Monitor GPFS scratch partition

Reviewed-by: Aleix Boné <abonerib@bsc.es>

m/common/base/env.nix

@@ -21,6 +21,8 @@
     }
   ];
 
+  environment.enableAllTerminfo = true;
+
   environment.variables = {
     EDITOR = "vim";
     VISUAL = "vim";

m/common/base/users.nix

@@ -56,7 +56,7 @@
         home = "/home/Computational/rpenacob";
         description = "Raúl Peñacoba";
         group = "Computational";
-        hosts = [ "owl1" "owl2" "hut" "tent" ];
+        hosts = [ "owl1" "owl2" "hut" "tent" "fox" ];
         hashedPassword = "$6$TZm3bDIFyPrMhj1E$uEDXoYYd1z2Wd5mMPfh3DZAjP7ztVjJ4ezIcn82C0ImqafPA.AnTmcVftHEzLB3tbe2O4SxDyPSDEQgJ4GOtj/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFYfXg37mauGeurqsLpedgA2XQ9d4Nm0ZGo/hI1f7wwH rpenacob@bsc"
@@ -69,7 +69,7 @@
         home = "/home/Computational/anavarro";
         description = "Antoni Navarro";
         group = "Computational";
-        hosts = [ "hut" "tent" "raccoon" ];
+        hosts = [ "hut" "tent" "raccoon" "fox" ];
         hashedPassword = "$6$QdNDsuLehoZTYZlb$CDhCouYDPrhoiB7/seu7RF.Gqg4zMQz0n5sA4U1KDgHaZOxy2as9pbIGeF8tOHJKRoZajk5GiaZv0rZMn7Oq31";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAILWjRSlKgzBPZQhIeEtk6Lvws2XNcYwHcwPv4osSgst5 anavarro@ssfhead"
@@ -82,7 +82,7 @@
         home = "/home/Computational/abonerib";
         description = "Aleix Boné";
         group = "Computational";
-        hosts = [ "owl1" "owl2" "hut" "tent" "raccoon" ];
+        hosts = [ "owl1" "owl2" "hut" "tent" "raccoon" "fox" ];
         hashedPassword = "$6$V1EQWJr474whv7XJ$OfJ0wueM2l.dgiJiiah0Tip9ITcJ7S7qDvtSycsiQ43QBFyP4lU0e0HaXWps85nqB4TypttYR4hNLoz3bz662/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIIFiqXqt88VuUfyANkZyLJNiuroIITaGlOOTMhVDKjf abonerib@bsc"
@@ -121,7 +121,7 @@
         home = "/home/Computational/dalvare1";
         description = "David Álvarez";
         group = "Computational";
-        hosts = [ "hut" "tent" ];
+        hosts = [ "hut" "tent" "fox" ];
         hashedPassword = "$6$mpyIsV3mdq.rK8$FvfZdRH5OcEkUt5PnIUijWyUYZvB1SgeqxpJ2p91TTe.3eQIDTcLEQ5rxeg.e5IEXAZHHQ/aMsR5kPEujEghx0";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGEfy6F4rF80r4Cpo2H5xaWqhuUZzUsVsILSKGJzt5jF dalvare1@ssfhead"
@@ -140,6 +140,20 @@
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKGt0ESYxekBiHJQowmKpfdouw0hVm3N7tUMtAaeLejK vincent@varch"
         ];
       };
+
+      pmartin1 = {
+        # Arbitrary UID but large so it doesn't collide with other users on ssfhead.
+        uid = 9652;
+        isNormalUser = true;
+        home = "/home/Computational/pmartin1";
+        description = "Pedro J. Martinez-Ferrer";
+        group = "Computational";
+        hosts = [ "fox" ];
+        hashedPassword = "$6$nIgDMGnt4YIZl3G.$.JQ2jXLtDPRKsbsJfJAXdSvjDIzRrg7tNNjPkLPq3KJQhMjfDXRUvzagUHUU2TrE2hHM8/6uq8ex0UdxQ0ysl.";
+        openssh.authorizedKeys.keys = [
+          "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIV5LEAII5rfe1hYqDYIIrhb1gOw7RcS1p2mhOTqG+zc pedro@pedro-ThinkPad-P14s-Gen-2a"
+        ];
+      };
     };
 
     groups = {

m/fox/configuration.nix

@@ -14,7 +14,7 @@
   swapDevices = lib.mkForce [];
 
   boot.initrd.availableKernelModules = [ "xhci_pci" "ahci" "nvme" "usbhid" "usb_storage" "sd_mod" ];
-  boot.kernelModules = [ "kvm-amd" ];
+  boot.kernelModules = [ "kvm-amd" "amd_uncore" ];
 
   hardware.cpu.amd.updateMicrocode = lib.mkDefault config.hardware.enableRedistributableFirmware;
   hardware.cpu.intel.updateMicrocode = lib.mkForce false;
@@ -22,6 +22,14 @@
   # Use performance for benchmarks
   powerManagement.cpuFreqGovernor = "performance";
 
