From: kan.liang@intel.com
To: davem@davemloft.net, linux-kernel@vger.kernel.org,
netdev@vger.kernel.org
Cc: jeffrey.t.kirsher@intel.com, mingo@redhat.com,
peterz@infradead.org, kuznet@ms2.inr.ac.ru, jmorris@namei.org,
yoshfuji@linux-ipv6.org, kaber@trash.net,
akpm@linux-foundation.org, keescook@chromium.org,
viro@zeniv.linux.org.uk, gorcunov@openvz.org,
john.stultz@linaro.org, aduyck@mirantis.com, ben@decadent.org.uk,
decot@googlers.com, fw@strlen.de, alexander.duyck@gmail.com,
daniel@iogearbox.net, tom@herbertland.com, rdunlap@infradead.org,
xiyou.wangcong@gmail.com, hannes@stressinduktion.org,
stephen@networkplumber.org, alexei.starovoitov@gmail.com,
jesse.brandeburg@intel.com, andi@firstfloor.org,
Kan Liang <kan.liang@intel.com>
Subject: [RFC V3 PATCH 11/26] net/netpolicy: add MIX policy
Date: Mon, 12 Sep 2016 07:55:44 -0700 [thread overview]
Message-ID: <1473692159-4017-12-git-send-email-kan.liang@intel.com> (raw)
In-Reply-To: <1473692159-4017-1-git-send-email-kan.liang@intel.com>
From: Kan Liang <kan.liang@intel.com>
MIX policy is combine of other policies. It allows different queue has
different policy. If MIX policy is applied,
/proc/net/netpolicy/$DEV/policy shows per queue policy.
Usually, the workloads requires either high throughput or low latency.
So for current implementation, MIX policy is combine of LATENCY policy
and BULK policy.
The workloads which requires high throughput are usually utilize more
CPU resources compared to the workloads which requires low latency. This
means that if there is an equal interest in latency and throughput
performance, it is better to reserve more BULK queues than LATENCY
queues. In this patch, MIX policy is forced to include 1/3 LATENCY
policy queues and 2/3 BULK policy queues.
Signed-off-by: Kan Liang <kan.liang@intel.com>
---
include/linux/netpolicy.h | 7 +++
net/core/netpolicy.c | 139 ++++++++++++++++++++++++++++++++++++++++++----
2 files changed, 136 insertions(+), 10 deletions(-)
diff --git a/include/linux/netpolicy.h b/include/linux/netpolicy.h
index 951227b..f60331d 100644
--- a/include/linux/netpolicy.h
+++ b/include/linux/netpolicy.h
@@ -22,6 +22,12 @@ enum netpolicy_name {
NET_POLICY_BULK,
NET_POLICY_LATENCY,
NET_POLICY_MAX,
+
+ /*
+ * Mixture of the above policy
+ * Can only be set as global policy.
+ */
+ NET_POLICY_MIX,
};
enum netpolicy_traffic {
@@ -67,6 +73,7 @@ struct netpolicy_info {
enum netpolicy_name cur_policy;
unsigned long avail_policy[BITS_TO_LONGS(NET_POLICY_MAX)];
bool irq_affinity;
+ bool has_mix_policy;
/* cpu and queue mapping information */
struct netpolicy_sys_info sys_info;
/* List of policy objects 0 rx 1 tx */
diff --git a/net/core/netpolicy.c b/net/core/netpolicy.c
index 1d796a8..f56beca 100644
--- a/net/core/netpolicy.c
+++ b/net/core/netpolicy.c
@@ -283,6 +283,9 @@ static inline int node_distance_cmp(const void *a, const void *b)
return _a->distance - _b->distance;
}
+#define mix_latency_num(num) ((num) / 3)
+#define mix_throughput_num(num) ((num) - mix_latency_num(num))
+
static int _netpolicy_gen_obj_list(struct net_device *dev, bool is_rx,
enum netpolicy_name policy,
struct sort_node *nodes, int num_node,
@@ -290,7 +293,9 @@ static int _netpolicy_gen_obj_list(struct net_device *dev, bool is_rx,
{
cpumask_var_t node_tmp_cpumask, sibling_tmp_cpumask;
struct cpumask *node_assigned_cpumask;
+ int *l_num = NULL, *b_num = NULL;
int i, ret = -ENOMEM;
+ int num_node_cpu;
u32 cpu;
if (!alloc_cpumask_var(&node_tmp_cpumask, GFP_ATOMIC))
@@ -302,6 +307,23 @@ static int _netpolicy_gen_obj_list(struct net_device *dev, bool is_rx,
if (!node_assigned_cpumask)
goto alloc_fail2;
+ if (policy == NET_POLICY_MIX) {
