diff mbox series

[ovs-dev,v2,1/1] net: openvswitch: reduce cpu_used_mask memory

Message ID OS3P286MB22954422E3DD09FF5FD6B091F5D19@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM
State Changes Requested
Headers show
Series [ovs-dev,v2,1/1] net: openvswitch: reduce cpu_used_mask memory | expand

Checks

Context Check Description
ovsrobot/intel-ovs-compilation fail test: fail

Commit Message

缘 陶 Feb. 1, 2023, 1:24 p.m. UTC 
From: Eddy Tao <taoyuan_eddy@hotmail.com>

'struct cpumask cpu_used_mask' is embedded in struct sw_flow.
However, its size is hardcoded to CONFIG_NR_CPUS bits, which can be
8192 by default, it costs memory and slows down ovs_flow_alloc.
This fix uses actual CPU number instead

Signed-off-by: Eddy Tao <taoyuan_eddy@hotmail.com>
---
 net/openvswitch/flow.c       |  6 +++---
 net/openvswitch/flow.h       |  2 +-
 net/openvswitch/flow_table.c | 24 +++++++++++++++++++++---
 3 files changed, 25 insertions(+), 7 deletions(-)

Comments

Jiri Pirko Feb. 1, 2023, 1:44 p.m. UTC | #1 
Wed, Feb 01, 2023 at 02:24:39PM CET, taoyuan_eddy@hotmail.com wrote:
>From: Eddy Tao <taoyuan_eddy@hotmail.com>
>
>'struct cpumask cpu_used_mask' is embedded in struct sw_flow.
>However, its size is hardcoded to CONFIG_NR_CPUS bits, which can be
>8192 by default, it costs memory and slows down ovs_flow_alloc.
>This fix uses actual CPU number instead
>
>Signed-off-by: Eddy Tao <taoyuan_eddy@hotmail.com>

Eddy, looks like you missed my second comment to v1. Could you please
check again?

Thanks!
缘 陶 Feb. 1, 2023, 3:02 p.m. UTC | #2 
Hi, Jiri:

      
    I looked into v2 content, both "From" field and "Signed-off-by" field are 'Eddy Tao' now, in the CC list, 'Eddy Tao' was also
placed automatically/correctly

>>Hmm, I guess that the name should be rather "Dddy Taoyuan" ? Please fix, ==> this is point 1 I guess and it has been fixed in v2
>>also in your "From:" header and preferably email client. ===> this is point 2 ==> i think "git config --global user.name="Eddy Tao" also worked for this point

More about 'email client', smtp-mail.outlook.com is the smtp server and git send-email directs the patch file to to the recipients.
I did not have further email client settings regarding to name spelling.

Could you clarify more about the 'email client' part?

Thanks
eddy
缘 陶 Feb. 2, 2023, 5:09 a.m. UTC | #3 
Hi, Jiri:

I guest you are pointing to the field "From: taoyuan_eddy@hotmail.com" in the patch header linked from "Headers show" section in the patch page


https://patchwork.kernel.org/project/netdevbpf/patch/OS3P286MB22954422E3DD09FF5FD6B091F5D19@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM/

I will fix that accordingly.

Thanks for your time

eddy
Jakub Kicinski Feb. 2, 2023, 5:35 a.m. UTC | #4 
On Thu, 2 Feb 2023 05:09:51 +0000 陶 缘 wrote:
> I guest you are pointing to the field "From: taoyuan_eddy@hotmail.com" in the patch header linked from "Headers show" section in the patch page
> 
> 
> https://patchwork.kernel.org/project/netdevbpf/patch/OS3P286MB22954422E3DD09FF5FD6B091F5D19@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM/
> 
> I will fix that accordingly.

The From is correct, please look at the entire email Jiri also
commented about the code.

