Our site is slow..
-
We have noticed that our site is much slower than many of our competitors and expect that this is affecting our organic ranking.
We are on dedicated UK Fast server with
[20/08/2013 16:44:35] Tony Jackson: Operating System: CentOS 6 64-bit
CPU: 1x Intel Xeon E5-2620 @ 2.0GHz
Memory: 8x 8GB DDR3 RDIMM
Hard Drive: 4x 128GB SSD RAID10
[20/08/2013 16:46:28] Tony Jackson: Nginx, percona, tomcat/solr, Magento CE, cat: 25200 productsI could really do with your thoughts on this page for example
http://www.pretavoir.co.uk/sunglasses/ray-ban-sunglasses.html
-
I am not a huge fan of APC at present (PHP PECL library, not the power battery company). Maybe nginx won't segfault like Apache has been for us.
As for the hosting, what I mean is to use a load balancer with multiple servers. Will you take some performance hit in getting DB data? Probably, but very little. But you're getting far worse now with Magento so it doesn't matter how fast your machine is (like I said, it's a beast so if it's not sitting at 0.01 almost all the time you've got major issues). Remember that this impressive machine is also a single point of failure. I had an impressive box running our DB once (multiple webservers) and the RAID controller crapped out in the middle of the day. We got back up under the two hour SLA but it cost us a lot of sales.
Now we run two webservers, a multi-AZ DB (automatic failover to secondary if master dies) and all behind a load balancer in AWS. I won't pretend this isn't without any issues (we wound up in an odd instance where the DB failover didn't work as expected) but it's a lot more redundant and scalable. I bet our setup is cheaper than your behemoth, too. Remember, you still have to chew through all the code each and every time the page is loaded (your problem is processing the individual thread, not horsepower). Splitting your site amongst multiple webservers means you have scalability as well.
-
Highland, Thank you for the response.
We are using memcached locally as it seems to give best results, having tried a combination of APC and memcached.
Would moving our database to a different server speed up the time to first byte(ttfp) as currently we sit with very little load on cpu? What would be the benefit?
Where you mention 'a cloud based solution' are you referring to using Cloudflare to sit in front of our server to act as a cdn and cache, or to move to a complete cloud based solution? I assume it is their Business package you refer to which gives the ddos and other protection.
Looking at Googles pagespeed tools, out ttfp seems to be the hold-up. which then just leaves the off site code (Snapenage, Comodo, etc) bringing up the last elements.
-
Thanks for this response.
We had been looking at Cloudflare and also at rearranging our server somewhat. Will let you know.
-
Magento is built on top of Zend Framework 1, a notoriously slow PHP framework. It also does some things that slow it down. Some thoughts...
- Be sure your use the Magento caching system.
- Move your database off to another machine. 25k products is a LOT
- Your hosting setup is monolithic. While your box is a beast of a machine (12 threads, 64GB RAM, 4x 128GB SSD) it's still susceptible to slow-down. I bet 50 concurrent users could bring it to its knees. While CDNs can help offload some of this, I recommend the beast with a cloud based solution. I bet you could get 2 or 3 servers plus a DB server for less than what you're paying for this one beast. Then put your machines behind a load balancer. So you would have multiple web servers serving your site up, a load balancer routing traffic to the fastest one and a common DB powering it.
- Switch to Cloudflare for your DNS. They will cache pages for you and they do it for free. They also add a layer of security.
- Use WMT to benchmark your site speed. It tells you the load time in a handy graph. Play around with it and see what happens.
-
We are using Magento on Nginxwth caching enabled with memcache
-
Generating the page seems to take very long. What shopping cart software are you using? Can it cache pages?
-
Thanks for your reply.
This page is a better example of our problem
http://www.pretavoir.co.uk/sunglasses/ray-ban-sunglasses.html
-
Your website isn't that slow from London but there lots of things you can do to improve speed:
1. Use a CDN like NetDNA to host CSS, Javascript and images. By using a CDN, you will also increase the number of simultaneous (parallel) downloads since these files will be hosted on another (sub)domain.
2. You have lots of Javascript files. Try combining them into one file.
3. Add a cache header, this will instruct web browsers to cache your images, css and Javascript files. Simply add this to your .htaccess file:
AddType image/x-icon .ico
<ifmodule mod_headers.c=""># YEAR
<filesmatch ".(ico|gif|jpg|jpeg|png|flv|pdf)$"="">Header set Cache-Control "max-age=29030400"</filesmatch>WEEK
<filesmatch ".(js|css|swf)$"="">Header set Cache-Control "max-age=604800"</filesmatch>
24 HOURS
<filesmatch ".(html|htm|txt|php)$"="">Header set Cache-Control "max-age=86400"</filesmatch></ifmodule>
======================================================
... and sorry for my english.
