[202412] [FRR] Add support for 514 BGP sessions

src/sonic-frr/patch/0044-zebra-Modify-dplane-loop-to-allow-backpressure-to-fi.patch

@@ -1,8 +1,7 @@
-From 4671ddf4920553b663fda129f7c4366839347645 Mon Sep 17 00:00:00 2001
+From e6e096f2507e76c375ba9d6b20c05af0b61ce2cd Mon Sep 17 00:00:00 2001
 From: Donald Sharp <[email protected]>
 Date: Wed, 12 Jun 2024 14:14:48 -0400
-Subject: [PATCH 3/5] zebra: Modify dplane loop to allow backpressure to filter
- up
+Subject: [PATCH] zebra: Modify dplane loop to allow backpressure to filter up
 
 Currently when the dplane_thread_loop is run, it moves contexts
 from the dg_update_list and puts the contexts on the input queue
@@ -30,11 +29,12 @@ context system and memory will not go out of control.
 
 Signed-off-by: Donald Sharp <[email protected]>
 
+
 diff --git a/zebra/zebra_dplane.c b/zebra/zebra_dplane.c
-index c52e032660..f0e1ff6f27 100644
+index 44ee41d8c..0460463bc 100644
 --- a/zebra/zebra_dplane.c
 +++ b/zebra/zebra_dplane.c
-@@ -7155,10 +7155,10 @@ static void dplane_thread_loop(struct thread *event)
+@@ -7279,10 +7279,10 @@ static void dplane_thread_loop(struct event *event)
  {
  	struct dplane_ctx_list_head work_list;
  	struct dplane_ctx_list_head error_list;
@@ -47,7 +47,7 @@ index c52e032660..f0e1ff6f27 100644
  	bool reschedule = false;
 
  	/* Capture work limit per cycle */
-@@ -7182,18 +7182,48 @@ static void dplane_thread_loop(struct thread *event)
+@@ -7306,18 +7306,48 @@ static void dplane_thread_loop(struct event *event)
  	/* Locate initial registered provider */
  	prov = dplane_prov_list_first(&zdplane_info.dg_providers);
 
@@ -104,7 +104,7 @@ index c52e032660..f0e1ff6f27 100644
  	DPLANE_UNLOCK();
 
  	atomic_fetch_sub_explicit(&zdplane_info.dg_routes_queued, counter,
-@@ -7212,8 +7242,9 @@ static void dplane_thread_loop(struct thread *event)
+@@ -7336,8 +7366,9 @@ static void dplane_thread_loop(struct event *event)
  		 * items.
  		 */
  		if (IS_ZEBRA_DEBUG_DPLANE_DETAIL)
@@ -116,7 +116,7 @@ index c52e032660..f0e1ff6f27 100644
 
  		/* Capture current provider id in each context; check for
  		 * error status.
-@@ -7271,18 +7302,61 @@ static void dplane_thread_loop(struct thread *event)
+@@ -7395,18 +7426,61 @@ static void dplane_thread_loop(struct event *event)
  		if (!zdplane_info.dg_run)
  			break;
 
@@ -185,8 +185,8 @@ index c52e032660..f0e1ff6f27 100644
  		dplane_provider_unlock(prov);
 
  		if (counter >= limit)
-@@ -7293,7 +7367,7 @@ static void dplane_thread_loop(struct thread *event)
- 				   counter, dplane_provider_get_name(prov));
+@@ -7422,7 +7496,7 @@ static void dplane_thread_loop(struct event *event)
+ 		}
 
  		/* Locate next provider */
 -		prov = dplane_prov_list_next(&zdplane_info.dg_providers, prov);

