Merge branch 'main' into node-metrics-canister-front-end

dfinity · Aug 22, 2024 · 7b28ddc · 7b28ddc
2 parents 90fa192 + 1f4df9a
commit 7b28ddc
Show file tree

Hide file tree

Showing 24 changed files with 881 additions and 130 deletions.
diff --git a/.bazelrc b/.bazelrc
@@ -35,7 +35,7 @@ build --@rules_rust//:extra_rustc_flags=-Cdebug-assertions=on
 build --@rules_rust//:extra_rustc_flag=-Dbindings_with_variant_name
 build --strip=never
 
-# build:dfinity --remote_cache=bazel-remote.idx.dfinity.network
+build:dfinity --remote_cache=bazel-remote.idx.dfinity.network
 # build --remote_cache=grpc://localhost:9092
 build --remote_instance_name=default
 build --google_default_credentials=false
@@ -46,14 +46,14 @@ build --remote_timeout=30s # Default is 60s.
 build:ci --remote_timeout=5m # Default is 60s.
 build:ci --remote_upload_local_results=true
 
-# build:dfinity --experimental_remote_downloader=bazel-remote.idx.dfinity.network --experimental_remote_downloader_local_fallback
+build:dfinity --experimental_remote_downloader=bazel-remote.idx.dfinity.network --experimental_remote_downloader_local_fallback
 build:local --experimental_remote_downloader=
 
 # Does not produce valid JSON. See https://github.com/bazelbuild/bazel/issues/14209
 build --execution_log_json_file=bazel-build-log.json
 
-# build:dfinity --bes_results_url=https://dash.idx.dfinity.network/invocation/
-# build:dfinity --bes_backend=bes.idx.dfinity.network
+build:dfinity --bes_results_url=https://dash.idx.dfinity.network/invocation/
+build:dfinity --bes_backend=bes.idx.dfinity.network
 build --bes_timeout=30s # Default is no timeout.
 build:ci --bes_timeout=180s # Default is no timeout.
 build:ci --bes_upload_mode=fully_async
@@ -72,7 +72,7 @@ build:fmt --aspects=@rules_rust//rust:defs.bzl%rustfmt_aspect
 build:fmt --output_groups=+rustfmt_checks
 build --@rules_rust//:rustfmt.toml=//:rustfmt.toml
 
-test --test_output=errors
+test --test_output=streamed
 test --test_env=RUST_BACKTRACE=full
 
 test:precommit --build_tests_only

diff --git a/.github/workflows/qualify.yaml b/.github/workflows/qualify.yaml
@@ -113,3 +113,29 @@ jobs:
           filename: ${{ inputs.version }}-${{ steps.date.outputs.date }}.tar
           folderId: ${{ secrets.ARTIFACTS_DRIVE_FOLDER_ID }}
           name: ${{ inputs.version }}-${{ steps.date.outputs.date }}.tar
+
+      - name: "Setup message"
+        id: slack
+        shell: bash
+        run: |
+          COMMIT="${{ inputs.version }}"
+          FULL_MESSAGE="Qualification of \`${COMMIT}\`: "
+          if [[ "${{ needs.qualify.result }}" =~ ^(success)$ ]]; then
+            FULL_MESSAGE="${FULL_MESSAGE} :white_check_mark:"
+          elif [[ "${{ needs.qualify.result }}" =~ ^(failure|timed_out)$ ]]; then
+            FULL_MESSAGE="${FULL_MESSAGE} :x:"
+          fi
+
+          echo "message=${FULL_MESSAGE}" >> $GITHUB_OUTPUT
+
+      - name: "Notify DRE on slack"
+        uses: slackapi/slack-github-action@6c661ce58804a1a20f6dc5fbee7f0381b469e001 # v1.25.0
+        with:
+          channel-id: eng-release-bots
+          slack-message: |
+            ${{ steps.slack.outputs.message }}
+
+            Artifacts of run: `${{ inputs.version }}-${{ steps.date.outputs.date }}.tar`
+            Artifacts can be found on <https://drive.google.com/drive/u/1/folders/${{secrets.ARTIFACTS_DRIVE_FOLDER_ID}}|Google Drive :open_file_folder:>
+        env:
+          SLACK_BOT_TOKEN: ${{ secrets.SLACK_API_TOKEN }}
diff --git a/WORKSPACE.bazel b/WORKSPACE.bazel
@@ -25,9 +25,9 @@ http_archive(
 )
 
