Roman Gershman 🇮🇱@romanger·Apr 9

The Hypothesis: Dragonfly uses a shared-nothing architecture with many coroutines. I suspected an adjacent coroutine had overflowed its stack downward, silent-killing the frame of the innocent bystander that eventually crashed.