General WordPress performance info
After all static files to cdn and move javascript out of html header. I also enabled multi CNAME cdn to see whether it increase page loading speed(not enabled in my cdn plugin yet, still testing). Here is the resault,
It seems CSS loading will still block css background images even those included in main html header. I also used Varnish to front proxy WordPress, because WordPress becomes extremely slow after move database from MyISAM to InnoDB.
Updates: I found 2 website helping draw water fall chart. Pagetest by AOL and Site-Perf.com.
Updates 2: I partly solved css image not preloading problem by insert an invisible img tag like this,
<img src="http://m1.cdnyy.com/x/wp-content/themes/aeros/images/autumn.jpg" alt="" height="1" width="1" style="border:0;display:none" />
But this only work in Chrome. IE will not load any image before css loaded.
Look at loading time of autumn.jpg, near 200ms improvement in Chrome.
Yejun Web optimization, wordpress
Check this out.
If your wordpress comments log is filled with local ips, you may give a try.
Yejun Web comments, plugin, spam, wordpress
More cloud news this week.
Google just announced paid resources for GAE.
The price is similar to other cloud provider. Interesting is that they also charge 0.01 cent per email recipient .
Yejun Uncategorized
If you use my WordPress CDN plugin and amazon cloudfront, you may have problem putting files into s3 storage. Here is a simple way without using any commercial tool if you are using Linux.
First download s3sync . Extract it to somewhere. In this example I used my home directory.
Edit ~/.s3conf/s3config.yml, which should looks like this
aws_access_key_id: your s3accesskey
aws_secret_access_key: your secret key
Enter wordpress directory
cd wordpress
find * -type f -readable \( -name \*.css -o -name \*.js -o \
-name \*.png -o -name \*.jpg -o -name \*.gif -o -name \*.jpeg \) \
-exec ~/s3sync/s3cmd.rb -v put bucket:prefix/{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 \;Change bucket to your real bucket name. If you don’t need any prefix, do not include slash. Adjust cache-control header. ~/s3sync/s3cmd.rb should point to where you extracted s3sync.
Update 1: Don’t forget install mime-types if you Linux distro didn’t install it by default. Check whether /etc/mime.types exists.
Update 2: s3cmd.rb does not set content-type at all. I think python version does. Any way I wrote a script to redo everything.
#!/bin/sh
BUCKET=
#Set your bucket
PREFIX=
#If you want to use prefix set it like PREFIX=blog/
find * -type f -readable -name \*.css -exec ~/s3sync/s3cmd.rb -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:text/css \;
find * -type f -readable -name \*.js -exec ~/s3sync/s3cmd.rb -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:application/x-javascript \;
find * -type f -readable -name \*.png -exec ~/s3sync/s3cmd.rb -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/png \;
find * -type f -readable -name \*.gif -exec ~/s3sync/s3cmd.rb -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/gif \;
find * -type f -readable \( -name \*.jpg -o -name \*.jpeg \) -exec ~/s3sync/s3cmd.rb -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/jpeg \;Update 3: I just realized cloudfront does not gzip files. So I rewrote my script to force gzip encoding on css and js files.
#!/bin/sh
BUCKET=
#Your bucket
PREFIX=
#If you want to use prefix set it like PREFIX=blog/
S3CMD=/home/user/s3sync/s3cmd.rb
#Your absolute path to s3cmd.rb
find * -type f -readable -name \*.css -exec sh -c "gzip -9 -c {} > /tmp/s3tmp && \
$S3CMD -v put $BUCKET:$PREFIX{} /tmp/s3tmp x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:text/css Content-Encoding:gzip" \;
find * -type f -readable -name \*.js -exec sh -c "gzip -9 -c {} > /tmp/s3tmp && \
$S3CMD -v put $BUCKET:$PREFIX{} /tmp/s3tmp x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:application/x-javascript Content-Encoding:gzip" \;
find * -type f -readable -name \*.png -exec $S3CMD -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/png \;
find * -type f -readable -name \*.gif -exec $S3CMD -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/gif \;
find * -type f -readable \( -name \*.jpg -o -name \*.jpeg \) -exec $S3CMD -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/jpeg \;Update 4: 4/1/2009
I added function to copy a single file or single directory.
#!/bin/sh
if [[ -n $1 ]]; then
LOC=$1
else
LOC="*"
fi
BUCKET=
#Your bucket
PREFIX=
#If you want to use prefix set it like PREFIX=blog/
S3CMD=/home/user/s3sync/s3cmd.rb
#Your absolute path to s3cmd.rb
find $LOC -type f -readable -name \*.css -exec sh -c "gzip -9 -c {} > /tmp/s3tmp && \
$S3CMD -v put $BUCKET:$PREFIX{} /tmp/s3tmp x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:text/css Content-Encoding:gzip" \;
find $LOC -type f -readable -name \*.js -exec sh -c "gzip -9 -c {} > /tmp/s3tmp && \
$S3CMD -v put $BUCKET:$PREFIX{} /tmp/s3tmp x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:application/x-javascript Content-Encoding:gzip" \;
find $LOC -type f -readable -name \*.png -exec ${S3CMD} -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/png \;
find $LOC -type f -readable -name \*.gif -exec ${S3CMD} -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/gif \;
find $LOC -type f -readable \( -name \*.jpg -o -name \*.jpeg \) -exec ${S3CMD} -v put $BUCKET:$PREFIX{} {} \
x-amz-acl:public-read Cache-Control:max-age=604800 Content-Type:image/jpeg \;For example if you saved this script to a file name cloudfront:
cd wordpress
cloudfront wp-content/uploads
Without any command line argument this script will upload all file under current directory.
Yejun Linux, Web amazon, aws, cloudfront, s3, s3cmd, s3sync
Finally transfered my domain from 1&1 to gkg.net as I blogged a couple days ago.
My IPv6 tld glue record was inserted into .net tld DNS server instantly from gkg.net web interface. Highly recommend gkg as domain registrar.
IPv6 Badge
Yejun Linux domain, ipv6, registrar
RSS
Follow