* [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory
@ 2023-02-02 10:32 Eddy Tao
2023-02-02 11:05 ` [ovs-dev] " Eelco Chaudron
0 siblings, 1 reply; 4+ messages in thread
From: Eddy Tao @ 2023-02-02 10:32 UTC (permalink / raw)
To: netdev
Cc: Eddy Tao, Pravin B Shelar, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, dev, linux-kernel
Use actual CPU number instead of hardcoded value to decide the size
of 'cpu_used_mask' in 'struct sw_flow'. Below is the reason.
'struct cpumask cpu_used_mask' is embedded in struct sw_flow.
Its size is hardcoded to CONFIG_NR_CPUS bits, which can be
8192 by default, it costs memory and slows down ovs_flow_alloc
as well as the iteration of bits in cpu_used_mask when handling
netlink message from ofproto
To address this, redefine cpu_used_mask to pointer
append cpumask_size() bytes after 'stat' to hold cpumask
cpumask APIs like cpumask_next and cpumask_set_cpu never access
bits beyond cpu count, cpumask_size() bytes of memory is enough
Signed-off-by: Eddy Tao <taoyuan_eddy@hotmail.com>
---
net/openvswitch/flow.c | 8 +++++---
net/openvswitch/flow.h | 2 +-
net/openvswitch/flow_table.c | 8 +++++---
3 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index e20d1a973417..0109a5f86f6a 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 +135,8 @@ 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 +160,8 @@ 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..dc6a174c3194 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]);
@@ -1196,7 +1197,8 @@ int ovs_flow_init(void)
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;
--
2.27.0
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [ovs-dev] [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory
2023-02-02 10:32 [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory Eddy Tao
@ 2023-02-02 11:05 ` Eelco Chaudron
[not found] ` <OS3P286MB22951B162C8A486E39F250BFF5D69@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM>
0 siblings, 1 reply; 4+ messages in thread
From: Eelco Chaudron @ 2023-02-02 11:05 UTC (permalink / raw)
To: Eddy Tao
Cc: netdev, dev, linux-kernel, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, David S. Miller
On 2 Feb 2023, at 11:32, Eddy Tao wrote:
> Use actual CPU number instead of hardcoded value to decide the size
> of 'cpu_used_mask' in 'struct sw_flow'. Below is the reason.
>
> 'struct cpumask cpu_used_mask' is embedded in struct sw_flow.
> Its size is hardcoded to CONFIG_NR_CPUS bits, which can be
> 8192 by default, it costs memory and slows down ovs_flow_alloc
> as well as the iteration of bits in cpu_used_mask when handling
> netlink message from ofproto
I’m trying to understand how this will decrease memory usage. The size of the flow_cache stayed the same (actually it’s large due to the extra pointer).
Also do not understand why the iteration is less, as the mask is initialized the same.
Cheers,
Eelco
> To address this, redefine cpu_used_mask to pointer
> append cpumask_size() bytes after 'stat' to hold cpumask
>
> cpumask APIs like cpumask_next and cpumask_set_cpu never access
> bits beyond cpu count, cpumask_size() bytes of memory is enough
>
> Signed-off-by: Eddy Tao <taoyuan_eddy@hotmail.com>
> ---
> net/openvswitch/flow.c | 8 +++++---
> net/openvswitch/flow.h | 2 +-
> net/openvswitch/flow_table.c | 8 +++++---
> 3 files changed, 11 insertions(+), 7 deletions(-)
>
> diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
> index e20d1a973417..0109a5f86f6a 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 +135,8 @@ 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 +160,8 @@ 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..dc6a174c3194 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]);
> @@ -1196,7 +1197,8 @@ int ovs_flow_init(void)
>
> 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;
> --
> 2.27.0
>
> _______________________________________________
> dev mailing list
> dev@openvswitch.org
> https://mail.openvswitch.org/mailman/listinfo/ovs-dev
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [ovs-dev] [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory
[not found] ` <OS3P286MB22951B162C8A486E39F250BFF5D69@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM>
@ 2023-02-02 11:44 ` Eelco Chaudron
[not found] ` <OS3P286MB2295485449967D11E7A86A0DF5D69@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM>
0 siblings, 1 reply; 4+ messages in thread
From: Eelco Chaudron @ 2023-02-02 11:44 UTC (permalink / raw)
To: 陶 缘
Cc: netdev, dev, linux-kernel, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, David S. Miller
On 2 Feb 2023, at 12:26, 陶 缘 wrote:
> Hi, Eelco:
>
> Thanks for your time going through the detail.
> The thing is: sizeof(struct cpumask), with default CONFIG_NR_CPUS 8192, has a size of 1024 bytes even on a system with only 4 cpus.
