Terrible TTFB with nginx+hhvm (10s+)

Yesterday morning I upgraded my HHVM version from 3.6.1 to 3.7.0. As far as I can tell by my memory, the dpkg logs, and my Git diff of the /etc directory, this was the only change that occurred on my system.

Before the update, my sites were loading in under two seconds. I tested in a variety of ways including my standard goto - webpagetest.org

After the update, my sites were taking anywhere from between two seconds to twenty seconds to load, most of that time waiting was for the initial time-to-first-byte.

I realize that TTFB can be misleading, but I'm also sure that ten seconds indicates that something is very wrong.

Does anyone know a good way to start debugging this issue? I've spent quite a bit of time already double-checking configurations and backtracking but nothing seems to be making a difference. The installation is fairly standard and the websites are running WordPress 4.2.1

Thanks in advance for your help.

2 Replies

Hi dmsnell,

Were you able to figure out what the problem is?

I am having the same issue.

Thanks!

Unfortunately @trav326 I wasn't able to debug it. I think that the official suggestion was to create a new Linode instance and install everything from scratch and see if the problem still existed, which was too much work for me to do. I mangled some other things and was able to get the load time reasonable but I haven't checked in some number of months.

Did this start for you on a normal update as well?

Reply

Please enter an answer
Tips:

You can mention users to notify them: @username

You can use Markdown to format your question. For more examples see the Markdown Cheatsheet.

> I’m a blockquote.

I’m a blockquote.

[I'm a link] (https://www.google.com)

I'm a link

**I am bold** I am bold

*I am italicized* I am italicized

Community Code of Conduct