+ l_num = kcalloc(num_node, sizeof(int), GFP_ATOMIC);
+ if (!l_num)
+ goto alloc_fail3;
+ b_num = kcalloc(num_node, sizeof(int), GFP_ATOMIC);
+ if (!b_num) {
+ kfree(l_num);
+ goto alloc_fail3;
+ }
+
+ for (i = 0; i < num_node; i++) {
+ num_node_cpu = cpumask_weight(&node_avail_cpumask[nodes[i].node]);
+ l_num[i] = mix_latency_num(num_node_cpu);
+ b_num[i] = mix_throughput_num(num_node_cpu);
+ }
+ }
+
/* Don't share physical core */
for (i = 0; i < num_node; i++) {
if (cpumask_weight(&node_avail_cpumask[nodes[i].node]) == 0)
@@ -312,7 +334,13 @@ static int _netpolicy_gen_obj_list(struct net_device *dev, bool is_rx,
cpu = cpumask_first(node_tmp_cpumask);
/* push to obj list */
- ret = netpolicy_add_obj(dev, cpu, is_rx, policy);
+ if (policy == NET_POLICY_MIX) {
+ if (l_num[i]-- > 0)
+ ret = netpolicy_add_obj(dev, cpu, is_rx, NET_POLICY_LATENCY);
+ else if (b_num[i]-- > 0)
+ ret = netpolicy_add_obj(dev, cpu, is_rx, NET_POLICY_BULK);
+ } else
+ ret = netpolicy_add_obj(dev, cpu, is_rx, policy);
if (ret) {
spin_unlock(&dev->np_ob_list_lock);
goto err;
@@ -325,6 +353,41 @@ static int _netpolicy_gen_obj_list(struct net_device *dev, bool is_rx,
spin_unlock(&dev->np_ob_list_lock);
}
+ if (policy == NET_POLICY_MIX) {
+ struct netpolicy_object *obj;
+ int dir = is_rx ? 0 : 1;
+ u32 sibling;
+
+ /* if have to share core, choose latency core first. */
+ for (i = 0; i < num_node; i++) {
+ if ((l_num[i] < 1) && (b_num[i] < 1))
+ continue;
+ spin_lock(&dev->np_ob_list_lock);
+ list_for_each_entry(obj, &dev->netpolicy->obj_list[dir][NET_POLICY_LATENCY], list) {
+ if (cpu_to_node(obj->cpu) != nodes[i].node)
+ continue;
+
+ cpu = obj->cpu;
+ for_each_cpu(sibling, topology_sibling_cpumask(cpu)) {
+ if (cpumask_test_cpu(sibling, &node_assigned_cpumask[nodes[i].node]) ||
+ !cpumask_test_cpu(sibling, &node_avail_cpumask[nodes[i].node]))
+ continue;
+
+ if (l_num[i]-- > 0)
+ ret = netpolicy_add_obj(dev, sibling, is_rx, NET_POLICY_LATENCY);
+ else if (b_num[i]-- > 0)
+ ret = netpolicy_add_obj(dev, sibling, is_rx, NET_POLICY_BULK);
+ if (ret) {
+ spin_unlock(&dev->np_ob_list_lock);
+ goto err;
+ }
+ cpumask_set_cpu(sibling, &node_assigned_cpumask[nodes[i].node]);
+ }
+ }
+ spin_unlock(&dev->np_ob_list_lock);
+ }
+ }
+
for (i = 0; i < num_node; i++) {
cpumask_xor(node_tmp_cpumask, &node_avail_cpumask[nodes[i].node], &node_assigned_cpumask[nodes[i].node]);
if (cpumask_weight(node_tmp_cpumask) == 0)
@@ -332,7 +395,15 @@ static int _netpolicy_gen_obj_list(struct net_device *dev, bool is_rx,
spin_lock(&dev->np_ob_list_lock);
for_each_cpu(cpu, node_tmp_cpumask) {
/* push to obj list */
- ret = netpolicy_add_obj(dev, cpu, is_rx, policy);
+ if (policy == NET_POLICY_MIX) {
+ if (l_num[i]-- > 0)
+ ret = netpolicy_add_obj(dev, cpu, is_rx, NET_POLICY_LATENCY);
+ else if (b_num[i]-- > 0)
+ ret = netpolicy_add_obj(dev, cpu, is_rx, NET_POLICY_BULK);
+ else
+ ret = netpolicy_add_obj(dev, cpu, is_rx, NET_POLICY_NONE);
+ } else
+ ret = netpolicy_add_obj(dev, cpu, is_rx, policy);
if (ret) {
spin_unlock(&dev->np_ob_list_lock);
goto err;
@@ -343,6 +414,11 @@ static int _netpolicy_gen_obj_list(struct net_device *dev, bool is_rx,
}
err:
+ if (policy == NET_POLICY_MIX) {
+ kfree(l_num);
+ kfree(b_num);
+ }
+alloc_fail3:
kfree(node_assigned_cpumask);
alloc_fail2:
free_cpumask_var(sibling_tmp_cpumask);
@@ -381,6 +457,22 @@ static int netpolicy_gen_obj_list(struct net_device *dev,
* 2. Remote core + the only logical core
* 3. Local core + the core's sibling is already in the object list
* 4. Remote core + the core's sibling is already in the object list
+ *
+ * For MIX policy, on each node, force 1/3 core as latency policy core,
+ * the rest cores are bulk policy core.