> While in practice the cpumask APIs like cpumask_next and cpumask_set_cpu never access more than cpumask_size() of bytes in the bitmap
> My change used cpumask_size() (in above example, consume 8 bytes after alignement for the cpumask, it saved 1016 bytes for every flow.
I looked at the wrong nr_cpumask_bits definition, so thanks for this education :)
> Your question reminded me to revisit the description "as well as the iteration of bits in cpu_used_mask", after a second think, this statement is not valid and should be removed.
> since the iteration API will not access the number of bytes decided by nr_cpu_ids(running CPUs)
>
> I will remove this statement after solving a final style issue in the next submission.
Thanks!
> Thanks
> eddy
> ________________________________
> 发件人: Eelco Chaudron <echaudro@redhat.com>
> 发送时间: 2023年2月2日 11:05
> 收件人: Eddy Tao <taoyuan_eddy@hotmail.com>
> 抄送: netdev@vger.kernel.org <netdev@vger.kernel.org>; dev@openvswitch.org <dev@openvswitch.org>; linux-kernel@vger.kernel.org <linux-kernel@vger.kernel.org>; Eric Dumazet <edumazet@google.com>; Jakub Kicinski <kuba@kernel.org>; Paolo Abeni <pabeni@redhat.com>; David S. Miller <davem@davemloft.net>
> 主题: Re: [ovs-dev] [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory
>
>
>
> On 2 Feb 2023, at 11:32, Eddy Tao wrote:
>
>> Use actual CPU number instead of hardcoded value to decide the size
>> of 'cpu_used_mask' in 'struct sw_flow'. Below is the reason.
>>
>> 'struct cpumask cpu_used_mask' is embedded in struct sw_flow.
>> Its size is hardcoded to CONFIG_NR_CPUS bits, which can be
>> 8192 by default, it costs memory and slows down ovs_flow_alloc
>> as well as the iteration of bits in cpu_used_mask when handling
>> netlink message from ofproto
>
> I’m trying to understand how this will decrease memory usage. The size of the flow_cache stayed the same (actually it’s large due to the extra pointer).
>
> Also do not understand why the iteration is less, as the mask is initialized the same.
>
> Cheers,
>
> Eelco
>
>> To address this, redefine cpu_used_mask to pointer
>> append cpumask_size() bytes after 'stat' to hold cpumask
>>
>> cpumask APIs like cpumask_next and cpumask_set_cpu never access
>> bits beyond cpu count, cpumask_size() bytes of memory is enough
>>
>> Signed-off-by: Eddy Tao <taoyuan_eddy@hotmail.com>
>> ---
>> net/openvswitch/flow.c | 8 +++++---
>> net/openvswitch/flow.h | 2 +-
>> net/openvswitch/flow_table.c | 8 +++++---
>> 3 files changed, 11 insertions(+), 7 deletions(-)
>>
>> diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
>> index e20d1a973417..0109a5f86f6a 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 +135,8 @@ 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 +160,8 @@ 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..dc6a174c3194 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]);
>> @@ -1196,7 +1197,8 @@ int ovs_flow_init(void)
>>
>> 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;
>> --
>> 2.27.0
>>
>> _______________________________________________
>> dev mailing list
>> dev@openvswitch.org
>> https://mail.openvswitch.org/mailman/listinfo/ovs-dev
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [ovs-dev] [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory
[not found] ` <OS3P286MB2295485449967D11E7A86A0DF5D69@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM>
@ 2023-02-02 13:33 ` Eelco Chaudron
0 siblings, 0 replies; 4+ messages in thread
From: Eelco Chaudron @ 2023-02-02 13:33 UTC (permalink / raw)
To: 陶 缘
Cc: netdev, dev, linux-kernel, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, David S. Miller
On 2 Feb 2023, at 13:40, 陶 缘 wrote:
> Hi, Eelco:
>
> I have a query regarding to the style check.
> Though the './scripts/checkpatch.pl' emit no warning/error, the 'netdev/checkpatch' still has one warning "WARNING: line length of 82 exceeds 80 columns"
> I went through the patch line by line and could not find any changed line exceeding the 80 character limit.
>
> I am afraid that the netdev/checkpatch takes counts on the removed line(old removed line has length exceeding 80 and i have revised that in the patch already
>
> Is there any known issue regarding to the netdev/checkpatch?
Not sure which netdev/checkpatch you are referring to. I always you the general kernel one in /script/checkpatch.pl.
Your patch looks good to me with /script/checkpatch.pl --strict.
