From e46c8e0558d287fcffde75bb458419288e71db62 Mon Sep 17 00:00:00 2001 From: Michael Anthony Knyszek Date: Wed, 19 Feb 2025 16:33:21 +0000 Subject: runtime: schedule cleanups across multiple goroutines This change splits the finalizer and cleanup queues and implements a new lock-free blocking queue for cleanups. The basic design is as follows: The cleanup queue is organized in fixed-sized blocks. Individual cleanup functions are queued, but only whole blocks are dequeued. Enqueuing cleanups places them in P-local cleanup blocks. These are flushed to the full list as they get full. Cleanups can only be enqueued by an active sweeper. Dequeuing cleanups always dequeues entire blocks from the full list. Cleanup blocks can be dequeued and executed at any time. The very last active sweeper in the sweep phase is responsible for flushing all local cleanup blocks to the full list. It can do this without any synchronization because the next GC can't start yet, so we can be very certain that nobody else will be accessing the local blocks. Cleanup blocks are stored off-heap because the need to be allocated by the sweeper, which is called from heap allocation paths. As a result, the GC treats cleanup blocks as roots, just like finalizer blocks. Flushes to the full list signal to the scheduler that cleanup goroutines should be awoken. Every time the scheduler goes to wake up a cleanup goroutine and there were more signals than goroutines to wake, it then forwards this signal to runtime.AddCleanup, so that it creates another goroutine the next time it is called, up to gomaxprocs goroutines. The signals here are a little convoluted, but exist because the sweeper and the scheduler cannot safely create new goroutines. For #71772. For #71825. Change-Id: Ie839fde2b67e1b79ac1426be0ea29a8d923a62cc Reviewed-on: https://go-review.googlesource.com/c/go/+/650697 Reviewed-by: Michael Pratt LUCI-TryBot-Result: Go LUCI Auto-Submit: Michael Knyszek --- src/runtime/runtime2.go | 54 +++++++++++++++++++++++++++---------------------- 1 file changed, 30 insertions(+), 24 deletions(-) (limited to 'src/runtime/runtime2.go') diff --git a/src/runtime/runtime2.go b/src/runtime/runtime2.go index 16f89f0bf5..da6791f9d2 100644 --- a/src/runtime/runtime2.go +++ b/src/runtime/runtime2.go @@ -458,30 +458,31 @@ type g struct { inMarkAssist bool coroexit bool // argument to coroswitch_m - raceignore int8 // ignore race detection events - nocgocallback bool // whether disable callback from C - tracking bool // whether we're tracking this G for sched latency statistics - trackingSeq uint8 // used to decide whether to track this G - trackingStamp int64 // timestamp of when the G last started being tracked - runnableTime int64 // the amount of time spent runnable, cleared when running, only used when tracking - lockedm muintptr - fipsIndicator uint8 - sig uint32 - writebuf []byte - sigcode0 uintptr - sigcode1 uintptr - sigpc uintptr - parentGoid uint64 // goid of goroutine that created this goroutine - gopc uintptr // pc of go statement that created this goroutine - ancestors *[]ancestorInfo // ancestor information goroutine(s) that created this goroutine (only used if debug.tracebackancestors) - startpc uintptr // pc of goroutine function - racectx uintptr - waiting *sudog // sudog structures this g is waiting on (that have a valid elem ptr); in lock order - cgoCtxt []uintptr // cgo traceback context - labels unsafe.Pointer // profiler labels - timer *timer // cached timer for time.Sleep - sleepWhen int64 // when to sleep until - selectDone atomic.Uint32 // are we participating in a select and did someone win the race? + raceignore int8 // ignore race detection events + nocgocallback bool // whether disable callback from C + tracking bool // whether we're tracking this G for sched latency statistics + trackingSeq uint8 // used to decide whether to track this G + trackingStamp int64 // timestamp of when the G last started being tracked + runnableTime int64 // the amount of time spent runnable, cleared when running, only used when tracking + lockedm muintptr + fipsIndicator uint8 + runningCleanups atomic.Bool + sig uint32 + writebuf []byte + sigcode0 uintptr + sigcode1 uintptr + sigpc uintptr + parentGoid uint64 // goid of goroutine that created this goroutine + gopc uintptr // pc of go statement that created this goroutine + ancestors *[]ancestorInfo // ancestor information goroutine(s) that created this goroutine (only used if debug.tracebackancestors) + startpc uintptr // pc of goroutine function + racectx uintptr + waiting *sudog // sudog structures this g is waiting on (that have a valid elem ptr); in lock order + cgoCtxt []uintptr // cgo traceback context + labels unsafe.Pointer // profiler labels + timer *timer // cached timer for time.Sleep + sleepWhen int64 // when to sleep until + selectDone atomic.Uint32 // are we participating in a select and did someone win the race? // goroutineProfiled indicates the status of this goroutine's stack for the // current in-progress goroutine profile @@ -730,6 +731,9 @@ type p struct { // Timer heap. timers timers + // Cleanups. + cleanups *cleanupBlock + // maxStackScanDelta accumulates the amount of stack space held by // live goroutines (i.e. those eligible for stack scanning). // Flushed to gcController.maxStackScan once maxStackScanSlack @@ -1083,6 +1087,7 @@ const ( waitReasonSynctestChanReceive // "chan receive (synctest)" waitReasonSynctestChanSend // "chan send (synctest)" waitReasonSynctestSelect // "select (synctest)" + waitReasonCleanupWait // "cleanup wait" ) var waitReasonStrings = [...]string{ @@ -1130,6 +1135,7 @@ var waitReasonStrings = [...]string{ waitReasonSynctestChanReceive: "chan receive (synctest)", waitReasonSynctestChanSend: "chan send (synctest)", waitReasonSynctestSelect: "select (synctest)", + waitReasonCleanupWait: "cleanup wait", } func (w waitReason) String() string { -- cgit v1.3