High Performance Blogging

WP Smush.it Plugin integrates smush.it with wordpress

April 19, 2009 in Wordpress Optimization | No comments

Yahoo’s excellent Exceptional Performance series recommends optimizing images in several lossless ways:

* stripping meta data from JPEGs

* optimizing JPEG compression

* converting certain GIFs to indexed PNGs

* stripping the un-used colours from indexed images

Smush.it offers an API that performs these optimizations (except for stripping JPEG meta data) automatically, and this plugin seamlessly integrates Smush.it with WordPress.

via WordPress › WP Smush.it « WordPress Plugins.

The State of Unreleased Browsers on V8 rev3: IE8 looks silly

February 7, 2009 in Benchmarks, Programming | 1 comment

I particularly like the regexp benchmark in google’s new revision of V8.

I will do more comparisons with different benchmarks but here is a quick update on the state of alpha browsers regarding the V8 benchmark on windows.

Test system: Mac Pro Early 2006: 2x Dual Core Xeon 5150 (2.66GHz), 3GB RAM, Vista x64 SP1.

Benchies!

IE8 RC1 64-bit on Google's V8 benchmark Revision 3

Firefox 3.2a1 32bit 200907033501 on V8 benchmark revision 3

Webkit rev. 40730 on V8 Benchmark revision 3

Chromium 32bit rev9376 on Google's V8 Benchmark Revision 3

TechReport Invalidates A Test

January 30, 2009 in Benchmarks | No comments

TechReport did a review of 4 intel X25-E in a RAID0 setup (A look at four X25-E Extreme SSDs in RAID – The Tech Report).

image courtesy of TechReport :)

However, there were some problems with the testing method.

RAID-0 of physical drives is dumb. Nobody should use it, for any reason, unless the drives underneath are mirrored. Benchmarking this is a bit like benchmarking how fast you can piss into the wind… not only do you get pee on yourself, nobody else cares.
Windows XP’s caching algorithms make bad assumptions about disk configuration. It assumes you are using platter-based disk drives. Try the whole suite again with vista x64 sp1 (and with/without “advanced performance” mode enabled in the device manager, you should see completely different numbers.
Also, this is a PCI-E x8 card, but it seems like it is in a PCI-E slot. PCI-E x1 = ~640MB/sec minus a little for striping (200MB/sec) = ~450MB/sec peak, which seems to be what you are seeing. I have four of those drives in a server with two separate controllers on x8 slots in RAID0 of a pair of 2-drive RAID1s and see ~500MB/sec reads with OS caching disabled: this is what I would expect with two effective drives worth, not four.

Note that, when I went to register for an account to comment there, it gave me an error, so I decided to blog about it instead.

HOWTO: use a PC GeForce 9800GTX+ in a real Mac Pro

January 28, 2009 in Mac, Software | No comments

UPDATE: I would highly suggest using netkas’ new universal ATI/NVIDIA injector.

Obtain a card that uses one or two 6pin PCI-Express connectors for power.
Step 2: obtain two ATI mac PCI express power adapters ($30) or make your own for $10.
Install this version of NVkush if you have a 512MB card. if it’s some other size, you may have luck by using diabolik’s NVkush plister. I only had to mess with nvkush in order to make this work, no other kexts required editing in 10.5.6.
rename AppleTyMCEDriver.kext to AppleTyMCEDriver.disabled
rename AppleUpstreamUserClient.kext to AppleUpstreamUserClient.disabled
boot with the display connected to your old 7300GT. ~~If NVkush has done its thing, your screen on your 7300GT might be rotated 90 degrees. this is ok.~~ [fixed in 10.5.7]
switch display to 9800GTX+
~~if you have a “hole” covering the top left portion of the screen that you cannot see, switch display back to 7300GT, wait to see your desktop background, and switch back.~~ [fixed in 10.5.7]
Check system profiler for quartz extreme and core image support.
ENJOY!!!

xbench real mac pro with PC 9800 GTX+ Xbench score

Click through for video proof that it works ;)
Read the rest of this entry »

The Basics of Reading a Website Performance Waterfall Graph

January 13, 2009 in Benchmarks, Programming, Wordpress Optimization | 2 comments

When you’re using various tools to get information on what exactly is making your website slow, the most common method to display detailed information is a waterfall graph.

In this article, I will show you some tools that provide waterfall graphs and also give an explanation of how to read a simple waterfall graph.

Read the rest of this entry »

How to Read a Website Performance Table

January 13, 2009 in Benchmarks, Programming, Wordpress Optimization | No comments

Services and tools such as AOL WebPageTest will provide you with graphs and punchlists of things you need to fix.

Here is how you read them!

Load time is the time that it took to transfer ALL of the page, and for it to stop transferring.

First byte is “how long it took for the beginning of the page to be sent to the browser”

“Start render” is “When the user begins to see a page form.”

Document complete is when the document is usable.

Fully loaded includes anything that loads after Document Complete, such as AJAX calls.

“Requests” are the number of items that had to be sent individually to the browser.

“Bytes in” is the total size of items that had to be sent to the browser.

	Load Time	First Byte	Start Render	Document Complete	Fully Loaded	Requests	Bytes In
First View	4.752s	0.301s	2.558s	4.752s	4.752s	16	590 KB
Repeat View	0.674s	0.425s	0.238s	0.674s	0.920s	6	1 KB