fix(influxdb3): Enterprise: update options in CLI reference:

Add options new in Beta
Remove old options, add see references, add anchors for backward compat.
Fix link checker test to not fail when no links exist in the article

content/influxdb3/enterprise/reference/config-options.md

@@ -54,6 +54,7 @@ influxdb3 serve
   - [object-store](#object-store)
   - [data-dir](#data-dir)
   - [node-id](#node-id)
+  - [cluster-id](#cluster-id)
   - [mode](#mode)
   - [license-email](#license-email)
   - [query-file-limit](#query-file-limit)
@@ -112,7 +113,6 @@ influxdb3 serve
 - [Memory](#memory)
   - [ram-pool-data-bytes](#ram-pool-data-bytes)
   - [exec-mem-pool-bytes](#exec-mem-pool-bytes)
-  - [buffer-mem-limit-mb](#buffer-mem-limit-mb)
   - [force-snapshot-mem-threshold](#force-snapshot-mem-threshold)
 - [Write-Ahead Log (WAL)](#write-ahead-log-wal)
   - [wal-flush-interval](#wal-flush-interval)
@@ -123,9 +123,6 @@ influxdb3 serve
   - [read-from-node-ids](#read-from-node-ids)
   - [replication-interval](#replication-interval)
 - [Compaction](#compaction)
-  - [compactor-id](#compactor-id)
-  - [compact-from-node-ids](#compact-from-node-ids)
-  - [run-compactions](#run-compactions)
   - [compaction-row-limit](#compaction-row-limit)
   - [compaction-max-num-files-per-plan](#compaction-max-num-files-per-plan)
   - [compaction-gen2-duration](#compaction-gen2-duration)
@@ -133,7 +130,7 @@ influxdb3 serve
   - [gen1-duration](#gen1-duration)
 - [Caching](#caching)
   - [preemptive-cache-age](#preemptive-cache-age)
-  - [parquet-mem-cache-size-mb](#parquet-mem-cache-size-mb)
+  - [parquet-mem-cache-size](#parquet-mem-cache-size)
   - [parquet-mem-cache-prune-percentage](#parquet-mem-cache-prune-percentage)
   - [parquet-mem-cache-prune-interval](#parquet-mem-cache-prune-interval)
   - [disable-parquet-mem-cache](#disable-parquet-mem-cache)
@@ -153,6 +150,7 @@ influxdb3 serve
 - [bucket](#bucket)
 - [data-dir](#data-dir)
 - [node-id](#node-id)
+- [cluster-id](#cluster-id)
 - [mode](#mode)
 - [license-email](#license-email)
 - [query-file-limit](#query-file-limit)
@@ -162,12 +160,12 @@ influxdb3 serve
 Specifies which object storage to use to store Parquet files.
 This option supports the following values:
 
-- `memory` _(default)_
+- `memory` _(default)_: Effectively no object persistence
-- `memory-throttled`
+- `memory-throttled`: Like `memory` but with latency and throughput that somewhat resembles a cloud object store
-- `file`
+- `file`: Stores objects in the local filesystem (must also set `--data-dir`)
-- `s3`
+- `s3`: Amazon S3 (must also set `--bucket`, `--aws-access-key-id`, `--aws-secret-access-key`, and possibly `--aws-default-region`)
-- `google`
+- `google`: Google Cloud Storage (must also set `--bucket` and `--google-service-account`)
-- `azure`
+- `azure`: Microsoft Azure blob storage (must also set `--bucket`, `--azure-storage-account`, and `--azure-storage-access-key`)
 
 | influxdb3 serve option | Environment variable     |
 | :--------------------- | :----------------------- |
@@ -197,17 +195,30 @@ configuration--for example, the same bucket.
 
 ---
 
+#### cluster-id
+
+Specifies the cluster identifier that prefixes the object store path for the Enterprise Catalog. 
+This value must be different than the [`--node-id`](#node-id) value.
+
+| influxdb3 serve option | Environment variable               |
+| :--------------------- | :--------------------------------- |
+| `--cluster-id`         | `INFLUXDB3_ENTERPRISE_CLUSTER_ID`  |
+
+---
+
 #### mode
 
 Sets the mode to start the server in.
 