Hope that helps!
-
Yes had looked at GT Metrix though not paid much attention to YSlow. Will take a look now.
However it may be of more interest to look at the speed of this page rather than homepage;
http://www.pretavoir.co.uk/sunglasses/ray-ban-sunglasses.html
-
Hi Sean,
Your system looks pretty decent... I guess it depends on your traffic load though.
Have you checked out your results on GTMetrix.com?
You scored well in the PageSpeed testing, but not in YSlow. I'd take a look and see if you could leverage some of the suggestions there.
Hope this helps.
Mike
Got a burning SEO question?
Subscribe to Moz Pro to gain full access to Q&A, answer questions, and ask your own.
Browse Questions
Explore more categories
-
Moz Tools
Chat with the community about the Moz tools.
-
SEO Tactics
Discuss the SEO process with fellow marketers
-
Community
Discuss industry events, jobs, and news!
-
Digital Marketing
Chat about tactics outside of SEO
-
Research & Trends
Dive into research and trends in the search industry.
-
Support
Connect on product support and feature requests.
Related Questions
-
Problem on my site
Hello, thank you for guiding me
Competitive Research | | kaajshop 0
I had a problem with the speed of the site. I do not know how to solve this problem
this page:https://kaajshop.com/cat/700 -
2 sites with low DA and PA and unoptimised <title>outranking everyone for competitive search term - How ?</title>
Im doing some keyword research for a new client, Ive found 2 anomalies for competitive search terms where sites with unoptimised <title>tags, poor backlinks and other stats, (compared to the other sites listed in the SERP) are out ranking everyone and claiming the #1 spot</p> <p> The 2 search terms are :</p> <ul> <li dir="ltr"> <p dir="ltr"><a href="https://www.google.co.uk/search?q=interior+designers+london&oq=interior+designers+london&aqs=chrome..69i57j69i65j69i60j69i65l2j69i60.2784j0j1&sourceid=chrome&ie=UTF-8">Interior designers London</a>- #1 new-id.co.uk - <a href="https://moz.com/researchtools/ose/links?site=new-id.co.uk&filter=&source=external&target=page&group=0&page=1&sort=page_authority&anchor_id=&anchor_type=&anchor_text=&from_site=">OSE info</a></p> </li> <li dir="ltr"> <p dir="ltr"><a href="https://www.google.co.uk/search?q=interior+designers+london&oq=interior+designers+london&aqs=chrome..69i57j69i65j69i60j69i65l2j69i60.2784j0j1&sourceid=chrome&ie=UTF-8#q=interior+designer+london">Interior designer London</a>- #1 nstudio.co.uk - <a href="https://moz.com/researchtools/ose/links?site=http%3A%2F%2Fnstudio.com%2F&filter=&source=external&target=page&group=0&page=1&sort=page_authority&anchor_id=&anchor_type=&anchor_text=&from_site=">OSE info</a></p> </li> </ul> <p> (interestingly they hardly rank at all for any modification of those search terms)</p> <p> The only thing i could think of is that they both had some really good links using that exact anchor text, but ive been checking OSE for the past month both in the backlinks and the just discovered but couldnt see anything like that.</p> <p>I conducted the SERP checking from a laptop with a broadband connection based in London, although im not very local to either of these locations im about an 8th of the cities distance away from one of those location and about half a cities distance away from the other. So i dont think its a local skew thats causing the SERP rankings.</p> <p>For both sites i can see they had old domains which now redirect to the them :</p> <ul> <li dir="ltr"> <p dir="ltr"><span data-mce-mark="1">New-id.co.uk = </span><span data-mce-mark="1"><a href="http://newidinteriors.com/">newidinteriors.com</a> - <a href="https://moz.com/researchtools/ose/links?site=http%3A%2F%2Fnewidinteriors.com&no_redirects=1&filter=&source=external&target=page&group=0&page=1&sort=page_authority&anchor_id=&anchor_type=&anchor_text=&from_site=">OSE info</a> - PA1, DA1</span></p> </li> <li dir="ltr"> <p dir="ltr"><span data-mce-mark="1">Nstudio.co.uk = intarya.com - <a href="https://moz.com/researchtools/ose/links?site=www.intarya.com&filter=&source=external&target=page&group=0&page=1&sort=page_authority&anchor_id=&anchor_type=&anchor_text=&from_site=">OSE info</a> - Da 32, PA43</span></p> </li> </ul> <p> Although the intarya domain was quite strong with good backlinks (but nothing above par comapred to the other sites the nstudio.co.uk site is now outranking, the anchor text was mostly natural with only some keyword anchor text from PA1 pages. </p> <p>The <a href="http://newidinteriors.com/">newidinteriors.com</a> didnt seem to have a backlink profile, both PA1 and DA1.</p> <p> Ive taken screenshots of the SERP pages below, but feel free to dig further</p> <p>Any idea what's going on here ?</p> <a download="HWkjmDf.png" class="imported-anchor-tag" href="http://i.imgur.com/HWkjmDf.png" target="_blank">HWkjmDf.png</a> <a download="A70jXse.png" class="imported-anchor-tag" href="http://i.imgur.com/A70jXse.png" target="_blank">A70jXse.png</a></title>
Competitive Research | | mike8780 -
Help! New site won't rank locally but should...
