circuit-oram-docker

Circuit ORAM docker experimentation environment

Ian Goldberg, iang@uwaterloo.ca

This repo contains scripts to run Jarecki and Wei's 3-party Circuit ORAM in docker containers for easy experimentation on varying the ORAM size, and network latency and bandwidth.

These scripts are in support of our paper:

Adithya Vadapalli, Ryan Henry, Ian Goldberg. Duoram: A Bandwidth-Efficient Distributed ORAM for 2- and 3-Party Computation. USENIX Security Symposium 2023. https://eprint.iacr.org/2022/1747

It is a fork of Wei's published code, with two small changes:

• We add an iters: field to the config.yaml file to control at runtime the number of iterations of the protocol to run
• We tag the test code output with labels indicating what values it is outputting, where useful.

plus the dockerization and reproduction scripts in the docker folder.

Reproduction instructions

Follow these instructions to reproduce the Circuit ORAM data points (timings and bandwidth usage of Circuit ORAM operations for various ORAM sizes and network settings) for the plots in our paper. See below if you want to run experiments of your choosing.

• cd docker
• Build the docker image with ./build-docker
• Start the dockers with ./start-docker
  • This will start three dockers, each running one of the parties.

• Run the reproduction script ./repro with one of the following arguments:

  • ./repro test: Run a short (just about 10 seconds) "kick-the-tires" test. You should see output like the following:

    Running test experiment...
    Tue 21 Feb 2023 02:55:51 PM EST: Running 16 1us 100gbit 2 ...
    CircuitORAMOnln read 16 1us 100gbit 2 0.172 s
    CircuitORAMTotl read 16 1us 100gbit 2 0.54 s
    CircuitORAMOnln read 16 1us 100gbit 2 710.625 KiB
    CircuitORAMTotl read 16 1us 100gbit 2 4957 KiB
    

  The last four lines are the output data points, telling you that a Circuit ORAM read test on an ORAM of size 2¹⁶, with a network configuration of 1us latency and 100gbit bandwidth, performing 2 read operations, took 0.172 s of online time and 0.54 s of total (precomputation plus online) time, and 710.625 KiB of online bandwidth and 4957 KiB of total bandwidth. If you've run the test before, you will see means and stddevs of all of the output data points. When you run it, the time of course will depend on the particulars of your hardware, but the bandwidths used should be exactly the values quoted above.

  • ./repro small numops: Run the "small" tests. These are the tests up to size 2²⁶, and produce all the data points for most of Figure 9. numops is the number of operations to run for each test; we used the default of 128 for the figures in the paper, but you can use a lower number to make the tests run faster. For the default of 128, these tests should complete in about 2 to 3 hours, and require 2 GB of available RAM.

  • ./repro large numops: Run the "large" tests. These are the rightmost 3 data points in Figure 9. They are not essential to our major claims, so they are optional to run. For the default numops of 128, these experiments will require about 2 hours to run and 2 GB of available RAM.

  • ./repro all numops: Run both the "small" and "large" tests.

  • ./repro none numops: Run no tests. This command is nonetheless useful in order to parse the output logs and display the data points for the graphs (see below).

  • ./repro single size latency bandwidth numops: run a single manually selected test with the given parameters.

  • After small, large, all, or none, the script will parse all of the outputs that have been collected with the specified numops (in this run or previous runs), and output them as they would appear in each of the subfigures of Figure 9.

• When you're done, ./stop-docker

Manual instructions

• cd docker
• ./build-docker
• ./start-docker
  • This will start three dockers, each running one of the parties.

Then to simulate network latency and capacity (optional):

• ./set-networking 30ms 100mbit

To turn that off again:

• ./unset-networking

If you have a NUMA machine, you might want to pin each party to one NUMA node. To do that, set these environment variables before running ./run-experiment below:

• export ORAM_NUMA_C="numactl -N 1 -m 1"
• export ORAM_NUMA_D="numactl -N 2 -m 2"
• export ORAM_NUMA_E="numactl -N 3 -m 3"

Adjust the numactl arguments to taste, of course, depending on your machine's configuration. Alternately, you can use things like -C 0-7 instead of -N 1 to pin to specific cores, even on a non-NUMA machine.

Run experiments:

• ./run-experiment size numops >> outfile

  • size is the base-2 log of the number of entries in the ORAM (so size = 20 is an ORAM with 1048576 entries, for example). Defaults to 20.
  • numops is the number of read operations to perform. Defaults to 128.

• ./parse_logs outfile

  • Parses the file output by one or more executions of ./run-experiment to extract, for each experiment, the average number of bytes sent by each party and the time taken.

When you're all done:

• ./stop-docker