Two more notes:
 - don't top post on the list
 - reply in plain text not HTML
Jakub Kicinski Feb. 2, 2023, 5:36 a.m. UTC | #5 
On Wed, 1 Feb 2023 21:35:15 -0800 Jakub Kicinski wrote:
> On Thu, 2 Feb 2023 05:09:51 +0000 陶 缘 wrote:
> > I guest you are pointing to the field "From: taoyuan_eddy@hotmail.com" in the patch header linked from "Headers show" section in the patch page
> > 
> > 
> > https://patchwork.kernel.org/project/netdevbpf/patch/OS3P286MB22954422E3DD09FF5FD6B091F5D19@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM/
> > 
> > I will fix that accordingly.  
> 
> The From is correct, please look at the entire email Jiri also
> commented about the code.
> 
> Two more notes:
>  - don't top post on the list
>  - reply in plain text not HTML

One more thing, please make sure you read the process information 
for Linux networking:

https://www.kernel.org/doc/html/next/process/maintainer-netdev.html
缘 陶 Feb. 2, 2023, 6:44 a.m. UTC | #6 
Thank you Jakub, for your reminder. i will take care of the comment in the code as well in the next submission

eddy
diff mbox series

Patch

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index e20d1a973417..06345cd8c777 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -107,7 +107,7 @@  void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 
 					rcu_assign_pointer(flow->stats[cpu],
 							   new_stats);
-					cpumask_set_cpu(cpu, &flow->cpu_used_mask);
+					cpumask_set_cpu(cpu, flow->cpu_used_mask);
 					goto unlock;
 				}
 			}
@@ -135,7 +135,7 @@  void ovs_flow_stats_get(const struct sw_flow *flow,
 	memset(ovs_stats, 0, sizeof(*ovs_stats));
 
 	/* We open code this to make sure cpu 0 is always considered */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
+	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, flow->cpu_used_mask)) {
 		struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
 
 		if (stats) {
@@ -159,7 +159,7 @@  void ovs_flow_stats_clear(struct sw_flow *flow)
 	int cpu;
 
 	/* We open code this to make sure cpu 0 is always considered */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
+	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, flow->cpu_used_mask)) {
 		struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
 
 		if (stats) {
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 073ab73ffeaa..b5711aff6e76 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -229,7 +229,7 @@  struct sw_flow {
 					 */
 	struct sw_flow_key key;
 	struct sw_flow_id id;
-	struct cpumask cpu_used_mask;
+	struct cpumask *cpu_used_mask;
 	struct sw_flow_mask *mask;
 	struct sw_flow_actions __rcu *sf_acts;
 	struct sw_flow_stats __rcu *stats[]; /* One for each CPU.  First one
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 0a0e4c283f02..63c95c9a814d 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -87,11 +87,12 @@  struct sw_flow *ovs_flow_alloc(void)
 	if (!stats)
 		goto err;
 
+	flow->cpu_used_mask = (struct cpumask *)&flow->stats[nr_cpu_ids];
 	spin_lock_init(&stats->lock);
 
 	RCU_INIT_POINTER(flow->stats[0], stats);
 
-	cpumask_set_cpu(0, &flow->cpu_used_mask);
+	cpumask_set_cpu(0, flow->cpu_used_mask);
 
 	return flow;
 err:
@@ -115,7 +116,7 @@  static void flow_free(struct sw_flow *flow)
 					  flow->sf_acts);
 	/* We open code this to make sure cpu 0 is always considered */
 	for (cpu = 0; cpu < nr_cpu_ids;
-	     cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
+	     cpu = cpumask_next(cpu, flow->cpu_used_mask)) {
 		if (flow->stats[cpu])
 			kmem_cache_free(flow_stats_cache,
 					(struct sw_flow_stats __force *)flow->stats[cpu]);
@@ -1194,9 +1195,26 @@  int ovs_flow_init(void)
 	BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long));
 	BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));
 
+	/* Simply embedding 'struct cpumask' in 'struct sw_flow'
+	 * consumes memory unnecessarily large. Cpumask is an bitmap
+	 * of CONFIG_NR_CPUS bits, which is hardcoded in .config
+	 * and default value can be 8192, in this case is 1024 bytes.
+	 * It drops ovs_flow_alloc performance and cost memory.
+	 * We should use actual CPU count instead of hardcoded value.
+	 *
+	 * To address this, 'cpu_used_mask' is redefined to pointer
+	 * and append a cpumask_size() after 'stat' to hold the memory
+	 * for struct cpumask.
+	 *
+	 * cpumask APIs like cpumask_next and cpumask_set_cpu are defined
+	 * to never access bits beyond cpu count, as such above change is
+	 * safe even though the actual memory provided is smaller than
+	 * sizeof(struct cpumask)
+	 */
 	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
 				       + (nr_cpu_ids
-					  * sizeof(struct sw_flow_stats *)),
+					  * sizeof(struct sw_flow_stats *))
+				       + cpumask_size(),
 				       0, 0, NULL);
 	if (flow_cache == NULL)
 		return -ENOMEM;