This reverts commit go.dev/cl/528657.
Reason for revert: broke a lot of builders.
Change-Id: I70c33062020e997c4df67b3eaa2e886cf0da961e
Reviewed-on: https://go-review.googlesource.com/c/go/+/543660
Reviewed-by: Than McIntosh <thanm@google.com>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Add runtime-internal locks to the mutex contention profile.
Store up to one call stack responsible for lock contention on the M,
until it's safe to contribute its value to the mprof table. Try to use
that limited local storage space for a relatively large source of
contention, and attribute any contention in stacks we're not able to
store to a sentinel _LostContendedLock function.
Avoid ballooning lock contention while manipulating the mprof table by
attributing to that sentinel function any lock contention experienced
while reporting lock contention.
Guard collecting real call stacks with GODEBUG=profileruntimelocks=1,
since the available data has mixed semantics; we can easily capture an
M's own wait time, but we'd prefer for the profile entry of each
critical section to describe how long it made the other Ms wait. It's
too late in the Go 1.22 cycle to make the required changes to
futex-based locks. When not enabled, attribute the time to the sentinel
function instead.
Fixes#57071
Change-Id: I3eee0ccbfc20f333b56f20d8725dfd7f3a526b41
Reviewed-on: https://go-review.googlesource.com/c/go/+/528657
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
Auto-Submit: Rhys Hiltner <rhys@justin.tv>
Reviewed-by: Than McIntosh <thanm@google.com>
A follow-up to https://go.dev/cl/534161 -- calls to runtime/trace.Start
and Stop synchronize with the GC, waiting for any in-progress mark phase
to complete. Disable automatic GCs to quiet the system, so we can
observe only the test's intentional pauses.
Change-Id: I6f8106c42528f9bda9afec1c151119783bbc78dc
Reviewed-on: https://go-review.googlesource.com/c/go/+/543075
Run-TryBot: Rhys Hiltner <rhys@justin.tv>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Michael Pratt <mpratt@google.com>
Auto-Submit: Rhys Hiltner <rhys@justin.tv>
Reviewed-by: Bryan Mills <bcmills@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
This CL adds four new time histogram metrics:
/sched/pauses/stopping/gc:seconds
/sched/pauses/stopping/other:seconds
/sched/pauses/total/gc:seconds
/sched/pauses/total/other:seconds
The "stopping" metrics measure the time taken to start a stop-the-world
pause. i.e., how long it takes stopTheWorldWithSema to stop all Ps.
This can be used to detect STW struggling to preempt Ps.
The "total" metrics measure the total duration of a stop-the-world
pause, from starting to stop-the-world until the world is started again.
This includes the time spent in the "start" phase.
The "gc" metrics are used for GC-related STW pauses. The "other" metrics
are used for all other STW pauses.
All of these metrics start timing in stopTheWorldWithSema only after
successfully acquiring sched.lock, thus excluding lock contention on
sched.lock. The reasoning behind this is that while waiting on
sched.lock the world is not stopped at all (all other Ps can run), so
the impact of this contention is primarily limited to the goroutine
attempting to stop-the-world. Additionally, we already have some
visibility into sched.lock contention via contention profiles (#57071).
/sched/pauses/total/gc:seconds is conceptually equivalent to
/gc/pauses:seconds, so the latter is marked as deprecated and returns
the same histogram as the former.
In the implementation, there are a few minor differences:
* For both mark and sweep termination stops, /gc/pauses:seconds started
timing prior to calling startTheWorldWithSema, thus including lock
contention.
These details are minor enough, that I do not believe the slight change
in reporting will matter. For mark termination stops, moving timing stop
into startTheWorldWithSema does have the side effect of requiring moving
other GC metric calculations outside of the STW, as they depend on the
same end time.
Fixes#63340
Change-Id: Iacd0bab11bedab85d3dcfb982361413a7d9c0d05
Reviewed-on: https://go-review.googlesource.com/c/go/+/534161
Reviewed-by: Michael Knyszek <mknyszek@google.com>
Auto-Submit: Michael Pratt <mpratt@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
In the existing implementation, all /gc/scan/* metrics are
always equal to 0 due to the dependency on gcStatDep not being
set. This leads to gcStatAggregate always containing zeros, and
always reporting 0 for those metrics.
Also, add a test to ensure that /gc/scan/* metrics are not empty.
Fixes#62477.
Change-Id: I67497347d50ed5c3ce1719a18714c062ec938cab
Reviewed-on: https://go-review.googlesource.com/c/go/+/525595
Reviewed-by: Michael Knyszek <mknyszek@google.com>
Auto-Submit: Michael Knyszek <mknyszek@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
Reviewed-by: Felix Geisendörfer <felix.geisendoerfer@datadoghq.com>
/gc/heap/live:bytes may exceed MemStats.HeapAlloc, even when all data is
flushed, becuase the GC may double-count objects when marking them. This
is an intentional design choice that is largely inconsequential. The
runtime is already robust to it, and the condition is rare.
Fixes#60607.