 http_file(
-    name = "bazelisk_darwin",
-    sha256 = "9a4b169038a63ebf60a9b4f367b449ab9b484c4ec7d1ef9f6b7a4196dfd50f33",
-    url = "https://github.com/bazelbuild/bazelisk/releases/download/v1.20.0/bazelisk-darwin",
+    name = "target_determinator",
+    sha256 = "65000bba3a5eb1713d93b1e08e33b6fbe5787535664bbc1ba2f4166b0d26d0a1",
+    url = "https://github.com/bazel-contrib/target-determinator/releases/download/v0.27.0/target-determinator.linux.amd64",
 )
 
 http_file(

diff --git a/docs/decentralization.md b/docs/decentralization.md
diff --git a/docs/javascript/katex.js b/docs/javascript/katex.js
@@ -0,0 +1,10 @@
+document$.subscribe(({ body }) => {
+    renderMathInElement(body, {
+        delimiters: [
+            { left: "$$", right: "$$", display: true },
+            { left: "$", right: "$", display: false },
+            { left: "\\(", right: "\\)", display: false },
+            { left: "\\[", right: "\\]", display: true }
+        ],
+    })
+})
diff --git a/docs/nns-proposals.md b/docs/nns-proposals.md
@@ -59,9 +59,157 @@ dre propose remove-node-operators kdqam-hauon-sdvym-42eyg-5wyff-4ywbw-v6iij-2sw2
     --summary "<An appropriate summary for the proposal, and a link to the forum post for further discussion, if possible>"
 ```
 
+### Removing nodes from a subnet
+
+There are situations where nodes need to be removed from subnets, such as for maintenance. Subnets are expected to maintain a certain size (number of nodes). Therefore, nodes cannot simply be removed from a subnet; new nodes must be added back into the subnet to maintain the required number.
+
+To free up nodes from a specific data center (e.g., bo1) within subnets, follow these steps:
+
+First, [open the public dashboard for the DC in question](https://dashboard.internetcomputer.org/center/bo1) to find a list of subnets that include nodes from the data center. Or, alternatively, you can bypass the public dashboard by querying the registry directly:
+
+```bash
+dre registry | jq '.nodes[] | select((.dc_id == "bo1") and (.subnet_id != null))'
+```
+**Explanation**: This command retrieves a dump of the registry, extracts the list of nodes, and selects only those that belong to the `bo1` data center and have a `subnet_id` set (i.e., not null).
+
+<details>
+  <summary><i>Click here to see the output of the above command</i></summary>
+  ```json
+  {
+    "node_id": "4jtgm-ywxcc-xh3o3-x2omx-tgmdm-gobca-agb3a-alvw4-dhmyn-khis6-xae",
+    "xnet": {
+      "ip_addr": "2600:c0d:3002:4:6801:dfff:fee7:5ae8",
+      "port": 2497
+    },
+    "http": {
+      "ip_addr": "2600:c0d:3002:4:6801:dfff:fee7:5ae8",
+      "port": 8080
+    },
+    "node_operator_id": "ut325-qbq5v-fli2f-e2a5h-qapdd-fsuyv-xej2j-ogvux-i3fc2-5nj3a-2ae",
+    "chip_id": null,
+    "hostos_version_id": "2e269c77aa2f6b2353ddad6a4ac3d5ddcac196b1",
+    "public_ipv4_config": null,
