Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#1

Post by zasgar » Thu, Oct 01, 2020, 4:18 PM UTC

Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF
pixielabs.ai

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#2

Post by devangs » Thu, Oct 01, 2020, 6:18 PM UTC

Having used an earlier version of this, I highly recommend it if you're carrying a pager in micro-service land, and don't have Brendan Gregg on your team.

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#3

Post by airocker » Thu, Oct 01, 2020, 6:24 PM UTC

Would love to see intrumentation without any code changes. Is it possible to write EBPF based tracers for JVM and Node/Python interpreters?

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#4

Post by blasrodri » Thu, Oct 01, 2020, 6:35 PM UTC

airocker wrote: post #3

Would love to see intrumentation without any code changes. Is it possible to write EBPF based tracers for JVM and Node/Python interpreters?

Check bcc-tools: https://github.com/iovisor/bcc/tree/master/tools

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#5

Post by zasgar » Thu, Oct 01, 2020, 6:37 PM UTC

airocker wrote: post #3

Would love to see intrumentation without any code changes. Is it possible to write EBPF based tracers for JVM and Node/Python interpreters?

Co-founder/CEO of Pixie here.

EBPF allows you to access static tracepoints that are defined in many runtime, and can be used to capture information about the state of the runtime.

Since most VM’s/runtimes allow monkey patching you can usually get to the same level of information without using EBPF. We plan to add support for this in Pixie in the future and provide a seamless experience regardless of what underlying tracing technology is used.

Lots of good stuff from Brendan Gregg here: http://www.brendangregg.com/Slides/Velocity2017_BPF_superpow...

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#6

Post by djstein » Thu, Oct 01, 2020, 8:08 PM UTC

this is really amazing. the marketing page is also top notch from a visual perspective

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#7

Post by kahrensdd » Thu, Oct 01, 2020, 8:09 PM UTC

I love the idea of instrumenting my clusters with less work. Signed up for the BETA and starting to get data out of one of my GKE clusters right away. Also I like how the cli just interacted with the cluster itself instead of tons of piping the output to other commands. Good luck Pixie team!

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#8

Post by hapless » Thu, Oct 01, 2020, 8:52 PM UTC

I closed the tab as soon as I saw "bash -c "$(curl ..."

Fuck that, forever. That is a waving red flag that the authors are targeting users too foolish to have any business using a computer.

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#9

Post by meddlepal » Thu, Oct 01, 2020, 8:56 PM UTC

hapless wrote: post #8

I closed the tab as soon as I saw "bash -c "$(curl ..." Fuck that, forever. That is a waving red flag that the authors are targeting users too foolish to have any business using a computer.

Lol. I love how irrationally upset people get about this.

How is this any worse than downloading a random tarball and running a makefile blindly or installing a deb with god knows what pre or post scripts exist.

If youre that concerned download it and read the script.

Re: Show HN: Pixie, Instant Kubernetes-Native Application Observability Using EBPF

#10

Post by oazizi » Thu, Oct 01, 2020, 9:30 PM UTC

airocker wrote: post #3

Would love to see intrumentation without any code changes. Is it possible to write EBPF based tracers for JVM and Node/Python interpreters?

Founding engineer at Pixie here.

To add to what zasgar mentioned, I just wanted to point out that our instrumentation-free approach does apply to JVM and Node/Python applications for many of the traces we gather. For example, we use EBPF to trace protocols like HTTP as the data passes through the kernel. By gathering the data in the kernel, these EBPF tracers are completely language agnostic.