In March 2018, Intel very kindly donated to my group a Terasic DE5a-Net Arria 10 GX FPGA Development Kit, though the Intel FPGA University Program. In this post, we document our initial experiments with the FPGA boards.

My notes for the course “Reliable Cloud Infrastructure: Design and Process” (Course 6 of “Architecting with Google Cloud Platform”) on Coursera.

My notes for the course “Elastic Cloud Infrastructure: Containers and Services” (Course 5 of “Architecting with Google Cloud Platform”) on Coursera.

My notes for the course “Elastic Cloud Infrastructure: Scaling and Automation” (Course 4 of “Architecting with Google Cloud Platform”) on Coursera.

My notes for the course “Essential Cloud Infrastructure: Core Services” (Course 3 of “Architecting with Google Cloud Platform”) on Coursera.

My notes for the course “Essential Cloud Infrastructure: Foundation” (Course 2 of “Architecting with Google Cloud Platform”) on Coursera.

My notes for the course “Google Cloud Platform Fundamentals: Core Infrastructure” (Course 1 of “Architecting with Google Cloud Platform”) on Coursera.

In this post, we document how we installed and configured BBCP on pulpo-dtn.

In this post, we describe how we installed TensorFlow 1.4 on the 4-GPU workstation Hydra.

In this post we explore running Pods on PRP Kubernetes cluster.

Rook is an open source orchestrator for distributed storage systems that currently focuses on orchestrating Ceph on top of Kubernetes.

In this post, we take a look at security on the PRP Kubernetes cluster.

I’ve obtained 2 Kubeconfig files for access to the PRP Kubernetes cluster.

PRP (Pacific Research Platform) has recently deployed a distributed Kubernetes cluster, as part of the CHASE-CI project funded by the NSF.

In this post, we describe how we installed TensorFlow with Anaconda on the 4-GPU workstation Hydra.

My notes for the course “Scalable Microservices with Kubernetes” on Udacity.

In this post, we describe how to compile and run Dr. Stephan Stellmach’s PADDI code on the Stampede2 supercomputer.

There are 2 ways to login to TACC supercomputer Stampede2 supercomputer.

I’ve recently designed and built a Visualization Wall for UCSC library.

Does MPI-IO works with CephFS?

In the post, we document the network tuning we’ve done for the nodes in the Pulpos cluster.

In this post, we describe how we cleanly installed Ceph v12.2.1 (codename Luminous) on the Pulpos cluster.

In this post, I document how I installed FUSE for macOS on my iMac.

In this post, we describe how to mount a subdirectory of CephFS on a machine running CentOS 7, particularly how to mount a subdirectory of our Luminous Ceph filesystem on the 4-GPU workstation Hydra.

If a user’s login shell is /sbin/nologin, would su, sudo or ssh honor it?

A white box switch, QuantaMesh BMS T3048-LY2R, provides networking connectivity to the Ceph storage cluster Pulpos. We runs Pica8 PicOS on the switch.

In this post, we document how we aggregated two 1GbE network interfaces into a logical bonded interface, on the 4-GPU workstation Hydra.

In this post, we document how we aggregated two 10GbE network interfaces into a logical bonded interface, on on pulpo-dtn.

In this post, we document how we installed Globus Connect Server on pulpo-dtn.

There are 4 GeForce GTX 1080 Ti in the 4-GPU workstation Hydra:

In this post, we document how we installed Docker on the 4-GPU workstation Hydra.

We set up module on Hydra to facilitate management and usage of different versions of a single software, such as multiple Python distributions, on the same machine.

There is a major security vulnerability for Supermicro servers with factory default IPMI settings!

Supermicro provides a set of utilities for configuring IPMI devices on Supermicro servers.

In this post, we describe how we installed Ceph v12.2.0 (codename Luminous) on the Pulpos cluster.

The Ceph admin socket allows you to query a daemon via a socket interface.

In this post, we describe how we installed Ceph v11.2 (codename Kraken) on the Pulpos cluster.

UCSC runs two directory services: Blue & Gold, on ldap-blue.ucsc.edu & ldap-gold.ucsc.edu respectively.

Hydra is a rack-mountable 4-GPU workstation for Machine Learning research, kindly provided to us by our partners at Pacific Research Platform.

In this post, we describe how we prepared the nodes in the Pulpos cluster for Ceph installation.

Tentakel is a program for executing the same command on many hosts in parallel using various remote methods.

PDSH is a an efficient, multithreaded remote shell client which executes commands on multiple remote hosts in parallel.

We use Ansible to configure our Ceph storage cluster Pulpos.

In this post I describe how we set up a home-brew environment for automated installation of CentOS 7 on the nodes of our Ceph storage cluster Pulpos.

FirewallD is a frontend controller / wrapper for iptables used to implement persistent network traffic rules.

The admin node of our Ceph storage cluster Pulpos is pulpo-admin.

In this post, I describe how I installed Ubuntu in Hyper-V, on my Dell XPS 15 9560 laptop running Windows 10 Pro Creators Update as of this writing.

In this post, we describe the network specifications and configurations of the Ceph storage cluster Pulpos.

venadi.ucsc.edu (IPv4 address: 128.114.109.74) is a Data Transfer Node, kindly provided by Pacific Research Platform (PRP), in order to improve the data transfer performance of the Hyades cluster. The system had been configured and tuned by John Graham at UCSD, before being shipped to UCSC.

In factory condition, the fans of my Surface Pro 3 ran almost non-stop, emitting a very audible crackling sound, even when the system was under very light load!

My first ITS project was to deploy a pilot Ceph Storage for Data Transfer and Data Warehousing in SciDMZ.

In this post, we document how I set up my GitHub Pages site, Thus Spake Manjusri, locally with Jekyll, on both my 27” iMac 2010 and my XPS 15 9560 laptop.

Starting from version 10.7 (Lion), Mac OS X includes 2 firewalls: PF & Application Firewall. Both are disabled by default.