any help would be greatly appreciated... picked up a new client, a used car dealer in New Jersey. Have a VERY spammy site before, tons of keyword stuffing and lots of dupe content. also had a horrible design. (www.coopscars.com) We updated the design and the content, made it relevant and unique, fixed title tags, etc. Now he's not ranking for anything locally other than his business name. He's got a decent number of links, we've added relevant citations, his social signals are much stronger than they were... We do lots of SEO for car dealers, and we know that he should be ranking SOMEWHERE at this point - not saying he should be page 1, but he should at least be somewhere in the top 5... and yes, bing/yahoo are different, but he ranks over there... one page 1 for "used cars south river" - so why completely non-existant on Google? just as a test, he put up a free website at www.coopscars.net just last week - and it's already ranking for several local terms. I'm completely confused here - i'm not a noob, I know the tactics we've used on him work for other dealers. Thinking there's got to be something that's blocking him, especially since there aren't but maybe 15-20 car dealers to compete against locally and he still doesn't show up... thought i'd come over here and see if anyone has any ideas...
Competitive Research | | Greg_Gifford0 -
Working through the slides on my first seo project, I'm trying to determine the most popular content on competition sites.
From the video, I understand I should be looking for unique opportunities. But is there a baseline for product qualification, ie., a min. PA,LRD, Inbound LInks, social shares, etc. I guess I'm asking what I should be looking for in the data provided on each competing site? What determines THE most popular and unique product?
Competitive Research | | AhmadS0 -
Site Ranks Better than Comp...but why?
My site is ranking better than some of the competition sites even though the Moz Rank and Moz Trust are lower, anyone know why?
Competitive Research | | CalgaryRealtor390 -
Sites With Duplicate Content Ranking Way Higher
The site I am writing about is easendtorontohomes.com I don't get it. I see that some of my competitors have more inbound links and have been around longer. Their SEOmoz trust etc is also higher. But I don't get how many could possibly be ranking higher since they're sites are all template based site via Web Tech Design and the content is duplicated from one to the other. The other weird thing is that they do everything wrong - they stuff their keywords tag, some of them use the same keywords/meta data on every single page, some of them don't even have meta tags, some of them don't even have a blog with ANY original content. Apart from listings EastEndTorontoHomes.com has TONS of original, well-researched, and keyword rich content. I just don't get it. Is it possible that google has some sort of relationship with that company? Or am I totally missing something? Some of these sites include: tinasmith.ca, mikeclarke.com, teamkassen.com
Competitive Research | | annasus0 -
Keywords in URL structure for Large Site
We are creating a national real estate website which will contain 2mil+ listings. Our aim is to compete with the National leaders in the field. We are trying to lock down a url structure and it basically comes down to if we should put a major keyword in the url structure or not. The structure would have regional keywords naturally. Its the addition of a more descriptive key word which is in question. Our domain name has no keywords in it. For the sake of this example, we would be targeting "city real estate"... oursite.com/real-estate/state/city/ or oursite.com/state/city/ Here is what the big sites use as an example: http://www.zillow.com/homes/for_sale/New-York-NY/ http://www.trulia.com/NY/New_York/ http://www.trulia.com/real_estate/New_York-New_York/ http://www.realtor.com/realestateandhomes-search/New-York Id love to not have to throw keywords in there and be as clean as possible but i also dont want to shoot myself in the foot. The big boys do add additional keywords in the url, does that mean we should? Id much rather be a leader than a follower but again, I dont want to mess this up from the start and these guys have probably tested this (or have they?). Input would be greatly appreciated.
Competitive Research | | cobbsfriedman0 -
Image only site on top of Google
Hi Everyone, I'm trying to rank in Google for 'Hid xenon' in the netherlands, but there is one site above all results: http://bit.ly/qlsjne As you can see the site almost has no backlinks, and has not a single word in it's content, all images. it's a keyword only domain, and that's probably the only reason why it's ranking that high, but that means then that i can never get higher then him in Google because of it's domainname? Even when it's such a shitty site? Thank you, regards yannick
Competitive Research | | iwebdevnl0