Top all-time · #21316
High Performance Linux
Company blog · natsys-lab.blogspot.rusystemsprogramming
High Performance Linux is the company blog at natsys-lab.blogspot.ru, writing about systems and programming. Since 2012, 3 different Hacker News readers have linked it 9 times, most often “Studying Intel TSX (Transactional Memory) Performance ”. The last post was in 2019, but the archive is still widely read.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
HN readers link this blog for its study of Intel TSX (transactional memory) performance on Haswell. One commenter cites it as evidence that the initial Haswell implementation was not very efficient.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
High Performance Linux: Tempesta FW, Linux kernel, HTTP, DDoS mitigation, Web Security, reverse proxy, HTTP proxy, Nginx, HAProxy, performance
Most-linked posts?
- Studying Intel TSX (Transactional Memory) Performance 2 people · 2 mentions · first linked 2014-01-10
What Hacker News says?
As a systems guy who was intially very skeptical of Transactional Memory, I've been very excited about TSX for a while. Unfortunately, it seems that the initial implementation in the haswell processors wasnt very efficient[1]. Im looking forward to future hardware implementations by intel. 1. http://natsys-lab.blogspot.ru/2013/11/studying-intel-tsx-per...
Comment linking /2013/11/studying-intel-tsx-performance.html
on “Errata prompt Intel to disable TSX in Haswell, early Broadwell CPUs”Submitted Lock-free Multi-producer Multi-consumer Queue on Ring Buffer as a story · 57 points
HN discussionThis is a good question. Currently we've integrated the queue in two projects in production state: user-space proxy server and VPN capturer (Linux kernel module). In both the cases we enhanced the queue with conditions like is the queue empty or is it full, so we can drop packets if consumers are overloaded and there is no sense to put a packet to the queue. Secondly, the queue is designed to work on multi-core envi…
Comment linking /2013/08/lock-free-condition-wait-for-lock-free.html
on “Lock-free Multi-producer Multi-consumer Queue on Ring Buffer”Submitted Studying Intel TSX (Transactional Memory) Performance as a story · 3 points
HN discussionSubmitted NatSys Lock-free Queue vs LMAX Disruptor vs boost::lockfree::queue as a story · 2 points
HN discussionSubmitted Lock-free Condition Wait for Lock-free Multi-producer Multi-consumer Queue as a story · 1 points
HN discussionSubmitted Linux: scaling softirq among many CPU cores as a story · 1 points
HN discussionSubmitted Haswell AVX2 for Simple Integer Bitwise Operations as a story · 1 points
HN discussionSubmitted Software transactional memory in gcc 4.7 as a story · 1 points
HN discussion