diff mbox series

[net-next,2/4] netfilter: conntrack: revisit the gc initial rescheduling bias

Message ID 20220921095000.29569-3-fw@strlen.de (mailing list archive)
State Accepted
Commit 2aa192757005f130b2dd3547dda6e462e761199f
Delegated to: Netdev Maintainers
Headers show
Series [net-next,1/4] netfilter: conntrack: fix the gc rescheduling delay | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Pull request is its own cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 3 this patch: 3
netdev/cc_maintainers fail 1 blamed authors not CCed: pablo@netfilter.org; 3 maintainers not CCed: pablo@netfilter.org coreteam@netfilter.org kadlec@netfilter.org
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 3 this patch: 3
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 23 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Florian Westphal Sept. 21, 2022, 9:49 a.m. UTC
From: Antoine Tenart <atenart@kernel.org>

The previous commit changed the way the rescheduling delay is computed
which has a side effect: the bias is now represented as much as the
other entries in the rescheduling delay which makes the logic to kick in
only with very large sets, as the initial interval is very large
(INT_MAX).

Revisit the GC initial bias to allow more frequent GC for smaller sets
while still avoiding wakeups when a machine is mostly idle. We're moving
from a large initial value to pretending we have 100 entries expiring at
the upper bound. This way only a few entries having a small timeout
won't impact much the rescheduling delay and non-idle machines will have
enough entries to lower the delay when needed. This also improves
readability as the initial bias is now linked to what is computed
instead of being an arbitrary large value.

Fixes: 2cfadb761d3d ("netfilter: conntrack: revisit gc autotuning")
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_core.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 8efa6bd5703c..8208a28ea342 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -86,10 +86,12 @@  static DEFINE_MUTEX(nf_conntrack_mutex);
 /* clamp timeouts to this value (TCP unacked) */
 #define GC_SCAN_INTERVAL_CLAMP	(300ul * HZ)
 
-/* large initial bias so that we don't scan often just because we have
- * three entries with a 1s timeout.
+/* Initial bias pretending we have 100 entries at the upper bound so we don't
+ * wakeup often just because we have three entries with a 1s timeout while still
+ * allowing non-idle machines to wakeup more often when needed.
  */
-#define GC_SCAN_INTERVAL_INIT	INT_MAX
+#define GC_SCAN_INITIAL_COUNT	100
+#define GC_SCAN_INTERVAL_INIT	GC_SCAN_INTERVAL_MAX
 
 #define GC_SCAN_MAX_DURATION	msecs_to_jiffies(10)
 #define GC_SCAN_EXPIRED_MAX	(64000u / HZ)
@@ -1477,7 +1479,7 @@  static void gc_worker(struct work_struct *work)
 
 	if (i == 0) {
 		gc_work->avg_timeout = GC_SCAN_INTERVAL_INIT;
-		gc_work->count = 1;
+		gc_work->count = GC_SCAN_INITIAL_COUNT;
 		gc_work->start_time = start_time;
 	}