From 5dd65ba63452e996debff5e67f4c1b180594c2c5 Mon Sep 17 00:00:00 2001
From: Eli Uriegas <1700823+seemethere@users.noreply.github.com>
Date: Thu, 21 May 2020 13:05:21 -0700
Subject: [PATCH] .circleci: Add simple backup and restore solution for RCs
 (#38690)

Summary:
* Does a basic upload of release candidates to an extra folder within our
S3 bucket.
* Refactors AWS promotion to allow for easier development of restoration
of backups

Backup restoration usage:
```
RESTORE_FROM=v1.6.0-rc3 restore-backup.sh
```
Requires:
  * AWS credentials to upload / download stuff
  * Anaconda credentials to upload
Pull Request resolved: https://github.com/pytorch/pytorch/pull/38690

Differential Revision: D21691033

Pulled By: seemethere

fbshipit-source-id: 31118814db1ca701c55a3cb0bc32caa1e77a833d
---
 .circleci/scripts/binary_linux_upload.sh   | 12 +++++
 .circleci/scripts/binary_macos_upload.sh   | 12 +++++
 .circleci/scripts/binary_windows_upload.sh | 11 ++++
 scripts/release/README.md                  | 60 +++++++++++++++++++++
 scripts/release/promote/common_utils.sh    | 37 ++++---------
 scripts/release/promote/libtorch_to_s3.sh  |  8 ---
 scripts/release/promote/s3_to_s3.sh        | 19 +++++++
 scripts/release/promote/wheel_to_s3.sh     | 12 -----
 scripts/release/restore-backup.sh          | 63 ++++++++++++++++++++++
 9 files changed, 188 insertions(+), 46 deletions(-)
 create mode 100644 scripts/release/README.md
 delete mode 100755 scripts/release/promote/libtorch_to_s3.sh
 create mode 100755 scripts/release/promote/s3_to_s3.sh
 delete mode 100755 scripts/release/promote/wheel_to_s3.sh
 create mode 100755 scripts/release/restore-backup.sh

diff --git a/.circleci/scripts/binary_linux_upload.sh b/.circleci/scripts/binary_linux_upload.sh
index 0a4e712ace1..754858ec6ff 100755
--- a/.circleci/scripts/binary_linux_upload.sh
+++ b/.circleci/scripts/binary_linux_upload.sh
@@ -18,20 +18,32 @@ PIP_UPLOAD_FOLDER=${PIP_UPLOAD_FOLDER:-nightly}
 #       The only difference is the trailing slash
 # Strip trailing slashes if there
 CONDA_UPLOAD_CHANNEL=$(echo "${PIP_UPLOAD_FOLDER}" | sed 's:/*$::')
+BACKUP_BUCKET="s3://pytorch-backup"
 
 # Upload the package to the final location
 pushd /home/circleci/project/final_pkgs
 if [[ "$PACKAGE_TYPE" == conda ]]; then
   retry conda install -yq anaconda-client
   retry anaconda -t "${CONDA_PYTORCHBOT_TOKEN}" upload  "$(ls)" -u "pytorch-${CONDA_UPLOAD_CHANNEL}" --label main --no-progress --force
+  # Fetch  platform (eg. win-64, linux-64, etc.) from index file
+  # Because there's no actual conda command to read this
+  subdir=$(tar -xOf ./*.bz2 info/index.json | grep subdir  | cut -d ':' -f2 | sed -e 's/[[:space:]]//' -e 's/"//g' -e 's/,//')
+  BACKUP_DIR="conda/${subdir}"
 elif [[ "$PACKAGE_TYPE" == libtorch ]]; then
   retry pip install -q awscli
   s3_dir="s3://pytorch/libtorch/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
   for pkg in $(ls); do
     retry aws s3 cp "$pkg" "$s3_dir" --acl public-read
   done
+  BACKUP_DIR="libtorch/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
 else
   retry pip install -q awscli
   s3_dir="s3://pytorch/whl/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
   retry aws s3 cp "$(ls)" "$s3_dir" --acl public-read
+  BACKUP_DIR="whl/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
+fi
+
+if [[ -n "${CIRCLE_TAG:-}" ]]; then
+  s3_dir="${BACKUP_BUCKET}/${CIRCLE_TAG}/${BACKUP_DIR}"
+  retry aws s3 cp . "$s3_dir"
 fi
diff --git a/.circleci/scripts/binary_macos_upload.sh b/.circleci/scripts/binary_macos_upload.sh
index 74fd69c0c9b..8784bac2c04 100755
--- a/.circleci/scripts/binary_macos_upload.sh
+++ b/.circleci/scripts/binary_macos_upload.sh
@@ -19,19 +19,31 @@ PIP_UPLOAD_FOLDER=${PIP_UPLOAD_FOLDER:-nightly}
 #       The only difference is the trailing slash
 # Strip trailing slashes if there
 CONDA_UPLOAD_CHANNEL=$(echo "${PIP_UPLOAD_FOLDER}" | sed 's:/*$::')
+BACKUP_BUCKET="s3://pytorch-backup"
 
