From 5b8e85034028906ab0a243399e18fd8b72fe2f76 Mon Sep 17 00:00:00 2001 From: Michael Anthony Knyszek Date: Mon, 3 Feb 2025 16:53:47 +0000 Subject: [PATCH] runtime: don't track scheduling latency for _Grunning <-> _Gsyscall MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit The current logic causes much more tracking than necessary, when really _Grunning and _Gsyscall are both sort of "running" from the perspective of tracking scheduling latency. This makes cgo calls and syscalls a little faster in the single-threaded case, and shows much larger improvement in the multi-threaded case by removing updates of shared variables (though this parallel microbenchmark is a little unrealistic, so don't ascribe too much weight to it). goos: linux goarch: amd64 pkg: internal/runtime/cgobench cpu: AMD EPYC 7B13 │ after.out │ after-2.out │ │ sec/op │ sec/op vs base │ CgoCall-64 35.83n ± 1% 34.69n ± 1% -3.20% (p=0.002 n=6) CgoCallParallel-64 5.338n ± 1% 1.352n ± 4% -74.67% (p=0.002 n=6) Change-Id: I2ea494dd5ebbbfb457373549986fbe2fbe318d45 Reviewed-on: https://go-review.googlesource.com/c/go/+/646275 Auto-Submit: Michael Knyszek Reviewed-by: Michael Pratt LUCI-TryBot-Result: Go LUCI --- src/runtime/proc.go | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/runtime/proc.go b/src/runtime/proc.go index 2ec2f8cfca..53f64e8032 100644 --- a/src/runtime/proc.go +++ b/src/runtime/proc.go @@ -1316,8 +1316,9 @@ func casgstatus(gp *g, oldval, newval uint32) { }) } - if oldval == _Grunning { - // Track every gTrackingPeriod time a goroutine transitions out of running. + if (oldval == _Grunning || oldval == _Gsyscall) && (newval != _Grunning && newval != _Gsyscall) { + // Track every gTrackingPeriod time a goroutine transitions out of _Grunning or _Gsyscall. + // Do not track _Grunning <-> _Gsyscall transitions, since they're two very similar states. if casgstatusAlwaysTrack || gp.trackingSeq%gTrackingPeriod == 0 { gp.tracking = true } -- 2.52.0