+    "subnet_id": "nl6hn-ja4yw-wvmpy-3z2jx-ymc34-pisx3-3cp5z-3oj4a-qzzny-jbsv3-4qe",
+    "dc_id": "bo1",
+    "node_provider_id": "lq5ra-f4ibl-t7wpy-hennc-m4eb7-tnfxe-eorgd-onpsl-wervo-7chjj-6qe",
+    "status": "Healthy"
+  }
+  {
+    "node_id": "af7ti-auyik-jfsne-tljmz-6purg-2msmy-jw34z-b4ie3-abk5f-h23xt-zae",
+    "xnet": {
+      "ip_addr": "2600:c0d:3002:4:6801:19ff:fe8c:de47",
+      "port": 2497
+    },
+    "http": {
+      "ip_addr": "2600:c0d:3002:4:6801:19ff:fe8c:de47",
+      "port": 8080
+    },
+    "node_operator_id": "ut325-qbq5v-fli2f-e2a5h-qapdd-fsuyv-xej2j-ogvux-i3fc2-5nj3a-2ae",
+    "chip_id": null,
+    "hostos_version_id": "2e269c77aa2f6b2353ddad6a4ac3d5ddcac196b1",
+    "public_ipv4_config": null,
+    "subnet_id": "w4rem-dv5e3-widiz-wbpea-kbttk-mnzfm-tzrc7-svcj3-kbxyb-zamch-hqe",
+    "dc_id": "bo1",
+    "node_provider_id": "lq5ra-f4ibl-t7wpy-hennc-m4eb7-tnfxe-eorgd-onpsl-wervo-7chjj-6qe",
+    "status": "Healthy"
+  }
+  {
+    "node_id": "fd5e4-a2xzl-lxu7m-kjvn6-2arnt-jghro-rdrgx-zvvkd-j2hza-pbwl4-5qe",
+    "xnet": {
+      "ip_addr": "2600:c0d:3002:4:6801:94ff:fec9:6b",
+      "port": 2497
+    },
+    "http": {
+      "ip_addr": "2600:c0d:3002:4:6801:94ff:fec9:6b",
+      "port": 8080
+    },
+    "node_operator_id": "ut325-qbq5v-fli2f-e2a5h-qapdd-fsuyv-xej2j-ogvux-i3fc2-5nj3a-2ae",
+    "chip_id": null,
+    "hostos_version_id": "2e269c77aa2f6b2353ddad6a4ac3d5ddcac196b1",
+    "public_ipv4_config": null,
+    "subnet_id": "tdb26-jop6k-aogll-7ltgs-eruif-6kk7m-qpktf-gdiqx-mxtrf-vb5e6-eqe",
+    "dc_id": "bo1",
+    "node_provider_id": "lq5ra-f4ibl-t7wpy-hennc-m4eb7-tnfxe-eorgd-onpsl-wervo-7chjj-6qe",
+    "status": "Healthy"
+  }
+  {
+    "node_id": "q2ucv-x7dv5-hheao-ocsye-jbg4z-enm75-ss62d-ehqhj-zwwm3-cap5q-tqe",
+    "xnet": {
+      "ip_addr": "2600:c0d:3002:4:6801:bcff:fee7:4008",
+      "port": 2497
+    },
+    "http": {
+      "ip_addr": "2600:c0d:3002:4:6801:bcff:fee7:4008",
+      "port": 8080
+    },
+    "node_operator_id": "ut325-qbq5v-fli2f-e2a5h-qapdd-fsuyv-xej2j-ogvux-i3fc2-5nj3a-2ae",
+    "chip_id": null,
+    "hostos_version_id": "2e269c77aa2f6b2353ddad6a4ac3d5ddcac196b1",
+    "public_ipv4_config": null,
+    "subnet_id": "io67a-2jmkw-zup3h-snbwi-g6a5n-rm5dn-b6png-lvdpl-nqnto-yih6l-gqe",
+    "dc_id": "bo1",
+    "node_provider_id": "lq5ra-f4ibl-t7wpy-hennc-m4eb7-tnfxe-eorgd-onpsl-wervo-7chjj-6qe",
+    "status": "Healthy"
+  }
+  ```
+</details>
+
+To further refine the command and group nodes by subnets:
+```bash
+DC=bo1
+dre registry | jq -r '.nodes | map(select((.dc_id == "'$DC'") and (.subnet_id != null))) | group_by(.subnet_id) | map("dre subnet replace --exclude '$DC' --nodes \([.[].node_id] | join(" "))") | .[]'
+```
+
+<details>
+<summary><i>Click here to see the explanation of the jq command</i></summary>
+
+1.  **`-r` (raw output):**
+
