Dennis Gorelik

We host 2 PostJobFree servers on SoftLayer (in their Dallas datacenter).
In the last year I started to get more and more warning signs that SoftLayer is slowly decaying (after acquisition by IBM 3 years ago).
So, finally, I decided to check how good is uptime of https://www.softlayer.com/

So I created a new "Keyword" monitor on https://uptimerobot.com
The monitor checks if "Data Centers" wording was rendered into SoftLayer's home page HTML.
UptimeRobot runs that check every minute.

So, how much uptime does the legendary hosting is able to keep for their web site?
According to UptimeRobot, SoftLayer's home page uptime is a pathetic 99%.
That means that there is 1% change that Softlayer home page is down at any given moment.
Among hosting providers, uptime below 99.9% is considered poor, and uptime above 99.99% is considered good.

According to UptimeRobot, when SoftLayer's home page is up, it has average response time of 681.72ms (about 0.7 seconds, which is kind of OK).

To put things in perspective: PostJobFree home page (that is hosted on dedicated server in SoftLayer) has 100% uptime (99.99%+) and 139ms average response time.



So for now our dedicated servers on SoftLayer still work, but if SoftLayer tech team keep deteriorating, they would eventually mess up their core network too, and then it would bring downtime to our servers as well.

So I am looking for a new hosting provider now.
Would you recommend any?

We moved our ElasticSearch job percolation functionality from Windows server to ElasticSearch cluster on two Linux VPS-es (3GB RAM + 2GB RAM).
Percolation performance improved at a fraction of hosting price (relative to price of dedicated Windows server).
The most important benefit is that we can increase percolation performance just by adding more nodes to our ElasticSearch cluster.
Performance of individual percolation query on ElasticSearch cluster is about the same as on single node, but adding more nodes to ES cluster allows to execute more queries in parallel.
From our experimentation we determined that optimal number of percolation queues on 2-node cluster (2 CPU cores on each node) is ... drum-roll ... 4 (1 for each CPU core).

That configuration allows us to percolate up to 216 jobs per minute.

Q: What is ElasticSearch percolation?
You may create a job search alert.
PostJobFree will put your alert alongside with 160K+ other users' job alerts into ElasticSearch job percolation index.
Then every time when we get a new job - we percolate that job against 160K records in job percolation.
If job matches your (or anyone else's) job alert, then ElasticSearch percolator returns IDs or all these alerts, so we know to send you email about new match.

Q: Why host ElasticSearch on Linux?
Windows version of ElasticSearch does not support mlockall setting. That means there is no good way to prevent ElasticSearch from using swap-file.