Change-Id: I4da402efc24327328d2d8780e4e49961b189f0ea
Reviewed-on: https://go-review.googlesource.com/c/go/+/501858
Auto-Submit: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
This test was introduced as a regression test for #60276. However, it
was quite flaky on a number of different platforms because there are
myriad ways the runtime can eat into time one might expect is completely
idle.
This change re-enables the test, but makes it much more resilient.
Because the issue we're testing for is persistent, we now require 10
consecutive failures to count. Any single success counts as a test
success. This change also makes the test's idle time bound more lenient,
allowing for a little bit of time to be eaten up. The regression we're
testing for results in nearly zero idle time being accounted for.
If this is still not good enough to eliminate flakes, this test should
just be deleted.
For #60276.
Fixes#60376.
Change-Id: Icd81f0c9970821b7f386f6d27c8a566fee4d0ff7
Reviewed-on: https://go-review.googlesource.com/c/go/+/498274
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Michael Pratt <mpratt@google.com>
Currently /gc/scan/total:bytes is computed as a separate sum. Compute it
using the same inputs so it's always consistent with the sum of
everything else in /gc/scan/*.
For #56857.
Change-Id: I43d9148a23b1d2eb948ae990193dca1da85df8a3
Reviewed-on: https://go-review.googlesource.com/c/go/+/497880
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
This test is fundamentally flaky because of a mismatch between how
internal idle time is calculated and how the test expects it to be
calculated. It's unclear how to resolve this mismatch, given that it's
perfectly valid for a goroutine to remain asleep while background
goroutines (e.g. the scavenger) run. In practice, we might be able to
set some generous lower-bound, but until we can confirm that on the
affected platforms, skip the test as flaky unconditionally.
For #60276.
For #60376.
Change-Id: Iffd5c4be10cf8ae8a6c285b61fcc9173235fbb2a
Reviewed-on: https://go-review.googlesource.com/c/go/+/497876
Run-TryBot: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Bryan Mills <bcmills@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Currently pidleget gets passed "now" from before the M goes into
netpoll, resulting in incorrect accounting of idle CPU time.
lastpoll is also stored with a stale "now": the mistake was added in the
same CL it was added for pidleget.
Recompute "now" after returning from netpoll.
Also, start tracking idle time on js/wasm at all.
Credit to Rhys Hiltner for the test case.
Fixes#60276.
Change-Id: I5dd677471f74c915dfcf3d01621430876c3ff307
Reviewed-on: https://go-review.googlesource.com/c/go/+/496183
Reviewed-by: Michael Pratt <mpratt@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Ian Lance Taylor <iant@google.com>
For #56857
Change-Id: I0622af974783ab435e91b9fb3c1ba43f256ee4ac
Reviewed-on: https://go-review.googlesource.com/c/go/+/497315
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Felix Geisendörfer <felix.geisendoerfer@datadoghq.com>
Auto-Submit: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Knyszek <mknyszek@google.com>
Change-Id: Ifaa73b64e5b6a1d37c753e2440b642478d7dfbce
Reviewed-on: https://go-review.googlesource.com/c/go/+/436957
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Ian Lance Taylor <iant@google.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Run-TryBot: hopehook <hopehook@golangcn.org>
Run-TryBot: Ian Lance Taylor <iant@google.com>
Auto-Submit: Ian Lance Taylor <iant@google.com>
This change adds a metric to the runtime/metrics package which tracks
total mutex wait time for sync.Mutex and sync.RWMutex. The purpose of
this metric is to be able to quickly get an idea of the total mutex wait
time.
The implementation of this metric piggybacks off of the existing G
runnable tracking infrastructure, as well as the wait reason set on a G
when it goes into _Gwaiting.
Fixes#49881.
Change-Id: I4691abf64ac3574bec69b4d7d4428b1573130517
Reviewed-on: https://go-review.googlesource.com/c/go/+/427618
Reviewed-by: Michael Pratt <mpratt@google.com>
Auto-Submit: Michael Knyszek <mknyszek@google.com>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
This changes adds a breakdown for estimated CPU usage by time. These
estimates are not based on real on-CPU counters, so each metric has a
disclaimer explaining so. They can, however, be more reasonably
compared to a total CPU time metric that this change also adds.
Fixes#47216.
Change-Id: I125006526be9f8e0d609200e193da5a78d9935be
Reviewed-on: https://go-review.googlesource.com/c/go/+/404307
Reviewed-by: Michael Pratt <mpratt@google.com>
Reviewed-by: Josh MacDonald <jmacd@lightstep.com>
Auto-Submit: Michael Knyszek <mknyszek@google.com>
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Right now we export alloc count metrics via the runtime/metrics package
and mark them as monotonic, but that's not actually true. As an
optimization, the runtime assumes a span is always fully allocated
before being uncached, and updates the accounting as such. In the rare
case that it's wrong, the span has enough information to back out what
did not get allocated.
This change uses 16 bits of padding in the mspan to house another field
that represents the amount of mspan slots filled just as the mspan is
cached. This is information is enough to get an exact count, allowing us
to make the metrics truly monotonic.