+    -   This option tells `jq` to output raw strings instead of JSON-formatted strings. This is particularly useful when you want to generate command-line strings like the one you're creating.
+2.  **`.nodes`:**
+
+    -   This accesses the `nodes` array in the JSON structure.
+3.  **`map(select((.dc_id == "bo1") and (.subnet_id != null)))`:**
+
+    -   This filters the nodes array. It keeps only the nodes where `dc_id` is `"bo1"` and `subnet_id` is not `null`. `map` applies this filter to each element of the array.
+4.  **`group_by(.subnet_id)`:**
+
+    -   This groups the filtered nodes by their `subnet_id`. The result is an array of arrays, where each inner array contains nodes that share the same `subnet_id`.
+5.  **`map("dre subnet replace --exclude '$DC' --nodes \([.[].node_id] | join(" "))")`:**
+
+    -   This `map` applies a transformation to each group (each inner array).
+    -   The transformation constructs a string that starts with `"dre subnet replace --exclude '$DC' --nodes "`.
+    -   `\([.[].node_id] | join(" "))`:
+        -   `.[].node_id` accesses the `node_id` of each node in the current group.
+        -   `join(" ")` joins all the `node_id`s into a single string separated by spaces.
+    -   The result is a string for each subnet that lists all its nodes.
+6.  **`.[]`:**
+
+    -   This unwraps the array of strings created by the previous `map` step into individual strings. This means the output will be a list of commands, one per line.
+</details>
+
+<details>
+<summary><i>Click here to see the example output</i></summary>
+```
+dre subnet replace --exclude bo1 --nodes q2ucv-x7dv5-hheao-ocsye-jbg4z-enm75-ss62d-ehqhj-zwwm3-cap5q-tqe
+dre subnet replace --exclude bo1 --nodes 4jtgm-ywxcc-xh3o3-x2omx-tgmdm-gobca-agb3a-alvw4-dhmyn-khis6-xae
+dre subnet replace --exclude bo1 --nodes fd5e4-a2xzl-lxu7m-kjvn6-2arnt-jghro-rdrgx-zvvkd-j2hza-pbwl4-5qe
+dre subnet replace --exclude bo1 --nodes af7ti-auyik-jfsne-tljmz-6purg-2msmy-jw34z-b4ie3-abk5f-h23xt-zae
+```
+</details>
+
+You would now go through each of these output lines (subnets) and submit proposals. Remember to include a motivation for each proposal. For example:
+
+```bash
+dre subnet replace --exclude bo1 --nodes q2ucv-x7dv5-hheao-ocsye-jbg4z-enm75-ss62d-ehqhj-zwwm3-cap5q-tqe --motivation "Removing BO1 nodes for maintenance"
+```
+
 ### Removing nodes from the registry
 
-Here is an example where we remove all AW1 nodes for redeployment.
+Here is an example where we remove all AW1 nodes from the registry, for redeployment. Note that the nodes should already be removed from the subnet(s), so they should in unassigned state (awaiting subnet).
+You can get the node status by checking [the public dashboard](https://dashboard.internetcomputer.org/center/aw1) or with `dre registry` and then analyzing the generated JSON from the command.
+
+After all relevant nodes are removed from their subnets, you can also remove them from the registry with:
 
