Merge pull request #230731 from NixOS/bump/netdata

netdata: 1.38.1 -> 1.39.0

2 files changed, 17 insertions, 1 deletions

diff --git a/nixos/doc/manual/release-notes/rl-2305.section.md b/nixos/doc/manual/release-notes/rl-2305.section.md
index 425b340b9ea..7eafa6a9bef 100644
--- a/nixos/doc/manual/release-notes/rl-2305.section.md
+++ b/nixos/doc/manual/release-notes/rl-2305.section.md
@@ -387,6 +387,8 @@ In addition to numerous new and upgraded packages, this release has the followin
   }
   ```
 
+- `services.netdata` offers a `deadlineBeforeStopSec` option which enable users who have netdata instance that takes time to initialize to not have systemd kill them for no reason.
+
 - `services.dhcpcd` service now don't solicit or accept IPv6 Router Advertisements on interfaces that use static IPv6 addresses.
   If network uses both IPv6 Unique local addresses (ULA) and global IPv6 address auto-configuration with SLAAC, must add the parameter `networking.dhcpcd.IPv6rs = true;`.
 
diff --git a/nixos/modules/services/monitoring/netdata.nix b/nixos/modules/services/monitoring/netdata.nix
index 92c870bb23f..bd0dea83e1a 100644
--- a/nixos/modules/services/monitoring/netdata.nix
+++ b/nixos/modules/services/monitoring/netdata.nix
@@ -169,6 +169,20 @@ in {
           See: <https://learn.netdata.cloud/docs/agent/anonymous-statistics>
         '';
       };
+
+      deadlineBeforeStopSec = mkOption {
+        type = types.int;
+        default = 120;
+        description = lib.mdDoc ''
+          In order to detect when netdata is misbehaving, we run a concurrent task pinging netdata (wait-for-netdata-up)
+          in the systemd unit.
+
+          If after a while, this task does not succeed, we stop the unit and mark it as failed.
+
+          You can control this deadline in seconds with this option, it's useful to bump it
+          if you have (1) a lot of data (2) doing upgrades (3) have low IOPS/throughput.
+        '';
+      };
     };
   };
 
@@ -205,7 +219,7 @@ in {
           while [ "$(${pkgs.netdata}/bin/netdatacli ping)" != pong ]; do sleep 0.5; done
         '';
 
-        TimeoutStopSec = 60;
+        TimeoutStopSec = cfg.deadlineBeforeStopSec;
         Restart = "on-failure";
         # User and group
         User = cfg.user;