 pushd "$workdir/final_pkgs"
 if [[ "$PACKAGE_TYPE" == conda ]]; then
   retry conda install -yq anaconda-client
   retry anaconda -t "${CONDA_PYTORCHBOT_TOKEN}" upload "$(ls)" -u "pytorch-${CONDA_UPLOAD_CHANNEL}" --label main --no-progress --force
+  # Fetch  platform (eg. win-64, linux-64, etc.) from index file
+  # Because there's no actual conda command to read this
+  subdir=$(tar -xOf ./*.bz2 info/index.json | grep subdir  | cut -d ':' -f2 | sed -e 's/[[:space:]]//' -e 's/"//g' -e 's/,//')
+  BACKUP_DIR="conda/${subdir}"
 elif [[ "$PACKAGE_TYPE" == libtorch ]]; then
   retry pip install -q awscli
   s3_dir="s3://pytorch/libtorch/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
   for pkg in $(ls); do
     retry aws s3 cp "$pkg" "$s3_dir" --acl public-read
   done
+  BACKUP_DIR="libtorch/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
 else
   retry pip install -q awscli
   s3_dir="s3://pytorch/whl/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
   retry aws s3 cp "$(ls)" "$s3_dir" --acl public-read
+  BACKUP_DIR="whl/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
+fi
+
+if [[ -n "${CIRCLE_TAG:-}" ]]; then
+  s3_dir="${BACKUP_BUCKET}/${CIRCLE_TAG}/${BACKUP_DIR}"
+  retry aws s3 cp . "$s3_dir"
 fi
diff --git a/.circleci/scripts/binary_windows_upload.sh b/.circleci/scripts/binary_windows_upload.sh
index e87d7886838..73a2fd6bf6b 100644
--- a/.circleci/scripts/binary_windows_upload.sh
+++ b/.circleci/scripts/binary_windows_upload.sh
@@ -17,21 +17,32 @@ PIP_UPLOAD_FOLDER=${PIP_UPLOAD_FOLDER:-nightly/}
 #       The only difference is the trailing slash
 # Strip trailing slashes if there
 CONDA_UPLOAD_CHANNEL=$(echo "${PIP_UPLOAD_FOLDER}" | sed 's:/*$::')
+BACKUP_BUCKET="s3://pytorch-backup"
 
 pushd /root/workspace/final_pkgs
 # Upload the package to the final location
 if [[ "$PACKAGE_TYPE" == conda ]]; then
   retry conda install -yq anaconda-client
   retry anaconda -t "${CONDA_PYTORCHBOT_TOKEN}" upload  "$(ls)" -u "pytorch-${CONDA_UPLOAD_CHANNEL}" --label main --no-progress --force
+  # Fetch  platform (eg. win-64, linux-64, etc.) from index file
+  # Because there's no actual conda command to read this
+  subdir=$(tar -xOf ./*.bz2 info/index.json | grep subdir  | cut -d ':' -f2 | sed -e 's/[[:space:]]//' -e 's/"//g' -e 's/,//')
+  BACKUP_DIR="conda/${subdir}"
 elif [[ "$PACKAGE_TYPE" == libtorch ]]; then
   retry conda install -c conda-forge -yq awscli
   s3_dir="s3://pytorch/libtorch/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
   for pkg in $(ls); do
     retry aws s3 cp "$pkg" "$s3_dir" --acl public-read
   done
+  BACKUP_DIR="libtorch/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
 else
   retry conda install -c conda-forge -yq awscli
   s3_dir="s3://pytorch/whl/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
   retry aws s3 cp "$(ls)" "$s3_dir" --acl public-read
+  BACKUP_DIR="whl/${PIP_UPLOAD_FOLDER}${DESIRED_CUDA}/"
 fi
 
