diff options
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/blog-Tennnessee-build-farm.org | 499 |
1 files changed, 499 insertions, 0 deletions
diff --git a/docs/blog-Tennnessee-build-farm.org b/docs/blog-Tennnessee-build-farm.org new file mode 100644 index 0000000..8b3ede9 --- /dev/null +++ b/docs/blog-Tennnessee-build-farm.org @@ -0,0 +1,499 @@ +#+TITLE: Setup of a simple Guix build farm and substitute server +#+AUTHOR: Collin J. Doering + +A few months ago [[https://lists.gnu.org/archive/html/guix-devel/2024-07/msg00033.html][I announced on the guix mailing list]] that there was a new North American +based Guix substitute server and build farm, cuirass.genenetwork.org. This article provides +further information about how the build farm and substitute server was setup, and how you can +do so for yourself or your organization. Having more Guix substitutes servers available +improves build diversity (which can be checked with [[https://guix.gnu.org/manual/en/html_node/Invoking-guix-challenge.html][guix challenge]]), as well as substitute +availability and improved response times due to server locality. + +* TODO note inspiration, and in cases direct copy from https://git.savannah.gnu.org/cgit/guix/maintenance.git/tree/hydra/berlin.scm + +* Setting up a Minimal Guix Build Farm and Substitute Server + +Though a Guix build farm and substitute server could be deployed on any distribution, we +naturally chose to use Guix itself. There are a variety of components that provide the +necessary functionality: + +- [[https://guix.gnu.org/cuirass/][Cuirass]] :: Watches the the guix channel repository for changes, and manages building of + derivations, packages, etc.. +- [[https://guix.gnu.org/manual/en/html_node/Invoking-guix-publish.html][guix-publish]] :: Provides substitute archives for consumption by users (indirectly via nginx + as a local proxy). +- nginx :: Acts as a reverse proxy for Cuirass and guix-publish. +- certbot :: Fetches ssl certificates so cuirass and substitutes can be served over https. +- anonip :: Anatomizes http logs to preserver user privacy. + +How each of these components are setup is detailed below, component-by-component. You can see +the full source-code for the Tennessee build farm at +https://git.genenetwork.org/guix-north-america/. + +** Cuirass - building packages + +*** Define Cuirass Specs + +#+begin_src scheme + (define %cuirass-specs + #~(list (specification + (name "guix") + (priority 0) + (build '(channels guix)) + (channels %default-channels)))) +#+end_src + +*** Setup Cuirass Service + +#+begin_src scheme + (service cuirass-service-type + (cuirass-configuration + (host "localhost") + (specifications %cuirass-specs))) +#+end_src + +** Provide Substitutes using Guix Publish + +#+begin_src scheme + (service guix-publish-service-type + (guix-publish-configuration + (port 3000) + (cache "/var/cache/guix/publish"))) +#+end_src + +** Anonomize IPs (anonip) + +#+begin_src scheme + (define (anonip-service file) + (service anonip-service-type + (anonip-configuration + (input (format #false "/var/run/anonip/~a" file)) + (output (format #false "/var/log/anonip/~a" file))) + + (define %anonip-log-files + ;; List of files handled by Anonip + '("http.access.log" + "https.access.log")) + + (define (log-file->anonip-service-name file) + "Return the name of the Anonip service handling FILE, a log file." + (symbol-append 'anonip-/var/log/anonip/ (string->symbol file))) +#+end_src + +** Certbot + +#+begin_src scheme + (define* (le host #:optional privkey) + (string-append "/etc/letsencrypt/live/" + host "/" + (if privkey "privkey" "fullchain") + ".pem")) +#+end_src + +** Nginx Reverse Proxy + +*** abc + +#+begin_src scheme + (define publish-robots.txt + ;; Try to prevent good-faith crawlers from downloading substitutes. Allow + ;; indexing the root—which is expected to be static or cheap—to remain visible + ;; in search engine results