> Best regards
>
> eddy
>
> ________________________________
> 发件人: Eelco Chaudron <echaudro@redhat.com>
> 发送时间: 2023年2月2日 11:44
> 收件人: 陶 缘 <taoyuan_eddy@hotmail.com>
> 抄送: netdev@vger.kernel.org <netdev@vger.kernel.org>; dev@openvswitch.org <dev@openvswitch.org>; linux-kernel@vger.kernel.org <linux-kernel@vger.kernel.org>; Eric Dumazet <edumazet@google.com>; Jakub Kicinski <kuba@kernel.org>; Paolo Abeni <pabeni@redhat.com>; David S. Miller <davem@davemloft.net>
> 主题: Re: [ovs-dev] [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory
>
>
>
> On 2 Feb 2023, at 12:26, 陶 缘 wrote:
>
>> Hi, Eelco:
>>
>> Thanks for your time going through the detail.
>> The thing is: sizeof(struct cpumask), with default CONFIG_NR_CPUS 8192, has a size of 1024 bytes even on a system with only 4 cpus.
>> While in practice the cpumask APIs like cpumask_next and cpumask_set_cpu never access more than cpumask_size() of bytes in the bitmap
>> My change used cpumask_size() (in above example, consume 8 bytes after alignement for the cpumask, it saved 1016 bytes for every flow.
>
> I looked at the wrong nr_cpumask_bits definition, so thanks for this education :)
>
>> Your question reminded me to revisit the description "as well as the iteration of bits in cpu_used_mask", after a second think, this statement is not valid and should be removed.
>> since the iteration API will not access the number of bytes decided by nr_cpu_ids(running CPUs)
>>
>> I will remove this statement after solving a final style issue in the next submission.
>
> Thanks!
>
>
>> Thanks
>> eddy
>> ________________________________
>> 发件人: Eelco Chaudron <echaudro@redhat.com>
>> 发送时间: 2023年2月2日 11:05
>> 收件人: Eddy Tao <taoyuan_eddy@hotmail.com>
>> 抄送: netdev@vger.kernel.org <netdev@vger.kernel.org>; dev@openvswitch.org <dev@openvswitch.org>; linux-kernel@vger.kernel.org <linux-kernel@vger.kernel.org>; Eric Dumazet <edumazet@google.com>; Jakub Kicinski <kuba@kernel.org>; Paolo Abeni <pabeni@redhat.com>; David S. Miller <davem@davemloft.net>
>> 主题: Re: [ovs-dev] [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory
>>
>>
>>
>> On 2 Feb 2023, at 11:32, Eddy Tao wrote:
>>
>>> Use actual CPU number instead of hardcoded value to decide the size
>>> of 'cpu_used_mask' in 'struct sw_flow'. Below is the reason.
>>>
>>> 'struct cpumask cpu_used_mask' is embedded in struct sw_flow.
>>> Its size is hardcoded to CONFIG_NR_CPUS bits, which can be
>>> 8192 by default, it costs memory and slows down ovs_flow_alloc
>>> as well as the iteration of bits in cpu_used_mask when handling
>>> netlink message from ofproto
>>
>> I’m trying to understand how this will decrease memory usage. The size of the flow_cache stayed the same (actually it’s large due to the extra pointer).
>>
>> Also do not understand why the iteration is less, as the mask is initialized the same.
>>
>> Cheers,
>>
>> Eelco
>>
>>> To address this, redefine cpu_used_mask to pointer
>>> append cpumask_size() bytes after 'stat' to hold cpumask
>>>
>>> cpumask APIs like cpumask_next and cpumask_set_cpu never access
>>> bits beyond cpu count, cpumask_size() bytes of memory is enough
>>>
>>> Signed-off-by: Eddy Tao <taoyuan_eddy@hotmail.com>
>>> ---
>>> net/openvswitch/flow.c | 8 +++++---
>>> net/openvswitch/flow.h | 2 +-
>>> net/openvswitch/flow_table.c | 8 +++++---
>>> 3 files changed, 11 insertions(+), 7 deletions(-)
>>>
>>> diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
>>> index e20d1a973417..0109a5f86f6a 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 +135,8 @@ 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 +160,8 @@ 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..dc6a174c3194 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]);
>>> @@ -1196,7 +1197,8 @@ int ovs_flow_init(void)
>>>
>>> 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;
>>> --
>>> 2.27.0
>>>
>>> _______________________________________________
>>> dev mailing list
>>> dev@openvswitch.org
>>> https://mail.openvswitch.org/mailman/listinfo/ovs-dev
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2023-02-02 13:33 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-02-02 10:32 [PATCH net-next v3 1/1] net:openvswitch:reduce cpu_used_mask memory Eddy Tao
2023-02-02 11:05 ` [ovs-dev] " Eelco Chaudron
[not found] ` <OS3P286MB22951B162C8A486E39F250BFF5D69@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM>
2023-02-02 11:44 ` Eelco Chaudron
[not found] ` <OS3P286MB2295485449967D11E7A86A0DF5D69@OS3P286MB2295.JPNP286.PROD.OUTLOOK.COM>
2023-02-02 13:33 ` Eelco Chaudron
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.