article thumbnail

USENIX LISA2021 Computing Performance: On the Horizon

Brendan Gregg

## References I've reproduced the talk references below, so you can click on links: - [Gregg 08] Brendan Gregg, “ZFS L2ARC,” [link] Jul 2008 - [Gregg 10] Brendan Gregg, “Visualizations for Performance Analysis (and More),” [link] 2010 - [Greenberg 11] Marc Greenberg, “DDR4: Double the speed, double the latency? Ford, et al., “TCP

article thumbnail

USENIX SREcon APAC 2022: Computing Performance: What's on the Horizon

Brendan Gregg

My personal opinion is that I don't see a widespread need for more capacity given horizontal scaling and servers that can already exceed 1 Tbyte of DRAM; bandwidth is also helpful, but I'd be concerned about the increased latency for adding a hop to more memory. Ford, et al., “TCP

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

KeyCDN Launches New POPs in 2021

KeyCDN

The image below shows a significant drop in latency once we've launched the new point of presence in Israel. In fact, latency has been reduced by almost 50%! With a total of 5 POPs in Oceania, this continent benefits from lower latency with every POP added. Lagos - Nigeria Africa got its second POP!

Latency 110
article thumbnail

SQL Server 2016 – It Just Runs Faster: Always On Availability Groups Turbocharged

SQL Server According to Bob

Performance issues surrounding Availability Groups typically were related to disk I/O or network speeds. Our customers who deployed Availability Groups were now using servers for primary and secondary replicas with 12+ core sockets and flash storage SSD arrays providing microsecond to low millisecond latencies. one without a replica).

article thumbnail

The Performance Inequality Gap, 2023

Alex Russell

We're burning our inheritance and polluting the ecosystem on shockingly thin, perniciously marketed claims of "speed" and "agility" and "better UX" that have not panned out at all. That is, what was the average device in 2016? As this series has emphasised in years past, Average Selling Price ( ASP ) is destiny.

article thumbnail

Cache-Control for Civilians

CSS Wizardry

If, however, there wasn’t a new file on the server, we’ll bring back a 304 header, no new file, but an entire roundtrip of latency. We can completely cut out the overhead of a roundtrip of latency. On high latency connections, this saving could be tangible. What do we mean by a mutable or immutable file? FAQs Page.

Cache 264
article thumbnail

USENIX SREcon APAC 2022: Computing Performance: What's on the Horizon

Brendan Gregg

My personal opinion is that I don't see a widespread need for more capacity given horizontal scaling and servers that can already exceed 1 Tbyte of DRAM; bandwidth is also helpful, but I'd be concerned about the increased latency for adding a hop to more memory. Ford, et al., “TCP