https://blog.turboawesome.win/tags/latency/ Recent content in Latency on Bits, Trades & Systems Hugo en-us Thu, 01 Oct 2015 09:44:00 +0000 https://blog.turboawesome.win/2015/10/zgc-and-shenandoah-what-low-pause-gc-means-for-trading-systems/ Thu, 01 Oct 2015 09:44:00 +0000 https://blog.turboawesome.win/2015/10/zgc-and-shenandoah-what-low-pause-gc-means-for-trading-systems/ In 2015 the JVM GC landscape was about to change significantly. ZGC and Shenandoah were in development, promising sub-millisecond GC pauses regardless of heap size. Here's what the previews looked like and what they meant for latency-sensitive Java. https://blog.turboawesome.win/2015/05/understanding-safepoints-the-jvm-pauses-nobody-talks-about/ Wed, 27 May 2015 14:38:00 +0000 https://blog.turboawesome.win/2015/05/understanding-safepoints-the-jvm-pauses-nobody-talks-about/ GC pauses get all the attention, but safepoints are a broader category of JVM stop-the-world events that affect latency in ways GC tuning can't fix. https://blog.turboawesome.win/2014/10/benchmarking-without-lying-jmh-coordinated-omission-and-honest-numbers/ Wed, 29 Oct 2014 10:14:00 +0000 https://blog.turboawesome.win/2014/10/benchmarking-without-lying-jmh-coordinated-omission-and-honest-numbers/ Most latency benchmarks are wrong in the same ways. JMH solves the JVM measurement problems; coordinated omission is the harder issue that lives above it. https://blog.turboawesome.win/2014/08/choosing-a-gc-collector-for-low-latency-java-a-practical-comparison/ Wed, 06 Aug 2014 10:18:00 +0000 https://blog.turboawesome.win/2014/08/choosing-a-gc-collector-for-low-latency-java-a-practical-comparison/ CMS vs G1 vs parallel GC vs no-GC strategies. The tradeoffs as they actually played out in a latency-sensitive financial application, with real numbers. https://blog.turboawesome.win/2014/05/busy-spinning-vs-blocking-thread-strategies-for-ultra-low-latency/ Wed, 14 May 2014 10:31:00 +0000 https://blog.turboawesome.win/2014/05/busy-spinning-vs-blocking-thread-strategies-for-ultra-low-latency/ Blocking a thread hands control to the OS scheduler and costs you microseconds on wake-up. Busy spinning wastes a CPU core. The right choice depends on your latency target and hardware budget. https://blog.turboawesome.win/2014/02/fx-pricing-engine-architecture-from-feeds-to-executable-quotes/ Wed, 19 Feb 2014 11:08:00 +0000 https://blog.turboawesome.win/2014/02/fx-pricing-engine-architecture-from-feeds-to-executable-quotes/ End-to-end architecture of an FX pricing engine: LP feed ingestion, aggregation, spread logic, and quote distribution. The design choices that kept us under 500µs tick-to-quote. https://blog.turboawesome.win/2013/11/why-average-latency-is-a-lie-hdrhistogram-and-measuring-what-matters/ Wed, 27 Nov 2013 11:14:00 +0000 https://blog.turboawesome.win/2013/11/why-average-latency-is-a-lie-hdrhistogram-and-measuring-what-matters/ Average latency hides the distribution. HdrHistogram gives you a complete picture of latency across the full range — and it does so without distorting the system you're measuring. https://blog.turboawesome.win/2012/11/stop-the-world-gc-pauses-killed-our-sla-and-what-we-did-about-it/ Tue, 13 Nov 2012 11:08:00 +0000 https://blog.turboawesome.win/2012/11/stop-the-world-gc-pauses-killed-our-sla-and-what-we-did-about-it/ How garbage collection pauses blew our latency SLA during peak market hours, and the three-phase approach we used to get it under control. https://blog.turboawesome.win/2012/09/latency-vs-throughput-the-false-dichotomy-i-learned-the-hard-way/ Tue, 25 Sep 2012 10:33:00 +0000 https://blog.turboawesome.win/2012/09/latency-vs-throughput-the-false-dichotomy-i-learned-the-hard-way/ Optimising for throughput and optimising for latency are often portrayed as opposites. In practice they pull in different directions but are not mutually exclusive — and confusing them leads to systems that are bad at both. https://blog.turboawesome.win/2012/05/building-a-price-feed-aggregator-in-java-first-attempt/ Wed, 09 May 2012 14:22:00 +0000 https://blog.turboawesome.win/2012/05/building-a-price-feed-aggregator-in-java-first-attempt/ My first serious Java performance project: aggregating price feeds from multiple venues into a single best-bid-offer view. What I built, what was wrong with it, and what I learned rewriting it.