for, e.g., 'Guix CI'. + "\ + User-agent: *\r + Disallow: /\r + Allow: /$\r + \r + ") +#+end_src + +#+begin_src scheme + (define (publish-locations url) + "Return the nginx location blocks for 'guix publish' running on URL." + (list (nginx-location-configuration + (uri "/nix-cache-info") + (body + (list + (string-append + "proxy_pass " url "/nix-cache-info;") + ;; Cache this file since that's always the first thing we ask + ;; for. + "proxy_cache static;" + "proxy_cache_valid 200 100d;" ; cache hits for a looong time. + "proxy_cache_valid any 5m;" ; cache misses/others for 5 min. + "proxy_ignore_client_abort on;" + + ;; We need to hide and ignore the Set-Cookie header to enable + ;; caching. + "proxy_hide_header Set-Cookie;" + "proxy_ignore_headers Set-Cookie;"))) + + (nginx-location-configuration + (uri "/nar/") + (body + (list + (string-append "proxy_pass " url ";") + "client_body_buffer_size 256k;" + + ;; Be more tolerant of delays when fetching a nar. + "proxy_read_timeout 60s;" + "proxy_send_timeout 60s;" + + ;; Enable caching for nar files, to avoid reconstructing and + ;; recompressing archives. + "proxy_cache nar;" + "proxy_cache_valid 200 30d;" ; cache hits for 1 month + "proxy_cache_valid 504 3m;" ; timeout, when hydra.gnu.org is overloaded + "proxy_cache_valid any 1h;" ; cache misses/others for 1h. + + "proxy_ignore_client_abort on;" + + ;; Nars are already compressed. + "gzip off;" + + ;; We need to hide and ignore the Set-Cookie header to enable + ;; caching. + "proxy_hide_header Set-Cookie;" + "proxy_ignore_headers Set-Cookie;" + + ;; Provide a 'content-length' header so that 'guix + ;; substitute-binary' knows upfront how much it is downloading. + ;; "add_header Content-Length $body_bytes_sent;" + ))) + + (nginx-location-configuration + (uri "~ \\.narinfo$") + (body + (list + ;; Since 'guix publish' has its own caching, and since it relies + ;; on the atime of cached narinfos to determine whether a + ;; narinfo can be removed from the cache, don't do any caching + ;; here. + (string-append "proxy_pass " url ";") + + ;; For HTTP pipelining. This has a dramatic impact on + ;; performance. + "client_body_buffer_size 128k;" + + ;; Narinfos requests are short, serve many of them on a + ;; connection. + "keepalive_requests 600;" + + ;; Do not tolerate slowness of hydra.gnu.org when fetching + ;; narinfos: better return 504 quickly than wait forever. + "proxy_connect_timeout 10s;" + "proxy_read_timeout 10s;" + "proxy_send_timeout 10s;" + + ;; 'guix publish --ttl' produces a 'Cache-Control' header for + ;; use by 'guix substitute'. Let it through rather than use + ;; nginx's "expire" directive since the expiration time defined + ;; by 'guix publish' is the right one. + "proxy_pass_header Cache-Control;" + + "proxy_ignore_client_abort on;" + + ;; We need to hide and ignore the Set-Cookie header to enable + ;; caching. + "proxy_hide_header Set-Cookie;" + "proxy_ignore_headers Set-Cookie;"))) + + ;; Content-addressed files served by 'guix publish'. + (nginx-location-configuration + (uri "/file/") + (body + (list + (string-append "proxy_pass " url ";") + + "proxy_cache cas;" + "proxy_cache_valid 200 200d;" ; cache hits + "proxy_cache_valid any 5m;" ; cache misses/others + + "proxy_ignore_client_abort on;"))) + + ;; Try to prevent good-faith crawlers from downloading substitutes. + (nginx-location-configuration + (uri "= /robots.txt") + (body + (list + #~(string-append "try_files " + #$(plain-file "robots.txt" publish-robots.txt) + " =404;") + "root /;"))))) +#+end_src + +#+begin_src scheme + (define (balg02-locations publish-url) + "Return nginx location blocks with 'guix publish' reachable at + PUBLISH-URL." + (append (publish-locations publish-url) + (list + ;; Cuirass. + (nginx-location-configuration + (uri "/") + (body (list "proxy_pass http://localhost:8081;" + ;; ;; See + ;; ;; <https://community.torproject.org/onion-services/advanced/onion-location/>. + ;; (string-append + ;; "add_header Onion-Location http://" %ci-onion + ;; "$request_uri;") + ))) + (nginx-location-configuration + (uri "~ ^/admin") + (body + (list "if ($ssl_client_verify != SUCCESS) { return 403; } proxy_pass http://localhost:8081;"))) + + (nginx-location-configuration + (uri "/static") + (body + (list + "proxy_pass http://localhost:8081;" + ;; Cuirass adds a 'Cache-Control' header, honor it. + "proxy_cache static;" + "proxy_cache_valid 200 2d;" + "proxy_cache_valid any 10m;" + "proxy_ignore_client_abort on;"))) + + (nginx-location-configuration + (uri "/download") ;Cuirass "build products" + (body + (list + "proxy_pass http://localhost:8081;" + "expires 10d;" ;override 'Cache-Control' + "proxy_cache static;" + "proxy_cache_valid 200 30d;" + "proxy_cache_valid any 10m;" + "proxy_ignore_client_abort on;"))) + + (nginx-location-configuration ;certbot + (uri "/.well-known") + (body (list "root /var/www;")))))) +#+end_src + +#+begin_src scheme + (define %publish-url "http://localhost:3000") + + (define %tls-settings + (list + ;; Make sure SSL is disabled. + "ssl_protocols TLSv1.1 TLSv1.2 TLSv1.3;" + ;; Disable weak cipher suites. + "ssl_ciphers HIGH:!aNULL:!MD5;" + "ssl_prefer_server_ciphers on;" + + ;; Use our own DH parameters created with: + ;; openssl dhparam -out dhparams.pem 2048 + ;; as suggested at <https://weakdh.org/sysadmin.html>. + "ssl_dhparam /etc/dhparams.pem;")) +#+end_src + +#+begin_src scheme + (define %balg02-servers + (list + ;; Redirect domains that don't explicitly support HTTP (below) to HTTPS. + (nginx-server-configuration + (listen '("80")) + (raw-content + (list "return 308 https://$host$request_uri;"))) + + ;; Domains that still explicitly support plain HTTP. + (nginx-server-configuration + (listen '("80")) + (server-name `("cuirass.genenetwork.org" + ;; <https://logs.guix.gnu.org/guix/2021-11-20.log#155427> + "~[0-9]$" + ; TODO: onion + ; ,(regexp-quote %ci-onion) + )) + (locations (balg02-locations %publish-url)) + (raw-content + (list + "access_log /var/run/anonip/http.access.log;" + "proxy_set_header X-Forwarded-Host $host;" + "proxy_set_header X-Forwarded-Port $server_port;" + "proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;"))) + + ;; HTTPS servers + (nginx-server-configuration + (listen '("443 ssl")) + (server-name '("cuirass.genenetwork.org")) + (ssl-certificate (le "cuirass.genenetwork.org")) + (ssl-certificate-key (le "cuirass.genenetwork.org" 'key)) + (locations (balg02-locations %publish-url)) + (raw-content + (append + %tls-settings + (list + "access_log /var/run/anonip/https.access.log;" + "proxy_set_header X-Forwarded-Host $host;" + "proxy_set_header X-Forwarded-Port $server_port;" + "proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;" + ;; TODO: + ;; For Cuirass admin interface authentication + ;; "ssl_client_certificate /etc/ssl-ca/certs/ca.crt;" + ;; "ssl_verify_client optional;" + )))))) +#+end_src + +#+begin_src scheme + (define %extra-content + (list + "default_type application/octet-stream;" + "sendfile on;" + + (accept-languages) + + ;; Maximum chunk size to send. Partly this is a workaround for + ;; <http://bugs.gnu.org/19939>, but also the nginx docs mention that + ;; "Without the limit, one fast connection may seize the worker + ;; process entirely." + ;; <http://nginx.org/en/docs/http/ngx_http_core_module#sendfile_max_chunk> + "sendfile_max_chunk 1m;" + + "keepalive_timeout 65;" + + ;; Use HTTP 1.1 to talk to the backend so we benefit from keep-alive + ;; connections and chunked transfer encoding. The latter allows us to + ;; make sure we do not cache partial downloads. + "proxy_http_version 1.1;" + + ;; The 'inactive' parameter for caching is not very useful in our + ;; case: all that matters is that LRU sweeping happens when 'max_size' + ;; is hit. + + ;; cache for nar files + "proxy_cache_path /var/cache/nginx/nar" + " levels=2" + " inactive=8d" ; inactive keys removed