 This option supports the following values:
 
-- `read`
+- `all` _(default)_
-- `read_write` _(default)_
+- `ingest`
-- `compactor`
+- `query`
+- `compact`
+- `process`
 
-**Default:** `read_write`
+**Default:** `all`
 
 | influxdb3 serve option | Environment variable        |
 | :--------------------- | :-------------------------- |
@@ -844,9 +855,10 @@ Specifies the size of the RAM cache used to store data, in bytes.
 
 #### exec-mem-pool-bytes
 
-Specifies the size of the memory pool used during query execution, in bytes.
+Specifies the size of memory pool used during query execution.
+Can be given as absolute value in bytes or as a percentage of the total available memory (for example: `10%`).
 
-**Default:** `8589934592`
+**Default:** `20%`
 
 | influxdb3 serve option  | Environment variable            |
 | :---------------------- | :------------------------------ |
@@ -854,26 +866,14 @@ Specifies the size of the memory pool used during query execution, in bytes.
 
 ---
 
-#### buffer-mem-limit-mb
-
-Specifies the size limit of the buffered data in MB. If this limit is exceeded,
-the server forces a snapshot.
-
-**Default:** `5000`
-
-| influxdb3 serve option  | Environment variable            |
-| :---------------------- | :------------------------------ |
-| `--buffer-mem-limit-mb` | `INFLUXDB3_BUFFER_MEM_LIMIT_MB` |
-
----
-
 #### force-snapshot-mem-threshold
+<span id="buffer-mem-limit-mb" />
 
 Specifies the threshold for the internal memory buffer. Supports either a
-percentage (portion of available memory)of or absolute value
+percentage (portion of available memory) or absolute value in MB
-(total bytes)--for example: `70%` or `100000`.
+(total bytes)--for example: `70%` or `1000 MB`.
 
-**Default:** `70%`
+**Default:** `50%`
 
 | influxdb3 serve option           | Environment variable                     |
 | :------------------------------- | :--------------------------------------- |
@@ -972,47 +972,31 @@ Defines the interval at which each replica specified in the
 
 ### Compaction
 
-- [compactor-id](#compactor-id)
-- [compact-from-node-ids](#compact-from-node-ids)
-- [run-compactions](#run-compactions)
 - [compaction-row-limit](#compaction-row-limit)
 - [compaction-max-num-files-per-plan](#compaction-max-num-files-per-plan)
 - [compaction-gen2-duration](#compaction-gen2-duration)
 - [compaction-multipliers](#compaction-multipliers)
+- [compaction-cleanup-wait](#compaction-cleanup-wait)
 - [gen1-duration](#gen1-duration)
 
 #### compactor-id
 
-Specifies the prefix in the object store where all compacted data is written.
+> [!Important]
-Provide this option only if this server should handle compaction for its own
+> This option has been superseded by using `--mode compact`. See the [mode](#mode) section for details.
-write buffer and any replicas it manages.
-
-| influxdb3 serve option | Environment variable                |
-| :--------------------- | :---------------------------------- |
-| `--compactor-id`       | `INFLUXDB3_ENTERPRISE_COMPACTOR_ID` |
 
 ---
 
 #### compact-from-node-ids
 
-Defines a comma-separated list of writer identifier prefixes from which data is
+> [!Important]
-compacted.
+> This option has been superseded by using `--mode compact`. See the [mode](#mode) section for details.
-
-| influxdb3 serve option      | Environment variable                           |
-| :-------------------------- | :--------------------------------------------- |
-| `--compact-from-node-ids` | `INFLUXDB3_ENTERPRISE_COMPACT_FROM_WRITER_IDS` |
 
 ---
 
 #### run-compactions
 
-Indicates that the server should run compactions. Only a single server should
+> [!Important]
-run compactions for a given `compactor-id`. This option is only applicable if a
+> This option has been superseded by using `--mode compact`. See the [mode](#mode) section for details.
-`compactor-id` is set.
-
-| influxdb3 serve option | Environment variable                   |
-| :--------------------- | :------------------------------------- |
-| `--run-compactions`    | `INFLUXDB3_ENTERPRISE_RUN_COMPACTIONS` |
 
 ---
 
@@ -1070,6 +1054,19 @@ compaction levels. The first element specifies the duration of the first level
 