+  # Disable NUMA balancing
+  boot.kernel.sysctl."kernel.numa_balancing" = 0;
+
+  # Expose kernel addresses
+  boot.kernel.sysctl."kernel.kptr_restrict" = 0;
+
+  services.openssh.settings.X11Forwarding = true;
+
   networking = {
     timeServers = [ "ntp1.upc.edu" "ntp2.upc.edu" ];
     hostName = "fox";

m/hut/gpfs-probe.sh

@@ -2,10 +2,20 @@
 
 N=500
 
-t=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N} 2>&1; rm -f /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N}")
+t_proj=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N} 2>&1; rm -f /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N}")
+t_scratch=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /gpfs/scratch/bsc15/rodrigo/probe/gpfs.{1..$N} 2>&1; rm -f /gpfs/scratch/bsc15/rodrigo/probe/gpfs.{1..$N}")
+t_home=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /home/bsc/bsc015557/.gpfs/{1..$N} 2>&1; rm -f /home/bsc/bsc015557/.gpfs/{1..$N}")
 
-if [ -z "$t" ]; then
-  t="5.00"
+if [ -z "$t_proj" ]; then
+  t_proj="5.00"
+fi
+
+if [ -z "$t_scratch" ]; then
+  t_scratch="5.00"
+fi
+
+if [ -z "$t_home" ]; then
+  t_home="5.00"
 fi
 
 cat <<EOF
@@ -14,5 +24,7 @@ Content-Type: text/plain; version=0.0.4; charset=utf-8; escaping=values
 
 # HELP gpfs_touch_latency Time to create $N files.
 # TYPE gpfs_touch_latency gauge
-gpfs_touch_latency $t
+gpfs_touch_latency{partition="projects"} $t_proj
+gpfs_touch_latency{partition="home"} $t_home
+gpfs_touch_latency{partition="scratch"} $t_scratch
 EOF

m/hut/monitoring.nix

@@ -267,6 +267,14 @@
           }
         ];
       }
+      {
+        job_name = "tent";
+        static_configs = [
+          {
+            targets = [ "127.0.0.1:29002" ]; # Node exporter
+          }
+        ];
+      }
     ];
   };
 }

m/module/vpn-dac.nix

@@ -14,8 +14,6 @@
         remote vpn.ac.upc.edu 80
         resolv-retry infinite
         nobind
-        ;user nobody
-        ;group nogroup
         persist-key
         persist-tun
         ca ${./vpn-dac/ca.crt}
@@ -28,8 +26,9 @@
         auth-user-pass ${config.age.secrets.vpn-dac-login.path}
         reneg-sec 0
 
-	# Ignore 10.0.0.0 route as is not needed
-        pull-filter ignore "route 10.0.0.0"
+        # Only route fox-ipmi
+        pull-filter ignore "route "
+        route 147.83.35.27 255.255.255.255
       '';
     };
   };

m/tent/monitoring.nix

@@ -165,6 +165,7 @@
             "anella-bsc.cesca.cat"
             "upc-anella.cesca.cat"
             "fox.ac.upc.edu"
+            "fox-ipmi.ac.upc.edu"
             "arenys5.ac.upc.edu"
             "arenys0-2.ac.upc.edu"
             "epi01.bsc.es"

web/content/access/index.md

@@ -5,18 +5,12 @@ description: "Request access to the machines"
 
 ![Cave](./cave.jpg)
 
-Before requesting access to the jungle machines, you must be able to access the
-`ssfhead.bsc.es` node (only available via the intranet or VPN). You can request
-access to the login machine using a resource petition in the BSC intranet.
-
-Then, to request access to the machines we will need some information about you:
+To request access to the machines we will need some information:
 
 1. Which machines you want access to ([hut](/hut), [fox](/fox), owl1, owl2, eudy, koro...)
-1. Your user name and user id (to match the NFS permissions)
+1. Your user name (make sure it matches the one you use for the BSC intranet)
 1. Your real name and surname (for identification purposes)
 1. The salted hash of your login password, generated with `mkpasswd -m sha-512`
 1. An SSH public key of type Ed25519 (can be generated with `ssh-keygen -t ed25519`)
 
-Send an email to <jungle@bsc.es> with the details, or directly open a
-merge request in the [jungle
-repository](https://pm.bsc.es/gitlab/rarias/jungle/).
+Send an email to <jungle@bsc.es> with the details.