开启云盘并行挂载提升Pod启动速度

#!/bin/bash

set -e
set -o pipefail

readonly REQUIRED_VERSION="v1.30.4"
CLUSTER_ID=$1

if [ -z "$CLUSTER_ID" ]; then
    echo "Usage: enable_parallel_attach.sh <cluster-id>"
    exit 1
fi

check_version() {
    local ADDONS VERSION
    ADDONS=$(aliyun cs GET "/clusters/${CLUSTER_ID}/addon_instances")

    VERSION=$(echo "$ADDONS" | jq -r '.addons[] | select(.name=="csi-plugin") | .version')
    if ! printf "%s\n" "$REQUIRED_VERSION" "$VERSION" | sort -V -C; then
        echo "csi-plugin version $VERSION is not supported, please upgrade to $REQUIRED_VERSION or later"
        exit 1
    fi

    PROVISIONER=managed-csiprovisioner
    VERSION=$(echo "$ADDONS" | jq -r '.addons[] | select(.name=="managed-csiprovisioner") | .version')
    if [ -z "$VERSION" ]; then
        PROVISIONER=csi-provisioner
        VERSION=$(echo "$ADDONS" | jq -r '.addons[] | select(.name=="csi-provisioner") | .version')
    fi
    if ! printf "%s\n" "$REQUIRED_VERSION" "$VERSION" | sort -V -C; then
        echo "$PROVISIONER version $VERSION is not supported, please upgrade to $REQUIRED_VERSION or later"
        exit 1
    fi
}

update_node_pool() {
    local NODE_POOL_DOC
    NODE_POOL_DOC=$(aliyun cs GET "/clusters/${CLUSTER_ID}/nodepools/$1")

    if [ -n "$(echo "$NODE_POOL_DOC" | jq -r '(.scaling_group.tags // [])[] | select(.key=="supportConcurrencyAttach")')" ]; then
        echo "node pool already has supportConcurrencyAttach tag"
        return
    fi

    aliyun cs PUT "/clusters/${CLUSTER_ID}/nodepools/$1" --header "Content-Type=application/json" \
        --body "$(echo "$NODE_POOL_DOC" | jq -c '{
    "scaling_group": {
        "tags": ((.scaling_group.tags // []) + [{
            "key": "supportConcurrencyAttach",
            "value": "true"
        }])
    }
}')"
}

# 存量节点配置
update_nodes() {
    local PAGE=1
    local IDX TOTAL NODES_DOC ARGS
    while :; do
        echo "tagging nodes, page $PAGE"
        NODES_DOC=$(aliyun cs GET "/clusters/${CLUSTER_ID}/nodes" --pageSize 50 --pageNumber $PAGE)
        TOTAL=$(echo "$NODES_DOC" | jq -r '.page.total_count')

        ARGS=()
        IDX=0
        for node in $(echo "$NODES_DOC" | jq -r '.nodes[] | select(.is_aliyun_node) | .instance_id'); do
            IDX=$((IDX+1))
            ARGS+=("--ResourceId.$IDX" "$node")
        done
        if [ "$IDX" != "0" ]; then
            aliyun ecs TagResources --region "$ALIBABA_CLOUD_REGION_ID" --ResourceType Instance "${ARGS[@]}" \
                --Tag.1.Key supportConcurrencyAttach --Tag.1.Value true
            echo "finished nodes $(( (PAGE-1)*50+IDX ))/$TOTAL"
        fi

        if [[ $(( PAGE*50 )) -ge $TOTAL ]]; then
            break
        fi
        PAGE=$((PAGE+1))
    done
}

update_addon() {
    local ADDON=$1
    shift
    local CONFIG STATE
    CONFIG=$(aliyun cs GET "/clusters/${CLUSTER_ID}/addon_instances/${ADDON}" | \
        jq -c '.config | fromjson | (.FeatureGate // "" | split(",")) as $fg | .FeatureGate = ($fg + $ARGS.positional | unique | join(",")) | {config: . | tojson}' --args "$@")

    aliyun cs POST "/clusters/${CLUSTER_ID}/components/${ADDON}/config" --header "Content-Type=application/json" --body "$CONFIG"

    echo "Waiting for $ADDON config to complete"
    while true; do
        STATE=$(aliyun --secure cs GET "/clusters/${CLUSTER_ID}/addon_instances/${ADDON}" | jq -r '.state')
        echo "state: $STATE"
        if [ "$STATE" != "updating" ]; then
            break
        fi
        sleep 5
    done
    if [ "$STATE" != "active" ]; then
        echo "Failed to update $ADDON config"
        return 1
    fi
}

check_version

aliyun cs GET "/clusters/${CLUSTER_ID}/nodepools" | jq -r '.nodepools[]|.nodepool_info|"\(.nodepool_id)\t\(.name)"' | \
while read -r NODE_POOL_ID NODE_POOL_NAME; do
    echo "Updating tags for node pool $NODE_POOL_NAME ($NODE_POOL_ID)"
    update_node_pool "$NODE_POOL_ID"
done

ALIBABA_CLOUD_REGION_ID=$(aliyun cs GET "/clusters/${CLUSTER_ID}" | jq -r .region_id)

update_nodes

update_addon $PROVISIONER DiskADController=true DiskParallelAttach=true
update_addon csi-plugin DiskADController=true

echo "All done! Now the disks can be attached concurrently to the same node."