 ---
 
+#### compaction-cleanup-wait
+
+Specifies the amount of time that the compactor waits after finishing a compaction run
+to delete files marked as needing deletion during that compaction run.
+
+**Default:** `10m`
+
+| influxdb3 serve option      | Environment variable                           |
+| :-------------------------- | :--------------------------------------------- |
+| `--compaction-cleanup-wait` | `INFLUXDB3_ENTERPRISE_COMPACTION_CLEANUP_WAIT` |
+
+---
+
 #### gen1-duration
 
 Specifies the duration that Parquet files are arranged into. Data timestamps
@@ -1088,7 +1085,7 @@ compactor can merge into larger generations.
 ### Caching
 
 - [preemptive-cache-age](#preemptive-cache-age)
-- [parquet-mem-cache-size-mb](#parquet-mem-cache-size-mb)
+- [parquet-mem-cache-size](#parquet-mem-cache-size)
 - [parquet-mem-cache-prune-percentage](#parquet-mem-cache-prune-percentage)
 - [parquet-mem-cache-prune-interval](#parquet-mem-cache-prune-interval)
 - [disable-parquet-mem-cache](#disable-parquet-mem-cache)
@@ -1108,17 +1105,16 @@ Specifies the interval to prefetch into the Parquet cache during compaction.
 
 ---
 
-#### parquet-mem-cache-size-mb
+#### parquet-mem-cache-size
+<span id="parquet-mem-cache-size-mb" />
 
-Defines the size of the in-memory Parquet cache in megabytes (MB).
+Specifies the size of the in-memory Parquet cache in megabytes or percentage of total available memory.
 
-**Default:** `1000`
+**Default:** `20%`
 
 | influxdb3 serve option      | Environment variable                |
-| :---------------------------- | :------------------------------------ |
+| :-------------------------- | :---------------------------------- |
-| `--parquet-mem-cache-size-mb` | `INFLUXDB3_PARQUET_MEM_CACHE_SIZE_MB` |
+| `--parquet-mem-cache-size`  | `INFLUXDB3_PARQUET_MEM_CACHE_SIZE`  |
-
----
 
 #### parquet-mem-cache-prune-percentage
 
@@ -1225,7 +1221,12 @@ engine uses.
 
 Specifies the Python package manager that the processing engine uses.
 
-**Default:** `10s`
+This option supports the following values:
+- `discover` _(default)_: Automatically discover available package manager
+- `pip`: Use pip package manager
+- `uv`: Use uv package manager
+
+**Default:** `discover`
 
 | influxdb3 serve option | Environment variable |
 | :--------------------- | :------------------- |

cypress/e2e/content/article-links.cy.js

@@ -9,23 +9,34 @@ describe('Article links', () => {
   function isDownloadLink(href) {
     // Check for common download file extensions
     const downloadExtensions = [
-      '.pdf', '.zip', '.tar.gz', '.tgz', '.rar', '.exe', '.dmg', '.pkg', 
+      '.pdf',
-      '.deb', '.rpm', '.xlsx', '.csv', '.doc', '.docx', '.ppt', '.pptx'
+      '.zip',
+      '.tar.gz',
+      '.tgz',
+      '.rar',
+      '.exe',
+      '.dmg',
+      '.pkg',
+      '.deb',
+      '.rpm',
+      '.xlsx',
+      '.csv',
+      '.doc',
+      '.docx',
+      '.ppt',
+      '.pptx',
     ];
 
     // Check for download domains or paths
-    const downloadDomains = [
+    const downloadDomains = ['dl.influxdata.com', 'downloads.influxdata.com'];
-      'dl.influxdata.com',
-      'downloads.influxdata.com'
-    ];
 
     // Check if URL contains a download extension
-    const hasDownloadExtension = downloadExtensions.some(ext => 
+    const hasDownloadExtension = downloadExtensions.some((ext) =>
       href.toLowerCase().endsWith(ext)
     );
 
     // Check if URL is from a download domain
-    const isFromDownloadDomain = downloadDomains.some(domain => 
+    const isFromDownloadDomain = downloadDomains.some((domain) =>
       href.toLowerCase().includes(domain)
     );
 
