feat(users/flokli/nixos/archeology-ec2): automate bucket log parsing r/6996

This adds a `parse-bucket-logs.{service,timer}`, running once every
night at 3AM UTC, figuring out the last time it was run and parsing
bucket logs for all previous days.

It invokes the `archeology-parse-bucket-logs` script to produce
a .parquet file with the bucket logs in `s3://nix-cache-log/log/` for
that day (inside a temporary directory), then on success uploads the
produced parquet file to
`s3://nix-archeologist/nix-cache-bucket-logs/yyyy-mm-dd.parquet`.

Change-Id: Ia75ca8c43f8074fbaa34537ffdba68350c504e52
Reviewed-on: https://cl.tvl.fyi/c/depot/+/10011
Reviewed-by: edef <edef@edef.eu>
Tested-by: BuildkiteCI

1 files changed, 18 insertions, 0 deletions

diff --git a/users/flokli/nixos/archeology-ec2/configuration.nix b/users/flokli/nixos/archeology-ec2/configuration.nix
index af10771adc44..f0fc0c5d095c 100644
--- a/users/flokli/nixos/archeology-ec2/configuration.nix
+++ b/users/flokli/nixos/archeology-ec2/configuration.nix
@@ -6,6 +6,24 @@
     ../profiles/archeology.nix
   ];
 
+  systemd.timers.parse-bucket-logs = {
+    wantedBy = [ "multi-user.target" ];
+    timerConfig.OnCalendar = "*-*-* 03:00:00 UTC";
+  };
+
+  systemd.services.parse-bucket-logs = {
+    path = [ depot.users.flokli.archeology.parse-bucket-logs ];
+    serviceConfig = {
+      Type = "oneshot";
+      ExecStart = (pkgs.writers.writePython3 "parse-bucket-logs-continuously"
+        {
+          libraries = [ pkgs.python3Packages.boto3 ];
+        } ./parse-bucket-logs-continuously.py);
+      DynamicUser = "yes";
+      StateDirectory = "parse-bucket-logs";
+    };
+  };
+
   environment.systemPackages = [
     depot.users.flokli.archeology.parse-bucket-logs
   ];