From: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
virtualization@lists.linux-foundation.org,
linux-s390@vger.kernel.org
Cc: peterz@infradead.org, mingo@redhat.com, mpe@ellerman.id.au,
paulus@samba.org, benh@kernel.crashing.org,
paulmck@linux.vnet.ibm.com, waiman.long@hpe.com,
will.deacon@arm.com, boqun.feng@gmail.com, dave@stgolabs.net,
schwidefsky@de.ibm.com,
Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Subject: [PATCH v2 3/4] locking/osq: Drop the overload of osq_lock()
Date: Tue, 28 Jun 2016 10:43:10 -0400 [thread overview]
Message-ID: <1467124991-13164-4-git-send-email-xinhui.pan@linux.vnet.ibm.com> (raw)
In-Reply-To: <1467124991-13164-1-git-send-email-xinhui.pan@linux.vnet.ibm.com>
An over-committed guest with more vCPUs than pCPUs has a heavy overload in
osq_lock().
This is because vCPU A hold the osq lock and yield out, vCPU B wait per_cpu
node->locked to be set. IOW, vCPU B wait vCPU A to run and unlock the osq
lock.
Kernel has an interface bool vcpu_is_preempted(int cpu) to see if a vCPU is
currently running or not. So break the spin loops on true condition.
test case:
perf record -a perf bench sched messaging -g 400 -p && perf report
before patch:
18.09% sched-messaging [kernel.vmlinux] [k] osq_lock
12.28% sched-messaging [kernel.vmlinux] [k] rwsem_spin_on_owner
5.27% sched-messaging [kernel.vmlinux] [k] mutex_unlock
3.89% sched-messaging [kernel.vmlinux] [k] wait_consider_task
3.64% sched-messaging [kernel.vmlinux] [k] _raw_write_lock_irq
3.41% sched-messaging [kernel.vmlinux] [k] mutex_spin_on_owner.is
2.49% sched-messaging [kernel.vmlinux] [k] system_call
after patch:
20.68% sched-messaging [kernel.vmlinux] [k] mutex_spin_on_owner
8.45% sched-messaging [kernel.vmlinux] [k] mutex_unlock
4.12% sched-messaging [kernel.vmlinux] [k] system_call
3.01% sched-messaging [kernel.vmlinux] [k] system_call_common
2.83% sched-messaging [kernel.vmlinux] [k] copypage_power7
2.64% sched-messaging [kernel.vmlinux] [k] rwsem_spin_on_owner
2.00% sched-messaging [kernel.vmlinux] [k] osq_lock
Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
---
kernel/locking/osq_lock.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 05a3785..39d1385 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -21,6 +21,11 @@ static inline int encode_cpu(int cpu_nr)
return cpu_nr + 1;
}
+static inline int node_cpu(struct optimistic_spin_node *node)
+{
+ return node->cpu - 1;
+}
+
static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
{
int cpu_nr = encoded_cpu_val - 1;
@@ -118,8 +123,11 @@ bool osq_lock(struct optimistic_spin_queue *lock)
while (!READ_ONCE(node->locked)) {
/*
* If we need to reschedule bail... so we can block.
+ * Use vcpu_is_preempted to detech lock holder preemption issue
+ * and break. vcpu_is_preempted is a macro defined by false if
+ * arch does not support vcpu preempted check,
*/
- if (need_resched())
+ if (need_resched() || vcpu_is_preempted(node_cpu(node->prev)))
goto unqueue;
cpu_relax_lowlatency();
--
2.4.11
next prev parent reply other threads:[~2016-06-28 10:44 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-28 14:43 [PATCH v2 0/4] implement vcpu preempted check Pan Xinhui
2016-06-28 14:43 ` [PATCH v2 1/4] kernel/sched: introduce vcpu preempted check interface Pan Xinhui
2016-06-28 14:43 ` [PATCH v2 2/4] powerpc/spinlock: support vcpu preempted check Pan Xinhui
2016-07-05 9:57 ` Wanpeng Li
2016-07-06 4:58 ` xinhui
2016-07-06 6:46 ` Wanpeng Li
2016-07-06 7:58 ` Peter Zijlstra
2016-07-06 8:32 ` Wanpeng Li
2016-07-06 10:18 ` xinhui
2016-07-06 10:54 ` Balbir Singh
2016-07-15 15:35 ` Pan Xinhui
2016-06-28 14:43 ` Pan Xinhui [this message]
2016-06-28 14:43 ` [PATCH v2 4/4] kernel/locking: Drop the overload of {mutex, rwsem}_spin_on_owner Pan Xinhui
2016-07-06 6:52 ` [PATCH v2 0/4] implement vcpu preempted check Peter Zijlstra
2016-07-06 7:47 ` Juergen Gross
2016-07-06 8:19 ` Peter Zijlstra
2016-07-06 8:38 ` Juergen Gross
2016-07-06 12:44 ` Paolo Bonzini
2016-07-06 16:56 ` Christian Borntraeger
2016-07-06 10:05 ` xinhui
2016-07-06 10:44 ` Paolo Bonzini
2016-07-06 11:59 ` Peter Zijlstra
2016-07-06 12:08 ` Wanpeng Li
2016-07-06 12:28 ` Paolo Bonzini
2016-07-06 13:03 ` Wanpeng Li
2016-07-07 8:48 ` Wanpeng Li
2016-07-07 9:42 ` Peter Zijlstra
2016-07-07 10:12 ` Wanpeng Li
2016-07-07 10:27 ` Wanpeng Li
2016-07-07 11:15 ` Peter Zijlstra
2016-07-07 11:08 ` Peter Zijlstra
2016-07-07 11:09 ` Peter Zijlstra
2016-07-07 11:21 ` Peter Zijlstra
2016-07-11 15:10 ` Waiman Long
2016-07-12 4:16 ` Juergen Gross
2016-07-12 18:16 ` Waiman Long
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=1467124991-13164-4-git-send-email-xinhui.pan@linux.vnet.ibm.com \
--to=xinhui.pan@linux.vnet.ibm.com \
--cc=benh@kernel.crashing.org \
--cc=boqun.feng@gmail.com \
--cc=dave@stgolabs.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=paulmck@linux.vnet.ibm.com \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=schwidefsky@de.ibm.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=waiman.long@hpe.com \
--cc=will.deacon@arm.com \
/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).