@@ -40,19 +51,31 @@ describe('Article links', () => {
       cy.request({
         method: 'HEAD',
         url: href,
-        failOnStatusCode: false,
+      }).then((response) => {
-        timeout: 10000 // 10 second timeout for download links
+        const message = `Link is broken: ${href} (status: ${response.status})`;
-      }).then(response => {
+        try {
           expect(response.status).to.be.lt(400);
+        } catch (e) {
+          // Log the broken link with the URL for better visibility in reports
+          cy.log(`❌ BROKEN LINK: ${href} (${response.status})`);
+          throw new Error(message);
+        }
       });
     } else {
       cy.log(`** Testing link: ${href} **`);
       cy.request({
         url: href,
         failOnStatusCode: false,
-        timeout: 30000 // 30 second timeout for regular links
+        timeout: 10000, // 10 second timeout for regular links
-      }).then(response => {
+      }).then((response) => {
+        const message = `Link is broken: ${href} (status: ${response.status})`;
+        try {
           expect(response.status).to.be.lt(400);
+        } catch (e) {
+          // Log the broken link with the URL for better visibility in reports
+          cy.log(`❌ BROKEN LINK: ${href} (${response.status})`);
+          throw new Error(message);
+        }
       });
     }
   }
@@ -60,14 +83,21 @@ describe('Article links', () => {
   subjects.forEach((subject) => {
     it(`contains valid internal links on ${subject}`, function () {
       cy.visit(`${subject}`);
-      
+      // Test internal links
-      // Test internal links (including anchor links)
+      // 1. Timeout and fail the test if article is not found
-      cy.get('article a[href^="/"]').each(($a) => {
+      // 2. Check each link.
-        const href = $a.attr('href');
+      // 3. If no links are found, continue without failing
-        // Skip links that contain "kapa.ai"
+      cy.get('article').then(($article) => {
-        if (!href.includes('kapa.ai')) {
+        // Find links without failing the test if none are found
-          testLink(href);
+        const $links = $article.find('a[href^="/"]');
+        if ($links.length === 0) {
+          cy.log('No internal links found on this page');
+          return;
         }
+        cy.wrap($links).each(($a) => {
+          const href = $a.attr('href');
+          testLink(href);
+        });
       });
     });
 
@@ -78,9 +108,16 @@ describe('Article links', () => {
       const missingAnchors = [];
 
       // Process anchor links individually
-      cy.get('article a[href^="#"]').each(($a) => {
+      cy.get('article').then(($article) => {
-        const href = $a.prop('href'); // Use prop() instead of attr()
+        const $anchorLinks = $article.find('a[href^="#"]');
-        if (href && href.length > 1) { // Skip empty anchors (#)
+        if ($anchorLinks.length === 0) {
+          cy.log('No anchor links found on this page');
+          return;
+        }
+        cy.wrap($anchorLinks).each(($a) => {
+            const href = $a.prop('href');
+            if (href && href.length > 1) {
+              // Skip empty anchors (#)
               // Get just the fragment part
               const url = new URL(href);
               const anchorId = url.hash.substring(1); // Remove the # character
@@ -91,7 +128,7 @@ describe('Article links', () => {
               }
 
               // Use DOM to check if the element exists, but don't fail if missing
-          cy.window().then(win => {
+              cy.window().then((win) => {
                 const element = win.document.getElementById(anchorId);
                 if (element) {
                   cy.log(`✅ Anchor target exists: #${anchorId}`);
@@ -102,10 +139,13 @@ describe('Article links', () => {
                 }
               });
             }
-      }).then(() => {
+          })
+          .then(() => {
             // After checking all anchors, log a summary
             if (missingAnchors.length > 0) {
-          cy.log(`⚠️ Found ${missingAnchors.length} missing anchor targets: ${missingAnchors.join(', ')}`);
+              cy.log(
+                `⚠️ Found ${missingAnchors.length} missing anchor targets: ${missingAnchors.join(', ')}`
+              );
             } else {
               cy.log('✅ All anchor targets are valid');
             }
@@ -114,12 +154,23 @@ describe('Article links', () => {
 
       it(`contains valid external links on ${subject}`, function () {
         cy.visit(`${subject}`);
-      
         // Test external links
-      cy.get('article a[href^="http"]').each(($a) => {
+        // 1. Timeout and fail the test if article is not found
+        // 2. Check each link.
+        // 3. If no links are found, continue without failing
+        cy.get('article').then(($article) => {
+          // Find links without failing the test if none are found
+          const $links = $article.find('a[href^="http"]');
+          if ($links.length === 0) {
+            cy.log('No external links found on this page');
+            return;
+          }
+          cy.wrap($links).each(($a) => {
             const href = $a.attr('href');
             testLink(href);
           });
         });
       });
     });
+  });
+});