4 Commits

Author SHA1 Message Date
5cfd7f0858 Fetch website from its own git repository
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-02 15:45:21 +02:00
9c5e22d62d Add script to trim the repository
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-02 15:44:56 +02:00
00fe0f46a1 Add acinca user
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 12:27:43 +02:00
79940876c3 Restart slurmd on failure
A failure to reach the control node can cause slurmd to fail and the
unit remains in the failed state until is manually restarted. Instead,
try to restart the service every 30 seconds, forever:

    owl1% systemctl show slurmd | grep -E 'Restart=|RestartUSec='
    Restart=on-failure
    RestartUSec=30s
    owl1% pgrep slurmd
    5903
    owl1% sudo kill -SEGV 5903
    owl1% pgrep slurmd
    6137

Fixes: #177
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-09-30 17:20:39 +02:00
5 changed files with 70 additions and 6 deletions

46
doc/trim.sh Executable file
View File

@@ -0,0 +1,46 @@
#!/bin/sh
# Trims the jungle repository by moving the website to its own repository and
# removing it from jungle. It also removes big pdf files and kernel
# configurations so the jungle repository is small.
set -e
if [ -e oldjungle -o -e newjungle -o -e website ]; then
echo "remove oldjungle/, newjungle/ and website/ first"
exit 1
fi
# Clone the old jungle repo
git clone gitea@tent:rarias/jungle.git oldjungle
# First split the website into a new repository
mkdir website && git -C website init -b master
git-filter-repo \
--path web \
--subdirectory-filter web \
--source oldjungle \
--target website
# Then remove the website, pdf files and big kernel configs
mkdir newjungle && git -C newjungle init -b master
git-filter-repo \
--invert-paths \
--path web \
--path-glob 'doc*.pdf' \
--path-glob '**/kernel/configs/lockdep' \
--path-glob '**/kernel/configs/defconfig' \
--source oldjungle \
--target newjungle
set -x
du -sh oldjungle newjungle website
# 57M oldjungle
# 2,3M newjungle
# 6,4M website
du -sh --exclude=.git oldjungle newjungle website
# 30M oldjungle
# 700K newjungle
# 3,5M website

View File

@@ -156,7 +156,6 @@
};
csiringo = {
# Arbitrary UID but large so it doesn't collide with other users on ssfhead.
uid = 9653;
isNormalUser = true;
home = "/home/Computational/csiringo";
@@ -168,6 +167,19 @@
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHA65zvvG50iuFEMf+guRwZB65jlGXfGLF4HO+THFaed csiringo@bsc.es"
];
};
acinca = {
uid = 9654;
isNormalUser = true;
home = "/home/Computational/acinca";
description = "Arnau Cinca";
group = "Computational";
hosts = [ "apex" "hut" "fox" "owl1" "owl2" ];
hashedPassword = "$6$S6PUeRpdzYlidxzI$szyvWejQ4hEN76yBYhp1diVO5ew1FFg.cz4lKiXt2Idy4XdpifwrFTCIzLTs5dvYlR62m7ekA5MrhcVxR5F/q/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFmMqKqPg4uocNOr3O41kLbZMOMJn3m2ZdN1JvTR96z3 bsccns@arnau-bsc"
];
};
};
groups = {

View File

@@ -2,10 +2,13 @@
let
website = pkgs.stdenv.mkDerivation {
name = "jungle-web";
src = theFlake;
src = pkgs.fetchgit {
url = "https://jungle.bsc.es/git/rarias/jungle-website.git";
rev = "739bf0175a7f05380fe7ad7023ff1d60db1710e1";
hash = "sha256-ea5DzhYTzZ9TmqD+x95rdNdLbxPnBluqlYH2NmBYmc4=";
};
buildInputs = [ pkgs.hugo ];
buildPhase = ''
cd web
rm -rf public/
hugo
'';

View File

@@ -16,7 +16,7 @@
# If slurmd fails to contact the control server it will fail, causing the
# node to remain out of service until manually restarted. Always try to
# restart it.
Restart = "on-failure";
Restart = "always";
RestartSec = "30s";
};

View File

@@ -2,10 +2,13 @@
let
website = pkgs.stdenv.mkDerivation {
name = "jungle-web";
src = theFlake;
src = pkgs.fetchgit {
url = "https://jungle.bsc.es/git/rarias/jungle-website.git";
rev = "739bf0175a7f05380fe7ad7023ff1d60db1710e1";
hash = "sha256-ea5DzhYTzZ9TmqD+x95rdNdLbxPnBluqlYH2NmBYmc4=";
};
buildInputs = [ pkgs.hugo ];
buildPhase = ''
cd web
rm -rf public/
hugo
'';