 ```bash
 dre nodes remove aw1 --motivation "Removing AW1 nodes for redeployment"

diff --git a/mkdocs.yml b/mkdocs.yml
@@ -77,3 +77,13 @@ markdown_extensions:
           class: mermaid
           format: !!python/name:pymdownx.superfences.fence_code_format
   - tables
+  - pymdownx.arithmatex:
+      generic: true
+
+extra_javascript:
+  - javascript/katex.js
+  - https://unpkg.com/katex@0/dist/katex.min.js
+  - https://unpkg.com/katex@0/dist/contrib/auto-render.min.js
+
+extra_css:
+  - https://unpkg.com/katex@0/dist/katex.min.css
diff --git a/node-labels/mainnet.yaml b/node-labels/mainnet.yaml
@@ -2634,90 +2634,6 @@ data:
     2a00:fc0:5000:300:6801:ffff:fe54:b396:
       dc: mb1
       label: dll14
-    2a01:138:900a:0:6801:21ff:fec5:3a04:
-      dc: mu1
-      label: dll06
-    2a01:138:900a:0:6801:22ff:feff:a6e:
-      dc: mu1
-      label: dll15
-    2a01:138:900a:0:6801:31ff:feb4:bbd1:
-      dc: mu1
-      label: dll17
-    2a01:138:900a:0:6801:32ff:fec6:c12:
-      dc: mu1
-      label: dll14
-    2a01:138:900a:0:6801:33ff:fe92:8893:
-      dc: mu1
-      label: dll26
-    2a01:138:900a:0:6801:58ff:fe37:d524:
-      dc: mu1
-      label: dll21
-    2a01:138:900a:0:6801:5cff:feed:7be2:
-      dc: mu1
-      label: dll11
-    2a01:138:900a:0:6801:62ff:fe6b:7d8f:
-      dc: mu1
-      label: dll12
-    2a01:138:900a:0:6801:74ff:feab:762b:
-      dc: mu1
-      label: dll03
-    2a01:138:900a:0:6801:7aff:fe41:3051:
-      dc: mu1
-      label: dll22
-    2a01:138:900a:0:6801:87ff:fe34:eed7:
-      dc: mu1
-      label: dll01
-    2a01:138:900a:0:6801:88ff:fed5:853b:
-      dc: mu1
-      label: dll18
-    2a01:138:900a:0:6801:8fff:fe1d:e5bf:
-      dc: mu1
-      label: dll28
-    2a01:138:900a:0:6801:90ff:fe63:2c5d:
-      dc: mu1
-      label: dll04
-    2a01:138:900a:0:6801:96ff:fe5a:f63:
-      dc: mu1
-      label: dll05
-    2a01:138:900a:0:6801:96ff:febd:4be1:
-      dc: mu1
-      label: dll16
-    2a01:138:900a:0:6801:98ff:fe7c:2c57:
-      dc: mu1
-      label: dll19
-    2a01:138:900a:0:6801:a4ff:fef0:c947:
-      dc: mu1
-      label: dll13
-    2a01:138:900a:0:6801:b5ff:fe42:bc61:
-      dc: mu1
-      label: dll23
-    2a01:138:900a:0:6801:baff:fe5f:a337:
-      dc: mu1
-      label: dll02
-    2a01:138:900a:0:6801:beff:fed6:43de:
-      dc: mu1
-      label: dll10
-    2a01:138:900a:0:6801:c4ff:fe39:29d9:
-      dc: mu1
-      label: dll07
-    2a01:138:900a:0:6801:c6ff:fe4e:789b:
-      dc: mu1
-      label: dll20
-    2a01:138:900a:0:6801:d3ff:febe:73a0:
-      dc: mu1
-      label: dll27
-    2a01:138:900a:0:6801:e2ff:fe80:b65:
-      dc: mu1
-      label: dll08
-    2a01:138:900a:0:6801:e7ff:fe6d:75a1:
-      dc: mu1
-      label: dll25
-    2a01:138:900a:0:6801:e9ff:fe7a:68ae:
-      dc: mu1
-      label: dll09
-    2a01:138:900a:0:6801:ebff:fef3:1625:
-      dc: mu1
-      label: dll24
     2a01:2a8:a13c:1:6801:18ff:fec5:5f32:
       dc: zh6
       label: dll26
@@ -3381,4 +3297,3 @@ data:
     2a0f:cd00:2:1:6801:fdff:fe1d:d6e7:
       dc: ge1
       label: dll04
-