The conntrack garbage collection worker uses an adaptive algorithm that adjusts the scan interval based on the average timeout of tracked entries. The upper bound of this interval is hardcoded as GC_SCAN_INTERVAL_MAX (60 seconds). Expose the upper bound as a new sysctl, net.netfilter.nf_conntrack_gc_scan_interval_max, so it can be tuned at runtime without rebuilding the kernel. The default remains 60 seconds to preserve existing behavior. The sysctl is global and read-only in non-init network namespaces, consistent with nf_conntrack_max and nf_conntrack_buckets. In environments where long-lived offloaded flows dominate the table, the adaptive average drifts toward the maximum, delaying cleanup of short-lived expired entries such as those in TCP CLOSE state (10s timeout). Adding sysctl to set the maximum GC scan helps to tune according to the evironment. Signed-off-by: Prasanna S Panchamukhi cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: Simon Horman cc: Jonathan Corbet cc: Shuah Khan cc: Pablo Neira Ayuso cc: Florian Westphal cc: Phil Sutter cc: netdev@vger.kernel.org cc: linux-doc@vger.kernel.org cc: linux-kernel@vger.kernel.org to: netfilter-devel@vger.kernel.org cc: coreteam@netfilter.org --- Documentation/networking/nf_conntrack-sysctl.rst | 11 +++++++++++ include/net/netfilter/nf_conntrack.h | 1 + net/netfilter/nf_conntrack_core.c | 9 ++++++--- net/netfilter/nf_conntrack_standalone.c | 10 ++++++++++ 4 files changed, 28 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index 35f889259fcd..c848eef9bc4f 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -64,6 +64,17 @@ nf_conntrack_frag6_timeout - INTEGER (seconds) Time to keep an IPv6 fragment in memory. +nf_conntrack_gc_scan_interval_max - INTEGER (seconds) + default 60 + + Maximum interval between garbage collection scans of the connection + tracking table. The GC worker uses an adaptive algorithm that adjusts + the scan interval based on average entry timeouts; this parameter caps + the upper bound. Lower values cause expired entries (e.g. connections + in CLOSE state) to be cleaned up faster, at the cost of slightly more + CPU usage. Minimum value is 1. + This sysctl is only writeable in the initial net namespace. + nf_conntrack_generic_timeout - INTEGER (seconds) default 600 diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index bc42dd0e10e6..0449577f322e 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -331,6 +331,7 @@ extern struct hlist_nulls_head *nf_conntrack_hash; extern unsigned int nf_conntrack_htable_size; extern seqcount_spinlock_t nf_conntrack_generation; extern unsigned int nf_conntrack_max; +extern unsigned int nf_conntrack_gc_scan_interval_max; /* must be called with rcu read lock held */ static inline void diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 27ce5fda8993..54949246f329 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -91,7 +91,7 @@ static DEFINE_MUTEX(nf_conntrack_mutex); * allowing non-idle machines to wakeup more often when needed. */ #define GC_SCAN_INITIAL_COUNT 100 -#define GC_SCAN_INTERVAL_INIT GC_SCAN_INTERVAL_MAX +#define GC_SCAN_INTERVAL_INIT nf_conntrack_gc_scan_interval_max #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) #define GC_SCAN_EXPIRED_MAX (64000u / HZ) @@ -204,6 +204,9 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_max); + +unsigned int nf_conntrack_gc_scan_interval_max __read_mostly = GC_SCAN_INTERVAL_MAX; + seqcount_spinlock_t nf_conntrack_generation __read_mostly; static siphash_aligned_key_t nf_conntrack_hash_rnd; @@ -1568,7 +1571,7 @@ static void gc_worker(struct work_struct *work) delta_time = nfct_time_stamp - gc_work->start_time; /* re-sched immediately if total cycle time is exceeded */ - next_run = delta_time < (s32)GC_SCAN_INTERVAL_MAX; + next_run = delta_time < (s32)nf_conntrack_gc_scan_interval_max; goto early_exit; } @@ -1630,7 +1633,7 @@ static void gc_worker(struct work_struct *work) gc_work->next_bucket = 0; - next_run = clamp(next_run, GC_SCAN_INTERVAL_MIN, GC_SCAN_INTERVAL_MAX); + next_run = clamp(next_run, GC_SCAN_INTERVAL_MIN, nf_conntrack_gc_scan_interval_max); delta_time = max_t(s32, nfct_time_stamp - gc_work->start_time, 1); if (next_run > (unsigned long)delta_time) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 207b240b14e5..f8cab779763f 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -637,6 +637,7 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif + NF_SYSCTL_CT_GC_SCAN_INTERVAL_MAX, NF_SYSCTL_CT_LAST_SYSCTL, }; @@ -920,6 +921,14 @@ static struct ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, #endif + [NF_SYSCTL_CT_GC_SCAN_INTERVAL_MAX] = { + .procname = "nf_conntrack_gc_scan_interval_max", + .data = &nf_conntrack_gc_scan_interval_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + .extra1 = SYSCTL_ONE, + }, }; static struct ctl_table nf_ct_netfilter_table[] = { @@ -1043,6 +1052,7 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_MAX].mode = 0444; table[NF_SYSCTL_CT_EXPECT_MAX].mode = 0444; table[NF_SYSCTL_CT_BUCKETS].mode = 0444; + table[NF_SYSCTL_CT_GC_SCAN_INTERVAL_MAX].mode = 0444; } cnet->sysctl_header = register_net_sysctl_sz(net, "net/netfilter", -- 2.50.1 (Apple Git-155)