Re: Prefetching and false sharing

I am not sure how much I would trust an AWS machine in general for benchmarks On Sun, Jan 29, 2017 at 7:34 PM, Duarte Nunes wrote: > Forgot to mention that I had to use an AWS machine and CPU counters are not > available, so not posting those. > > > On Sunday, January

Re: How to sequence messages we sent to client and find bugs

With exchanges often traffic is sent to everyone when using non-reliable transports such as UDP. As example see the STAMP protocol (over UDP multicast). In this protocol every message is given a sequence number (perfectly ordered). Clients then can find any missing messages by looking for gaps in

New Instructions (Intel)

https://lkml.org/lkml/2016/10/12/530 -- Studying for the Turing test -- You received this message because you are subscribed to the Google Groups "mechanical-sympathy" group. To unsubscribe from this group and stop receiving emails from it, send an email to

Re: detecting "broken" TCP connections

In my experience protocol level tcp keep alives don't always work between implementations. BSD - windows used to be a primary culprit, though they were set they would not get hit in some cases. Things may be better today. On same implementation they should work quite well. Definitely worth testing

Re: US Presidents and Computing Security

Why do I have generals and couriers in my head? On Mon, Jan 2, 2017 at 7:43 AM, k...@kodewerk.com wrote: > > On Jan 2, 2017, at 8:31 AM, Chris Vest wrote: > > The rabbit hole of what-can-be-trusted goes pretty deep: >

Re: Does percentile metrics follow the rules of summations?

no because the 99th percentiles do not necessarily happen at the same time. On Wed, Dec 21, 2016 at 10:53 AM, Gaurav Abbi wrote: > Hi, > We are collecting certain metrics using (Graphite + Grafana) use them as a > tool to monitor system health and performance. > > For one

Modern Garbage Collection (good article)

Thought people on here would enjoy this https://medium.com/@octskyward/modern-garbage-collection-911ef4f8bd8e#.ptdzwcmq2 -- Studying for the Turing test -- You received this message because you are subscribed to the Google Groups "mechanical-sympathy" group. To unsubscribe from this group and

Re: Systematic Process to Reduce Linux OS Jitter

@Gil this should be a blog post. On Mon, Dec 26, 2016 at 5:09 PM, Gil Tene wrote: > One of the biggest reasons folks tend to stay away from the consumer CPUs in > this space (like the is the i7-6950X you mentioned below) is the ack of ECC > memory support. I really wish Intel

Re: Disk-based logger - write pretouch

I would be interested to test it with zfs, it might even be harmful On Mon, Jul 10, 2017 at 11:55 PM, Michael Barker wrote: > From our own experience with journaling the benefits of pre-touching files > depends on the file system used. When ended up using XFS and threw away

Re: Throughput test of OpenHFT networking

Will your production system be running over loopback? On Sun, May 13, 2018 at 1:59 AM, John Hening wrote: > I know that testing by loopback isn't the best idea (and that it omits a > part of the network stack) but it is the simplest and I have just a laptop > with one

Re: peanut butter

We used to have a similar one "mole asses" referring to https://en.wikipedia.org/wiki/Molasses. Though we also used it in regard to people on teams. On Tue, May 8, 2018 at 6:16 PM, Tony Finch wrote: > Some time ago I encountered the term "peanut butter", meaning bad > performance

Re: jHiccup for .NET?

If someone wants to work on it I have a profiler api implementation that could be a useful starting point. It supports both mono and the CLR (two separate implementations the mono one is in C the CLR C++) On Wed, Aug 29, 2018 at 1:07 PM Remi Forax wrote: > > > -- > >

Re: How does matching engine on the financial exchanges handle fail-over

Just to add to the already fair reply by Martin. Take a look at how eventstore works. It tolerates a minority of servers failing, takes load similar to stock exchanges, and is OSS so you can actually read the code. https://github.com/eventstore/eventstore. You can actually find our paxos

Re: Exclusive core for a process, is it reasonable?

>> >> The amount of effort going into this is astounding. I can't help thinking >> that it won't end well. >> >> On 04/09/2018 10:55 AM, Greg Young wrote: >> >> To be fair many of the fpga based things have also moved to asics. You >> know you are in fo

Re: Intra-process queue between Java and C++

Will the 16 bytes save you time? On Fri, Mar 30, 2018 at 10:36 PM, Roman Leventov wrote: > Martin, thanks a lot! > > I thought about Aeron IPC, but as far as I understand it maps to the queue > model only when there is a single producer and a single consumer. Also it >

Re: Mechanical sympathy for high schoolers?

So I would probably focus on some more basic principles with them and focus on what is faster and *why*. I would also *NOT* use javascript if the point was to look at efficiency but instead something like C. To be fair you can teach an aspiring student enough C to write basic data structures very

Re: Getting clock difference of 2 servers upto single digit micros (as close as possible)

So there is a well known protocol for this (determining relative clocks) from a rather unusual source... chess servers! Many people enjoy playing chess online very quickly (say 1 minute per side), when playing such quick games a small latency difference can make a huge overall difference so it

Re: Sorting a very large number of objects

Given the list and people having many levels of experience/age/etc its probably worth expounding on : I'm reminded about the old story of the McIlroy and Knuth word count programs. https://franklinchen.com/blog/2011/12/08/revisiting-knuth-and-mcilroys-word-count-programs/ On Sat, Jan 19, 2019 at

Re: Probing the CPU for metrics / info

take a look at http://libcpuid.sourceforge.net/index.html On Thu, Nov 29, 2018 at 5:19 PM Mani Sarkar wrote: > Hi, > > Haven't written here for a long time. I have a query about probing CPUs > (via commands and/or programs) to find out vital information about them > mostly speed/performance

Re: Faster System.nanotime() ?

"A) Some BIOSes resetting TSC on a single core or hyperthread on each socket (usually thread 0 of core 0) for some strange reason during the boot sequence. [I've conclusively shown this on some 4 socket Sandy Bridge systems.] This leads different vcores to have vastly differing TSC values, which

Re: What linux distribution is better tooled for learning about resource utilization and perf tuning

How well do you already know Linux? Are you comfortable compiling kernels etc or are you just looking for a stock install? While this seems like a trivial detail it's not :) On Thu, Jul 11, 2019, 9:53 PM Ruslan Rusu wrote: > Hi here, > > I'm a beginner in this space. As I read and learn was

Re: Resizable array, the fastest known approach

A bit older reference but worth benchmarking https://stackoverflow.com/questions/11621606/faster-way-to-move-memory-page-than-mremap On Tue, Feb 8, 2022 at 6:51 AM r r wrote: > Hello, > 1. What is the fastest implementation of resizable array in Java? I know > only one, that copies whole array

Re: Megamorphic virtual call optimization in Java

which jvm? On Sat, Feb 5, 2022 at 6:26 AM r r wrote: > Hello, > we know that there are some techniques that make virtual calls not so > expensive in JVM like Inline Cache or Polymorphic Inline Cache. > > Let's consider the following situation: > > Base is an interface. > > public void f(Base[]