Commit:     0723a69a63beec1ca6e792239ef75d0181387ef0
Parent:     6b8be6df7f971919622d152d144c8798ad7fd160
Author:     Benjamin LaHaise <[EMAIL PROTECTED]>
AuthorDate: Wed Jan 30 13:33:13 2008 +0100
Committer:  Ingo Molnar <[EMAIL PROTECTED]>
CommitDate: Wed Jan 30 13:33:13 2008 +0100

    x86: fix synchronize_rcu(): high latency on idle system
    an otherwise idle system takes about 3 ticks per network
    interface in unregister_netdev() due to multiple calls to synchronize_rcu(),
    which adds up to quite a few seconds for tearing down thousands of
    interfaces.  By flushing pending rcu callbacks in the idle loop, the system
    makes progress hundreds of times faster.  If this is indeed a sane thing to,
    it probably needs to be done for other architectures than x86.  And yes, the
    network stack shouldn't call synchronize_rcu() quite so much, but fixing 
    is a little more involved.
    Signed-off-by: Ingo Molnar <[EMAIL PROTECTED]>
    Signed-off-by: Thomas Gleixner <[EMAIL PROTECTED]>
 arch/x86/kernel/process_32.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 7a61b54..69a69c3 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -198,6 +198,9 @@ void cpu_idle(void)
                        idle = pm_idle;
+                       if (rcu_pending(cpu))
+                               rcu_check_callbacks(cpu, 0);
                        if (!idle)
                                idle = default_idle;
To unsubscribe from this list: send the line "unsubscribe git-commits-head" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at

Reply via email to