+ *
+ * Besides the above priority rules, there is one more rule
+ * - If it's sibling core's object has been applied a policy
+ * Choose the object which the sibling logical core applies latency policy first
+ *
+ * So the order of object list for MIX policy is as below:
+ * 1. Local core + the only logical core
+ * 2. Remote core + the only logical core
+ * 3. Local core + the core's sibling is latency policy core
+ * 4. Remote core + the core's sibling is latency policy core
+ * 5. Local core + the core's sibling is bulk policy core
+ * 6. Remote core + the core's sibling is bulk policy core
+ *
*/
#ifdef CONFIG_NUMA
dev_node = dev_to_node(dev->dev.parent);
@@ -451,14 +543,23 @@ static int net_policy_set_by_name(char *name, struct net_device *dev)
goto unlock;
}
- for (i = 0; i < NET_POLICY_MAX; i++) {
- if (!strncmp(name, policy_name[i], strlen(policy_name[i])))
- break;
- }
+ if (!strncmp(name, "MIX", strlen("MIX"))) {
+ if (dev->netpolicy->has_mix_policy) {
+ i = NET_POLICY_MIX;
+ } else {
+ ret = -ENOTSUPP;
+ goto unlock;
+ }
+ } else {
+ for (i = 0; i < NET_POLICY_MAX; i++) {
+ if (!strncmp(name, policy_name[i], strlen(policy_name[i])))
+ break;
+ }
- if (!test_bit(i, dev->netpolicy->avail_policy)) {
- ret = -ENOTSUPP;
- goto unlock;
+ if (!test_bit(i, dev->netpolicy->avail_policy)) {
+ ret = -ENOTSUPP;
+ goto unlock;
+ }
}
if (i == dev->netpolicy->cur_policy)
@@ -506,17 +607,35 @@ unlock:
static int net_policy_proc_show(struct seq_file *m, void *v)
{
struct net_device *dev = (struct net_device *)m->private;
+ enum netpolicy_name cur;
+ struct netpolicy_object *obj, *tmp;
int i;
if (WARN_ON(!dev->netpolicy))
return -EINVAL;
- if (dev->netpolicy->cur_policy == NET_POLICY_NONE) {
+ cur = dev->netpolicy->cur_policy;
+ if (cur == NET_POLICY_NONE) {
seq_printf(m, "%s: There is no policy applied\n", dev->name);
seq_printf(m, "%s: The available policy include:", dev->name);
for_each_set_bit(i, dev->netpolicy->avail_policy, NET_POLICY_MAX)
seq_printf(m, " %s", policy_name[i]);
+ if (dev->netpolicy->has_mix_policy)
+ seq_printf(m, " MIX");
seq_printf(m, "\n");
+ } else if (cur == NET_POLICY_MIX) {
+ seq_printf(m, "%s: MIX policy is running on the system\n", dev->name);
+ spin_lock(&dev->np_ob_list_lock);
+ for (i = NET_POLICY_NONE; i < NET_POLICY_MAX; i++) {
+ seq_printf(m, "%s: queues for %s policy\n", dev->name, policy_name[i]);
+ list_for_each_entry_safe(obj, tmp, &dev->netpolicy->obj_list[NETPOLICY_RX][i], list) {
+ seq_printf(m, "%s: rx queue %d\n", dev->name, obj->queue);
+ }
+ list_for_each_entry_safe(obj, tmp, &dev->netpolicy->obj_list[NETPOLICY_TX][i], list) {
+ seq_printf(m, "%s: tx queue %d\n", dev->name, obj->queue);
+ }
+ }
+ spin_unlock(&dev->np_ob_list_lock);
} else {
seq_printf(m, "%s: POLICY %s is running on the system\n",
dev->name, policy_name[dev->netpolicy->cur_policy]);
--
2.5.5
next prev parent reply other threads:[~2016-09-12 14:55 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-12 14:55 [RFC V3 PATCH 00/26] Kernel NET policy kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 01/26] net: introduce " kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 02/26] net/netpolicy: init " kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 03/26] net/netpolicy: get device queue irq information kan.liang
2016-09-12 16:48 ` Sergei Shtylyov
2016-09-13 12:23 ` Liang, Kan
2016-09-13 13:14 ` Alexander Duyck
2016-09-13 13:22 ` Liang, Kan