src/sonic-frr/patch/0044-zebra-Prevent-starvation-in-dplane_thread_loop.patch

@@ -0,0 +1,49 @@
+From 6faad863f30d29157e4c675ad956e3ccd38991a7 Mon Sep 17 00:00:00 2001
+From: Donald Sharp <[email protected]>
+Date: Fri, 14 Jun 2024 13:36:51 -0400
+Subject: [PATCH] zebra: Prevent starvation in dplane_thread_loop
+
+When removing a large number of routes, the linux kernel can take the
+cpu for an extended amount of time, leaving a situation where FRR
+detects a starvation event.
+
+r1# sharp install routes 10.0.0.0 nexthop 192.168.44.33 1000000 repeat 10
+2024-06-14 12:55:49.365 [NTFY] sharpd: [M7Q4P-46WDR] vty[5]@# sharp install routes 10.0.0.0 nexthop 192.168.44.33 1000000 repeat 10
+2024-06-14 12:55:49.365 [DEBG] sharpd: [YP4TQ-01TYK] Inserting 1000000 routes
+2024-06-14 12:55:57.256 [DEBG] sharpd: [TPHKD-3NYSB] Installed All Items 7.890085
+2024-06-14 12:55:57.256 [DEBG] sharpd: [YJ486-NX5R1] Removing 1000000 routes
+2024-06-14 12:56:07.802 [WARN] zebra: [QH9AB-Y4XMZ][EC 100663314] STARVATION: task dplane_thread_loop (634377bc8f9e) ran for 7078ms (cpu time 220ms)
+2024-06-14 12:56:25.039 [DEBG] sharpd: [WTN53-GK9Y5] Removed all Items 27.783668
+2024-06-14 12:56:25.039 [DEBG] sharpd: [YP4TQ-01TYK] Inserting 1000000 routes
+2024-06-14 12:56:32.783 [DEBG] sharpd: [TPHKD-3NYSB] Installed All Items 7.743524
+2024-06-14 12:56:32.783 [DEBG] sharpd: [YJ486-NX5R1] Removing 1000000 routes
+2024-06-14 12:56:41.447 [WARN] zebra: [QH9AB-Y4XMZ][EC 100663314] STARVATION: task dplane_thread_loop (634377bc8f9e) ran for 5175ms (cpu time 179ms)
+
+Let's modify the loop in dplane_thread_loop such that after a provider
+has been run, check to see if the event should yield, if so, stop
+and reschedule this for the future.
+
+Signed-off-by: Donald Sharp <[email protected]>
+---
+ zebra/zebra_dplane.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+diff --git a/zebra/zebra_dplane.c b/zebra/zebra_dplane.c
+index 06b34da209..3944876439 100644
+--- a/zebra/zebra_dplane.c
++++ b/zebra/zebra_dplane.c
+@@ -7441,6 +7441,11 @@ static void dplane_thread_loop(struct event *event)
+ 			zlog_debug("dplane dequeues %d completed work from provider %s",
+ 				   counter, dplane_provider_get_name(prov));
+
++		if (event_should_yield(event)) {
++			reschedule = true;
++			break;
++		}
++
+ 		/* Locate next provider */
+ 		prov = dplane_prov_list_next(&zdplane_info.dg_providers, prov);
+ 	}
+-- 
+2.39.5
+

src/sonic-frr/patch/0045-zebra-Limit-queue-depth-in-dplane_fpm_nl.patch

@@ -1,7 +1,7 @@
-From 50f606c158f6c89abd0d3f531905005d3a48a5b6 Mon Sep 17 00:00:00 2001
+From 1712fbd14dddd542e7aa4b468356abdfe42817d4 Mon Sep 17 00:00:00 2001
 From: Donald Sharp <[email protected]>
 Date: Wed, 12 Jun 2024 15:16:08 -0400
-Subject: [PATCH 4/5] zebra: Limit queue depth in dplane_fpm_nl
+Subject: [PATCH] zebra: Limit queue depth in dplane_fpm_nl
 
 The dplane providers have a concept of input queues
 and output queues.  These queues are chained together
@@ -16,12 +16,15 @@ queue when it is already full.  This will allow the backpressure
 to work appropriately in zebra proper.
 
 Signed-off-by: Donald Sharp <[email protected]>
+---
+ zebra/dplane_fpm_nl.c | 19 +++++++++++++++++++
+ 1 file changed, 19 insertions(+)
 
 diff --git a/zebra/dplane_fpm_nl.c b/zebra/dplane_fpm_nl.c
-index bc9815bb10..4fd42f64a2 100644
+index a054d362f..81f1c9417 100644
 --- a/zebra/dplane_fpm_nl.c
 +++ b/zebra/dplane_fpm_nl.c
-@@ -1560,6 +1560,25 @@ static int fpm_nl_process(struct zebra_dplane_provider *prov)
+@@ -1603,6 +1603,25 @@ static int fpm_nl_process(struct zebra_dplane_provider *prov)
 
  	fnc = dplane_provider_get_data(prov);
  	limit = dplane_provider_get_work_limit(prov);
@@ -36,7 +39,7 @@ index bc9815bb10..4fd42f64a2 100644
 +				   ") of internal work, hold off",
 +				   __func__, cur_queue);
 +		limit = 0;
-+	} else {
++	} else if (cur_queue != 0) {
 +		if (IS_ZEBRA_DEBUG_FPM)
 +			zlog_debug("%s: current queue is %" PRIu64
 +				   ", limiting to lesser amount of %" PRIu64,