Back in November we wrote a blog post about one latency spike. Today I'd like to share a continuation of that story. As it turns out, the misconfigured rmem setting wasn't the only source of added latency.
It looked like Mr Wolf hadn't finished his job.
After adjusting the previously discussed rmem sysctl we continued monitoring our systems' latency. Among other things we measured ping times to our edge servers. While the worst case improved and we didn't see 1000ms+ pings anymore, the line still wasn't flat. Here's a graph of ping latency between an idling internal machine and a production server. The test was done within the datacenter, the packets never went to the public internet. The Y axis of the chart shows ping times in milliseconds, the X axis is the time of the measurement. Measurements were taken every second for over 6 hours:

As you can see most pings finished below 1ms. But out of 21,600 measurements about 20 had high latency of up to 100ms. Not ideal, is it?
The latency occurred within our datacenter and the packets weren't lost. This suggested a kernel issue again. Linux responds to ICMP pings from its soft Continue reading
Follow these best practices to ensure optimal enterprise WLAN performance.
Veriflow aims to prevent breach network breaches resulting from configuration errors.
Everyone loves to talk about business critical applications that require extremely high availability, but it’s rare to see someone analyze the whole application stack and identify the weakest link.
For more details, watch my Designing Active/Active and Disaster Recovery Data Centers or attend one of my workshops.
If you start mapping out the major components of an application stack, you’ll probably arrive at this list (bottom-to-top):
Read more ...I’m happy to be given the opportunity to speak once more at Interop Vegas in 2016. No workshop for me this year, but I will be putting on three individual talks, all focusing on topics that have been very near and dear to me over the past year.
Last year I was very focused on putting the theory behind network automation into practical terms, and making it “real”. Over the past year I’ve seen rapid growth in adoption of these ideas, and I was happy to be just one very small part of helping to make that happen.
Since the last Interop, my career has steered me towards a more direct approach to network automation, specifically through software development. So I’d like to spend some time providing an overview of my sessions at the upcoming Interop Vegas 2016, which are all inspired by the last year of my career.
I am obviously very passionate about network automation, and have been very vocal about my belief that network automation only has a chance if it is done properly, which includes proper testing. I strongly believe that network automation can and should take place within the context of a Continue reading
Brocade's stock drops 14% on the announcement.
Take survey and enter to win one of two $200 Amazon Gift Cards.