2016-09-12 14:55 ` [RFC V3 PATCH 04/26] net/netpolicy: get CPU information kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 05/26] net/netpolicy: create CPU and queue mapping kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 06/26] net/netpolicy: set and remove IRQ affinity kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 07/26] net/netpolicy: enable and disable NET policy kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 08/26] net/netpolicy: introduce NET policy object kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 09/26] net/netpolicy: set NET policy by policy name kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 10/26] net/netpolicy: add three new NET policies kan.liang
2016-09-12 14:55 ` kan.liang [this message]
2016-09-12 14:55 ` [RFC V3 PATCH 12/26] net/netpolicy: NET device hotplug kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 13/26] net/netpolicy: support CPU hotplug kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 14/26] net/netpolicy: handle channel changes kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 15/26] net/netpolicy: implement netpolicy register kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 16/26] net/netpolicy: introduce per socket netpolicy kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 17/26] net/netpolicy: introduce netpolicy_pick_queue kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 18/26] net/netpolicy: set tx queues according to policy kan.liang
2016-09-12 20:23 ` Tom Herbert
2016-09-13 12:22 ` Liang, Kan
2016-09-12 14:55 ` [RFC V3 PATCH 19/26] net/netpolicy: tc bpf extension to pick Tx queue kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 20/26] net/netpolicy: set Rx queues according to policy kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 21/26] net/netpolicy: introduce per task net policy kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 22/26] net/netpolicy: set per task policy by proc kan.liang
2016-09-12 17:01 ` Sergei Shtylyov
2016-09-12 14:55 ` [RFC V3 PATCH 23/26] net/netpolicy: fast path for finding the queues kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 24/26] net/netpolicy: optimize for queue pair kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 25/26] net/netpolicy: limit the total record number kan.liang
2016-09-12 14:55 ` [RFC V3 PATCH 26/26] Documentation/networking: Document NET policy kan.liang
2016-09-12 15:38 ` [RFC V3 PATCH 00/26] Kernel " Florian Westphal
2016-09-12 17:21 ` Cong Wang
2016-09-12 15:52 ` Eric Dumazet
2016-09-19 20:39 ` Stephen Hemminger
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1473692159-4017-12-git-send-email-kan.liang@intel.com \
--to=kan.liang@intel.com \
--cc=aduyck@mirantis.com \
--cc=akpm@linux-foundation.org \
--cc=alexander.duyck@gmail.com \
--cc=alexei.starovoitov@gmail.com \
--cc=andi@firstfloor.org \
--cc=ben@decadent.org.uk \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=decot@googlers.com \
--cc=fw@strlen.de \
--cc=gorcunov@openvz.org \
--cc=hannes@stressinduktion.org \
--cc=jeffrey.t.kirsher@intel.com \
--cc=jesse.brandeburg@intel.com \
--cc=jmorris@namei.org \
--cc=john.stultz@linaro.org \
--cc=kaber@trash.net \
--cc=keescook@chromium.org \
--cc=kuznet@ms2.inr.ac.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rdunlap@infradead.org \
--cc=stephen@networkplumber.org \
--cc=tom@herbertland.com \
--cc=viro@zeniv.linux.org.uk \
--cc=xiyou.wangcong@gmail.com \
--cc=yoshfuji@linux-ipv6.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).