21–30 of 41 posts
In a real world app, I think you'd be considered lucky if the web-server is your bottleneck, rather than your DB or network connection.
Earlier quoted context omitted.
Douche much? Looking over your comments on HN, that latest comment seems to be the peak of your contribution here. In over two years you've picked up 394 karma points. I'm going with the assumption that all of those karma points are from being a pedant about the English language. You're such a valuable member of this community! Rock on.
Which of your 98 days here qualifies you to assess the peak of someone's contribution over a span of two years?
Quickly looking over SoftLayer's price sheet, it looks to be a little over $1k a month for Intel 5670 with 24GB of RAM
Earlier quoted context omitted.
Which of your 98 days here qualifies you to assess the peak of someone's contribution over a span of two years?
Look out everybody, this guy's been here for almost 1000 days!
Quickly looking over SoftLayer's price sheet, it looks to be a little over $1k a month for Intel 5670 with 24GB of RAM
I'm not really familiar with CPUs, but I got a hyperthreaded, quad core Xeon with 24 GB RAM, 750 2xRAID1 disks and 10 TB bandwidth from Hetzner for 60 euros a month... Isn't that comparable to what you mention, apart from being many times cheaper? http://www.hetzner.de/en/hosting/produkte_rootserver/ex5
http://ark.intel.com/compare/47920,37147
The Softlayer server is a Xeon, the Hetzner is a desktop grade processor.
Key differences for me
* Cache
* QPI (especially in a 2P config that makes a difference)
* Max TDP ... that's a HUGE one.
* ECC memory. See http://perspectives.mvdirona.com/2012/02/26/ObservationsOnEr... for why this is important
So, you're not comparing apples to apples
Sigh, another completely synthetic benchmark with big iron: A dual Intel Xeon X5670 with 24GB of RAM from SoftLayer. The X5670 has 6 cores @ 2.93 GHz, 2 threads per core, /proc/cpuinfo shows 24 CPUs. Serving a plain HTML page over localhost via nginx. A medium length blog post with pretty much no real-world information.
In a real world app, I think you'd be considered lucky if the web-server is your bottleneck, rather than your DB or network connection.
As someone who has only worked on extremely small sites, I've never had to deal with scaling/bottlenecks. Do you have any recommended reads on handling DB bottlenecks and the like so I can be prepared when that day comes? Thanks!
Earlier quoted context omitted.
As someone who has only worked on extremely small sites, I've never had to deal with scaling/bottlenecks. Do you have any recommended reads on handling DB bottlenecks and the like so I can be prepared when that day comes? Thanks!
Gregg Pollock made a series of videos (underwritten by RPM ( https://rpm.newrelic.com/) ), called Scaling Rails ( http://railslab.newrelic.com/scaling-rails ). It's phenomenal . That link shows the "contents" on the left-hand sidebar. Start at the bottom and work your way up the list.
Sigh, another completely synthetic benchmark with big iron: A dual Intel Xeon X5670 with 24GB of RAM from SoftLayer. The X5670 has 6 cores @ 2.93 GHz, 2 threads per core, /proc/cpuinfo shows 24 CPUs. Serving a plain HTML page over localhost via nginx. A medium length blog post with pretty much no real-world information.
Earlier quoted context omitted.
I'm not really familiar with CPUs, but I got a hyperthreaded, quad core Xeon with 24 GB RAM, 750 2xRAID1 disks and 10 TB bandwidth from Hetzner for 60 euros a month... Isn't that comparable to what you mention, apart from being many times cheaper? http://www.hetzner.de/en/hosting/produkte_rootserver/ex5
Not quite. Check this out http://ark.intel.com/compare/47920,37147 The Softlayer server is a Xeon, the Hetzner is a desktop grade processor. Key differences for me * Cache * QPI (especially in a 2P config that makes a difference) * Max TDP ... that's a HUGE one. * ECC memory. See http://perspectives.mvdirona.com/2012/02/26/ObservationsOnEr... for why this is important So, you're not comparing apples to apples