From: Willy Tarreau <w@1wt.eu>
Date: Wed, 6 Nov 2024 16:51:57 +0000 (+0100)
Subject: DEBUG: wdt: set the default blocked task delay to 100 ms
X-Git-Tag: v3.1-dev12~11
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=5f4fe201160a94a1b93930e76c6ce01abb0144ad;p=thirdparty%2Fhaproxy.git

DEBUG: wdt: set the default blocked task delay to 100 ms

The warn-blocked-traffic-after can be significantly lowered. In any
case, in order to be usable it must be well below the limit to have a
chance to emit exploitable traces before the watchdog finally fires.
Even configured at 1ms it looks very difficult to trigger it on a
laptop doing SSL and compression, so applying a 100-fold factor to
cover for large configs and small machines sounds sane for 3.1. In any
case, even at 100ms, the service degradation becomes quite visible.
---

diff --git a/doc/configuration.txt b/doc/configuration.txt
index 7faf865ab6..21fc7e0cd6 100644
--- a/doc/configuration.txt
+++ b/doc/configuration.txt
@@ -4398,7 +4398,7 @@ quiet
 warn-blocked-traffic-after <time>
   This allows to adjust the delay after which a stuck task blocking the traffic
   will trigger the emission of a warning on the standard error output. The
-  delay is expressed in milliseconds and defaults to 1000 ms. Permitted values
+  delay is expressed in milliseconds and defaults to 100 ms. Permitted values
   must be comprised between 1 ms and 1000 ms included. Lower values will
   trigger warnings frequently and higher ones will rarely. The watchdog will
   kill a runaway task that fails to respond twice for one second anyway, so a
diff --git a/src/wdt.c b/src/wdt.c
index edd9c09b31..dcec435d4a 100644
--- a/src/wdt.c
+++ b/src/wdt.c
@@ -44,7 +44,7 @@ static struct {
 } per_thread_wd_ctx[MAX_THREADS];
 
 /* warn about stuck tasks after this delay (ns) */
-static unsigned int wdt_warn_blocked_traffic_ns = 1000000000U;
+static unsigned int wdt_warn_blocked_traffic_ns = 100000000U;
 
 /* Setup (or ping) the watchdog timer for thread <thr>. Returns non-zero on
  * success, zero on failure. It interrupts once per second of CPU time. It