Search results

At the very least run your second test much longer than fastcgi_read_timeout 180;  Double check whether your steady state 200 response rate is lower than FCGI.

Yes, PHP-FPM won in the first.  Hardly a 10-X win you're making it out to be.  The second batch set with Apache vs Nginx is an example of looking at what the bottlenecks are and eliminating the non-relevant ones.  Removing .htaccess from Apache takes the web listener out of the equation and as...

Isn't this akin to asking what is a cloud?  what is a vps hoster?  There are standards and certifications, but not everybody subscribes to those definitions.  For some markets, it's unnecessary as long as the need is satisfied. Yes.  http://www.datapod.com.au/datapod There's a whole boatload...

Is your FCGI graph using the same number of children?  What's your process recycling set at?  Those would be the first I'd look at, but I know there's something off about your benchmarks. Numerous other people have benchmarked PHP CGI, PHP FCGI and FPM next to each other to determine if there...

Let's say we get 20 requests/s.  In FPM, it pushes 20 into the queue.  In the FCGI, it roundrobins any free child process.  If none are able to accept, it 500's immediately. Let's say your CPU can handle 10 PHP requests at any given time (and no FPM isn't faster).  After that first second, we...

Did you bother to look at the FPM queue backlog while running the tests?  The fun part with benchmarking FPM throughput is that unless you're using response time percentiles (not just raw throughput) you're missing out on a lot of how it works.  Default FPM has a limitless queue length that will...

'atta boy!  Show'em how we here fight in these neck of the d'net!

Pfft.  http://www.computerworld.com/s/article/9083478/Image_gallery_Space_Shuttle_i_Columbia_s_i_hard_disk_drive 7.77 km/s

There's a whole lot of bigger fish that are doing the verticals game (in hosting and out of it).  Dunno why it's such an issue - in each of those cases the market is far bigger than the toe-dip that the 'solutions' subsidiary can handle.  In almost all cases, they also don't undercut the...

The fact that it requires an 'and' in the domain name makes it worthless.  jewlery-gift.com will rank just as well if you were one of those that still think keywords in domain names count.  Stop words and all that jazz. edit: probably vying for the equivalent of the internet bridge / swampland...

I find it much more entertaining to chart gold spot prices against a reconstructed world stock index. On that chart, if you pulled out past 2004 it actually has quite a long term decline. It only started to recover during the 2005 ECB flustering. If you want to rationalize gold, I've found it...

It's actually based on the NPV of all future dividends (notional or real). And the futures curve gives a pretty good inkling of what the other 6 billion people actually think at any point in time. PE ratios and fundamentals are useful as paper napkin guides though. The hard part is that the...

Do this long enough and you realize that only one thing drives the market - the interest rate curve.  Everything else is just noise. edit: just to say something worthwhile... for BBY, be sure to look at its quick ratio.   It's current isn't that good either.  It's priced down for a good reason.

The 3.5.1 advisories all relate to user generated content.  Their blog doesn't allow signups from what I can tell.

The recent cold snap in NA is due to the polar vortex wobbling further south than usual due to the lessening of the temperature gradient in the arctic regions.  It's basically a cyclone that's powered and kept in place by the differential.

Good to hear you finally got it working.

Your blurry vision's probably contributing to the headaches. If you can, get someone to randomly take pics of you working at the computer from the side. You don't want to see any cantilevering. I,e slouching, leaning forward, arms outstretched etc. The bulk of your torso mass should be right...

As far as I can tell, it's 3.2 that brought in the bandwidth control (the hard cap) on top of the old bandwidth scheduler.  Maybe that's where your trouble lies.  There were a couple patches floating around before that circa 2011 if you want to try those.

Please check your kernel compilation options CONFIG_FAIR_GROUP_SCHED=y CONFIG_CFS_BANDWIDTH=y And here.  Follow this http://www.blaess.fr/christophe/2012/01/07/linux-3-2-cfs-cpu-bandwidth-english-version/

Fair enough.  Although if I wanted to sell under Proxmox, and I had already spent the money for the SAN required for HA, along with the fencing devices, I'd probably want to buy the VE Enterprise repo subscription too :)  Besides, I'm still waiting for DRS/VCB like things on Proxmox though :P...