+if [[ -n "${CIRCLE_TAG:-}" ]]; then
+  s3_dir="${BACKUP_BUCKET}/${CIRCLE_TAG}/${BACKUP_DIR}"
+  retry aws s3 cp . "$s3_dir"
+fi
diff --git a/scripts/release/README.md b/scripts/release/README.md
new file mode 100644
index 00000000000..3908142bb6b
--- /dev/null
+++ b/scripts/release/README.md
@@ -0,0 +1,60 @@
+# PyTorch Release Scripts
+
+These are a collection of scripts that are to be used for release activities.
+
+> NOTE: All scripts should do no actual work unless the `DRY_RUN` environment variable is set
+>       to `disabled`.
+>       The basic idea being that there should be no potential to do anything dangerous unless
+>       `DRY_RUN` is explicitly set to `disabled`.
+
+## Requirements to actually run these scripts
+* AWS access to pytorch account
+* Access to upload conda packages to the `pytorch` conda channel
+* Access to the PyPI repositories
+
+
+## Promote
+
+These are scripts related to promotion of release candidates to GA channels, these
+can actually be used to promote pytorch, libtorch, and related domain libraries.
+
+### Usage
+
+Usage should be fairly straightforward and should actually require no extra variables
+if you are running from the correct git tags. (i.e. the GA tag to promote is currently
+checked out)
+
+`PACKAGE_TYPE` and `PACKAGE_NAME` can be swapped out to promote other packages.
+
+#### Promoting pytorch wheels
+```bash
+promote/s3_to_s3.sh
+```
+
+#### Promoting libtorch archives
+```bash
+PACKAGE_TYPE=libtorch PACKAGE_NAME=libtorch promote/s3_to_s3.sh
+```
+
+#### Promoting conda packages
+```bash
+promote/conda_to_conda.sh
+```
+
+#### Promoting wheels to PyPI
+**WARNING**: These can only be run once and cannot be undone, run with caution
+```
+promote/wheel_to_pypi.sh
+```
+
+## Restoring backups
+
+All release candidates are currently backed up to `s3://pytorch-backup/${TAG_NAME}` and
+can be restored to the test channels with the `restore-backup.sh` script.
+
+Which backup to restore from is dictated by the `RESTORE_FROM` environment variable.
+
+### Usage
+```bash
+RESTORE_FROM=v1.5.0-rc5 ./restore-backup.sh
+```
diff --git a/scripts/release/promote/common_utils.sh b/scripts/release/promote/common_utils.sh
index 96ff10b3d5a..e50ccb11001 100644
--- a/scripts/release/promote/common_utils.sh
+++ b/scripts/release/promote/common_utils.sh
@@ -36,17 +36,8 @@ get_pytorch_version() {
 }
 
