Intel patch hampers performance of AWS EC2 servers

AWS customers complain of server slowdowns following implementation of Meltdown patch

Users of Amazon Web Services (AWS) have complained that the patches rushed out to mitigate the risks of the Meltdown chip flaw affecting Intel microprocessors has dramatically affected the performance of their AWS instances.

Customers have complained online about the performance hit that, they say, is affecting their applications.

The complaints relate to a patch issued in December, which they claims has seen an increase in CPU utilisation from EC2 cloud servers. Amazon is aware of this and said it'll help users fix the problem.

Software fixes have been made available to Windows, Linux and MacOS PCs and servers that run on Intel processors. The patch is intended to seclude the OS kernel to a virtual memory space so it isn't exposed to cyber crooks.

However, this appears to be slowing systems down. It's not clear how many customers have been affected and, while Meltdown doesn't affect CPUs designed and produced by AMD, its server market share today is so low cloud users don't really have a viable alternative.

Online forums have been brimming with complaints. One customer wrote: "Five days ago I received [an] email from AWS (see below for full text) which informed me that a reboot of one of my instances was necessary due to 'updates'.

"To pre-empt auto-reboot on 5th Jan I manually rebooted 3 days ago. Immediately following the reboot my server running on this instance started to suffer from cpu stress."

Attempts to fix this flaw has proved almost impossible: "Looking at CPU stats there was a very clear change in daily CPU usage pattern, despite continuing normal traffic to my server," added the user.

"I performed extensive review of what might have changed on my server configuration but drew a complete blank - configuration of the server did not change."

Another user wrote: "This just happened to us today on a c3.large. The cost to us to move the platform to new hardware and the lost confidence from our customers is huge."

Cloud technology giant AWS confirmed these suspicions to The Register, saying: "We don't expect meaningful performance impact for most customer workloads.

"There may end up being cases that are workload or OS specific that experience more of a performance impact. In those isolated cases, we will work with customers to mitigate any impact."

The Meltdown and Spectre CPU architecture flaws were revealed this week following a series of article in The Register that exposed a series of chip flaws that manufacturers were reluctant to admit.

Operating system coders have been working since the middle of last year to design workarounds in OS kernels that can mitigate the risk posed by the flaws, but have admitted that performance could suffer as a result.