From 363d7c2e6c2135bb561125fb0ed78c018e52b331 Mon Sep 17 00:00:00 2001 From: Nick Becker Date: Tue, 3 Nov 2020 13:41:14 -0800 Subject: [PATCH 1/2] default cluster setup to use tcp --- tpcx_bb/cluster_configuration/cluster-startup.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tpcx_bb/cluster_configuration/cluster-startup.sh b/tpcx_bb/cluster_configuration/cluster-startup.sh index 7525b6b3..15836645 100644 --- a/tpcx_bb/cluster_configuration/cluster-startup.sh +++ b/tpcx_bb/cluster_configuration/cluster-startup.sh @@ -1,6 +1,6 @@ #NVLINK or TCP ROLE=$1 -CLUSTER_MODE="NVLINK" +CLUSTER_MODE="TCP" USERNAME=$(whoami) MAX_SYSTEM_MEMORY=$(free -m | awk '/^Mem:/{print $2}')M From 291dc7b202ce8ade1d2e6cef5bcd0f9bb10b891f Mon Sep 17 00:00:00 2001 From: Nick Becker Date: Tue, 3 Nov 2020 13:42:58 -0800 Subject: [PATCH 2/2] readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6c07641c..a3ac12ef 100644 --- a/README.md +++ b/README.md @@ -61,7 +61,7 @@ In `cluster_configuration/cluster-startup.sh`: - Update `CONDA_ENV_PATH=...` to refer to your conda environment path. - Update `CONDA_ENV_NAME=...` to refer to the name of the conda environment you created, perhaps using the `yml` files provided in this repository. - Update `INTERFACE=...` to refer to the relevant network interface present on your cluster. - - Update `CLUSTER_MODE="NVLINK"` to refer to your communication method, either "TCP" or "NVLINK". + - Update `CLUSTER_MODE="TCP"` to refer to your communication method, either "TCP" or "NVLINK". - You may also need to change the `LOCAL_DIRECTORY` and `WORKER_DIR` depending on your filesystem. Make sure that these point to a location to which you have write access and that `LOCAL_DIRECTORY` is accessible from all nodes.