 aws_promote() {
-    package_type=$1
-    package_name=$2
+    package_name=$1
     pytorch_version=$(get_pytorch_version)
-    PYTORCH_S3_FROM=${PYTORCH_S3_FROM:-test}
-    PYTORCH_S3_TO=${PYTORCH_S3_TO:-}
-    if [[ -n "${PYTORCH_S3_TO}" ]]; then
-        # Add a trailing slash so that it'll go to the correct subdir instead of creating a prefix+file thing
-        PYTORCH_S3_TO="${PYTORCH_S3_TO}/"
-    fi
-    # Can be changed
-    PYTORCH_S3_BUCKET=${PYTORCH_S3_BUCKET:-"s3://pytorch"}
     # Dry run by default
     DRY_RUN=${DRY_RUN:-enabled}
     DRY_RUN_FLAG="--dryrun"
@@ -54,22 +45,16 @@ aws_promote() {
         DRY_RUN_FLAG=""
     fi
     AWS=${AWS:-aws}
-    while IFS=$'\n' read -r s3_ls_result; do
-        # File should be the last field
-        from=$(echo "${s3_ls_result}" | rev | cut -d' ' -f 1 | rev)
-        to=${from//${PYTORCH_S3_FROM}\//${PYTORCH_S3_TO}}
-        (
-            set -x
-            ${AWS} s3 cp ${DRY_RUN_FLAG} \
-                --only-show-errors \
-                --acl public-read \
-                "${PYTORCH_S3_BUCKET}/${from}" \
-                "${PYTORCH_S3_BUCKET}/${to}"
-        )
-    done < <(\
-        aws s3 ls --recursive "${PYTORCH_S3_BUCKET}/${package_type}/${PYTORCH_S3_FROM}" \
-            | grep -E "${package_name}-.*${pytorch_version}" \
-            | sed -e '/dev/d' \
+    (
+        set -x
+        ${AWS} s3 cp ${DRY_RUN_FLAG} \
+            --only-show-errors \
+            --acl public-read \
+            --recursive \
+            --exclude '*' \
+            --include "*${package_name}-${pytorch_version}*" \
+            "${PYTORCH_S3_FROM/\/$//}" \
+            "${PYTORCH_S3_TO/\/$//}"
     )
     # ^ We grep for package_name-.*pytorch_version to avoid any situations where domain libraries have
     #   the same version on our S3 buckets
diff --git a/scripts/release/promote/libtorch_to_s3.sh b/scripts/release/promote/libtorch_to_s3.sh
deleted file mode 100755
index 7a121a6e06a..00000000000
--- a/scripts/release/promote/libtorch_to_s3.sh
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-
-set -eou pipefail
-
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-source "${DIR}/common_utils.sh"
-
-aws_promote libtorch libtorch
diff --git a/scripts/release/promote/s3_to_s3.sh b/scripts/release/promote/s3_to_s3.sh
new file mode 100755
index 00000000000..21495ac3b32
--- /dev/null
+++ b/scripts/release/promote/s3_to_s3.sh
@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+set -eou pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "${DIR}/common_utils.sh"
+
+# Allow for users to pass PACKAGE_NAME
+# For use with other packages, i.e. torchvision, etc.
+PACKAGE_NAME=${PACKAGE_NAME:-torch}
+PACKAGE_TYPE=${PACKAGE_TYPE:-whl}
+
+PYTORCH_S3_BUCKET=${PYTORCH_S3_BUCKET:-s3://pytorch}
+FROM=${FROM:-test}
+PYTORCH_S3_FROM=${PYTORCH_S3_FROM:-${PYTORCH_S3_BUCKET}/${PACKAGE_TYPE}/${FROM}}
+TO=${TO:-}
+PYTORCH_S3_TO=${PYTORCH_S3_TO:-${PYTORCH_S3_BUCKET}/${PACKAGE_TYPE}/${TO}}
+
+aws_promote "${PACKAGE_NAME}"
diff --git a/scripts/release/promote/wheel_to_s3.sh b/scripts/release/promote/wheel_to_s3.sh
deleted file mode 100755
index 526d24ebaf8..00000000000
--- a/scripts/release/promote/wheel_to_s3.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-#!/usr/bin/env bash
-
-set -eou pipefail
-
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-source "${DIR}/common_utils.sh"
-
-# Allow for users to pass PACKAGE_NAME
-# For use with other packages, i.e. torchvision, etc.
-PACKAGE_NAME=${PACKAGE_NAME:-torch}
-
-aws_promote whl "${PACKAGE_NAME}"
diff --git a/scripts/release/restore-backup.sh b/scripts/release/restore-backup.sh
new file mode 100755
index 00000000000..6cf79549d6e
--- /dev/null
+++ b/scripts/release/restore-backup.sh
@@ -0,0 +1,63 @@
+#!/usr/bin/env bash
+
+set -eou pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "${DIR}/promote/common_utils.sh"
+
+if [[ -z "${RESTORE_FROM:-}" ]]; then
+    echo "ERROR: RESTORE_FROM environment variable must be specified"
+    echo "       example: RESTORE_FROM=v1.6.0-rc3 ${0}"
+    exit 1
+fi
+
+DRY_RUN=${DRY_RUN:-enabled}
+
+PYTORCH_S3_BACKUP_BUCKET=${PYTORCH_S3_BACKUP_BUCKET:-s3://pytorch-backup/${RESTORE_FROM}}
+PYTORCH_S3_TEST_BUCKET=${PYTORCH_S3_TEST_BUCKET:-s3://pytorch/}
+PYTORCH_S3_FROM=${PYTORCH_S3_FROM:-${PYTORCH_S3_BACKUP_BUCKET}}
+PYTORCH_S3_TO=${PYTORCH_S3_TO:-s3://pytorch/}
+
+restore_wheels() {
+    aws_promote torch whl
+}
+
+restore_libtorch() {
+    aws_promote libtorch-* libtorch
+}
+
+ANACONDA="true anaconda"
+if [[ ${DRY_RUN} = "disabled" ]]; then
+    ANACONDA="anaconda"
+fi
+PYTORCH_CONDA_TO=${PYTORCH_CONDA_TO:-pytorch-test}
+
+upload_conda() {
+    local pkg
+    pkg=${1}
+    (
+        set -x
+        ${ANACONDA} upload --skip -u "${PYTORCH_CONDA_TO}" "${pkg}"
+    )
+}
+
+export -f upload_conda
+
+restore_conda() {
+    TMP_DIR="$(mktemp -d)"
+    trap 'rm -rf ${TMP_DIR}' EXIT
+    (
+        set -x
+        aws s3 cp --recursive "${PYTORCH_S3_BACKUP_BUCKET}/conda" "${TMP_DIR}/"
+    )
+    export ANACONDA
+    export PYTORCH_CONDA_TO
+    # Should upload all bz2 packages in parallel for quick restoration
+    find "${TMP_DIR}" -name '*.bz2' -type f \
+        | xargs -P 10 -I % bash -c "(declare -t upload_conda); upload_conda %"
+}
+
+
+restore_wheels
+restore_libtorch
+restore_conda