after 8d + " keys_zone=nar:4m" ; nar cache meta data: ~32K keys + " max_size=10g;" ; total cache data size max + + ;; cache for content-addressed files + "proxy_cache_path /var/cache/nginx/cas" + " levels=2" + " inactive=180d" ; inactive keys removed after 180d + " keys_zone=cas:8m" ; nar cache meta data: ~64K keys + " max_size=50g;" ; total cache data size max + + ;; cache for build logs + "proxy_cache_path /var/cache/nginx/logs" + " levels=2" + " inactive=60d" ; inactive keys removed after 60d + " keys_zone=logs:8m" ; narinfo meta data: ~64K keys + " max_size=4g;" ; total cache data size max + + ;; cache for static data + "proxy_cache_path /var/cache/nginx/static" + " levels=1" + " inactive=10d" ; inactive keys removed after 10d + " keys_zone=static:1m" ; nar cache meta data: ~8K keys + " max_size=200m;" ; total cache data size max + + ;; If Hydra cannot honor these delays, then something is wrong and + ;; we'd better drop the connection and return 504. + "proxy_connect_timeout 10s;" + "proxy_read_timeout 10s;" + "proxy_send_timeout 10s;" + + ;; Cache timeouts for a little while to avoid increasing pressure. + "proxy_cache_valid 504 30s;")) +#+end_src + +#+begin_src scheme + (define %nginx-configuration + (nginx-configuration + (server-blocks %balg02-servers) + (server-names-hash-bucket-size 128) + (modules + (list + ;; Module to redirect users to the localized pages of their choice. + (file-append nginx-accept-language-module + "/etc/nginx/modules/ngx_http_accept_language_module.so"))) + (global-directives + '((worker_processes . 16) + (pcre_jit . on) + (events . ((worker_connections . 1024))))) + (extra-content + (string-join %extra-content "\n")) + (shepherd-requirement + (map log-file->anonip-service-name + %anonip-log-files)))) +#+end_src + +*** Cache activation + +#+begin_src scheme + (define %nginx-cache-activation + ;; Make sure /var/cache/nginx exists on the first run. + (simple-service 'nginx-/var/cache/nginx + activation-service-type + (with-imported-modules '((guix build utils)) + #~(begin + (use-modules (guix build utils)) + (mkdir-p "/var/cache/nginx"))))) +#+end_src + +*** Deploy hook + +#+begin_src scheme + (define %nginx-deploy-hook + (program-file + "nginx-deploy-hook" + #~(let ((pid (call-with-input-file "/var/run/nginx/pid" read))) + (kill pid SIGHUP)))) +#+end_src + +** Setup guix-daemon + +- Allow for substitutes from this server +- Adjust guix-daemon configuration (timeouts, # of build accounts, # of cores to use) + +#+begin_src scheme + (define* (guix-daemon-config #:key (max-jobs 5) (cores 4) + (build-accounts-to-max-jobs-ratio 4) + (authorized-keys '()) + (substitute-urls '())) + (guix-configuration + (substitute-urls substitute-urls) + (authorized-keys authorized-keys) + + ;; We don't want to let builds get stuck for too long, but we still want + ;; to allow building things that can take a while (eg. 3h). Adjust as necessary. + (max-silent-time 3600) + (timeout (* 6 3600)) + + (log-compression 'gzip) ;be friendly to 'guix publish' users + + (build-accounts (* build-accounts-to-max-jobs-ratio max-jobs)) + (extra-options (list "--max-jobs" (number->string max-jobs) + "--cores" (number->string cores) + "--gc-keep-derivations")))) +#+end_src + +#+begin_src scheme + (modify-services %base-services + (guix-service-type config => (guix-daemon-config + #:substitute-urls + '("https://cuirass.genenetwork.org") + #:max-jobs 20 + #:cores 4 + #:authorized-keys + (cons + (local-file "../../../.pubkeys/guix/cuirass.genenetwork.org.pub") + %default-authorized-guix-keys) + #:build-accounts-to-max-jobs-ratio 5))) +#+end_src + +** Optional + +*** Onion service + +* Setup + +TODO: talk about setup of Tennessee Guix Build Farm and Substitute Server specifics (eg. +remote install) + +* Conclusion + +TODO: ... + +- In the future, we hope to work with Guix maintainers to include this substitute server as + one of the provided Guix System defaults. |