search for: poll_dur

Displaying 5 results from an estimated 5 matches for "poll_dur".

Did you mean: poll_dev
2017 Nov 13
0
[PATCH RFC v3 6/6] KVM guest: introduce smart idle poll algorithm
...s */ + if (old == 0 && grow) + return 10000; + + val = old * grow; + if (val > max) + val = max; + + return val; +} + +static unsigned int shrink_poll_ns(unsigned int old, unsigned int shrink) +{ + if (shrink == 0) + return 0; + + return old / shrink; +} + +static void kvm_idle_update_poll_duration(ktime_t idle) +{ + unsigned long poll_duration = this_cpu_read(poll_duration_ns); + + /* so far poll duration is based on nohz */ + if (idle == -1ULL) + return; + + if (poll_duration && idle > paravirt_poll_threshold_ns) + poll_duration = shrink_poll_ns(poll_duration, +...
2017 Nov 13
0
[PATCH RFC v3 6/6] KVM guest: introduce smart idle poll algorithm
...s */ + if (old == 0 && grow) + return 10000; + + val = old * grow; + if (val > max) + val = max; + + return val; +} + +static unsigned int shrink_poll_ns(unsigned int old, unsigned int shrink) +{ + if (shrink == 0) + return 0; + + return old / shrink; +} + +static void kvm_idle_update_poll_duration(ktime_t idle) +{ + unsigned long poll_duration = this_cpu_read(poll_duration_ns); + + /* so far poll duration is based on nohz */ + if (idle == -1ULL) + return; + + if (poll_duration && idle > paravirt_poll_threshold_ns) + poll_duration = shrink_poll_ns(poll_duration, +...
2007 Jul 05
2
DTracing GNOME startup
Hi there, I''ve been using OpenSolaris for three months now, and I''ve started to get interested about to get my hands dirty with DTrace. Since I have an strong GNOME background, I would like to use it to help GNOME developers to find performance problems. Federico Mena Quintero, one of the Novell GNOME guys is one of the people that are working on GNOME performance stuff. He
2017 Nov 13
7
[PATCH RFC v3 0/6] x86/idle: add halt poll support
From: Yang Zhang <yang.zhang.wz at gmail.com> Some latency-intensive workload have seen obviously performance drop when running inside VM. The main reason is that the overhead is amplified when running inside VM. The most cost I have seen is inside idle path. This patch introduces a new mechanism to poll for a while before entering idle state. If schedule is needed during poll, then we
2017 Nov 13
7
[PATCH RFC v3 0/6] x86/idle: add halt poll support
From: Yang Zhang <yang.zhang.wz at gmail.com> Some latency-intensive workload have seen obviously performance drop when running inside VM. The main reason is that the overhead is amplified when running inside VM. The most cost I have seen is inside idle path. This patch introduces a new mechanism to poll for a while before entering idle state. If schedule is needed during poll, then we