Change-Id: Iaff3ca43f8745dc1bbb0232372423e014b89b920
Reviewed-on: https://go-review.googlesource.com/c/go/+/377516
Reviewed-by: Michael Pratt <mpratt@google.com>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
This change adds four additional metrics to the runtime/metrics package
to fill in a few gaps with runtime.MemStats that were overlooked. The
biggest one is TotalAlloc, which is impossible to find with the
runtime/metrics package, but also add a few others for convenience and
clarity. For instance, the total number of objects allocated and freed
are technically available via allocs-by-size and frees-by-size, but it's
onerous to get them (one needs to sum the sample counts in the
histograms).
The four additional metrics are:
- /gc/heap/allocs:bytes -- total bytes allocated (TotalAlloc)
- /gc/heap/allocs:objects -- total objects allocated (Mallocs - [tiny])
- /gc/heap/frees:bytes -- total bytes frees (TotalAlloc-HeapAlloc)
- /gc/heap/frees:objects -- total objects freed (Frees - [tiny])
This change also updates the descriptions of allocs-by-size and
frees-by-size to be more precise.
Change-Id: Iec8c1797a584491e3484b198f2e7f325b68954a7
Reviewed-on: https://go-review.googlesource.com/c/go/+/312431
Reviewed-by: Michael Pratt <mpratt@google.com>
Trust: Michael Knyszek <mknyszek@google.com>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Currently tiny allocations are not represented in either MemStats or
runtime/metrics, but they're represented in MemStats (indirectly) via
Mallocs. Add them to runtime/metrics by first merging
memstats.tinyallocs into consistentHeapStats (just for simplicity; it's
monotonic so metrics would still be self-consistent if we just read it
atomically) and then adding /gc/heap/tiny/allocs:objects to the list of
supported metrics.
Change-Id: Ie478006ab942a3e877b4a79065ffa43569722f3d
Reviewed-on: https://go-review.googlesource.com/c/go/+/312909
Trust: Michael Knyszek <mknyszek@google.com>
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Michael Pratt <mpratt@google.com>
This change modifies the *-by-size metrics' units to be based off the
bucket's unit (bytes) as opposed to the unit of the counts (objects).
This convention is more in-line with distributions in other metrics
systems.
Change-Id: Id3b68a09f52f0e1ff9f4346f613ae1cbd9f52f73
Reviewed-on: https://go-review.googlesource.com/c/go/+/282352
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
Trust: Michael Knyszek <mknyszek@google.com>
This change modifies the semantics of
runtime/metrics.Float64Histogram.Buckets to remove implicit buckets to
that extend to positive and negative infinity and instead defines all
bucket boundaries as explicitly listed.
Bucket boundaries remain the same as before except
/gc/heap/allocs-by-size:objects and /gc/heap/frees-by-size:objects no
longer have a bucket that extends to negative infinity.
This change simplifies the Float64Histogram API, making it both easier
to understand and easier to use.
Also, add a test for allocs-by-size and frees-by-size that checks them
against MemStats.
Fixes#43443.
Change-Id: I5620f15bd084562dadf288f733c4a8cace21910c
Reviewed-on: https://go-review.googlesource.com/c/go/+/281238
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
Trust: Michael Knyszek <mknyszek@google.com>
Currently these two metrics are reported incorrectly, going by the
documentation in the runtime/metrics package. We just copy in the
size-class-based values from the runtime wholesale, but those implicitly
have an inclusive upper-bound and exclusive lower-bound (e.g. 48-byte
size class contains objects in the size range (32, 48]) but the API
declares inclusive lower-bounds and exclusive upper-bounds.
Also, the bottom bucket representing (-inf, 1) should always be empty.
Extend the consistency check to verify this.
Updates #43329.
Change-Id: I11b5b062a34e13405ab662d15334bda91f779775
Reviewed-on: https://go-review.googlesource.com/c/go/+/279467
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
For #37112.
Change-Id: I994dfe848605b95ef6aec24f53869e929247e987
Reviewed-on: https://go-review.googlesource.com/c/go/+/247049
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
For #37112.
Change-Id: Ibb0425c9c582ae3da3b2662d5bbe830d7df9079c
Reviewed-on: https://go-review.googlesource.com/c/go/+/247047
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
This change adds metrics for the distribution of objects allocated and
freed by size, mirroring MemStats' BySize field.
For #37112.
Change-Id: Ibaf1812da93598b37265ec97abc6669c1a5efcbf
Reviewed-on: https://go-review.googlesource.com/c/go/+/247045
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
This change adds three new metrics: the heap goal, GC cycle count, and
forced GC count. These metrics are identical to their MemStats
counterparts.
For #37112.
Change-Id: I5a5e8dd550c0d646e5dcdbdf38274895e27cdd88
Reviewed-on: https://go-review.googlesource.com/c/go/+/247044
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
For #37112.
Change-Id: Idd3dd5c84215ddd1ab05c2e76e848aa0a4d40fb0
Reviewed-on: https://go-review.googlesource.com/c/go/+/247043
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
This change adds a new benchmark to the runtime tests for measuring the
latency of the new metrics implementation, based on the
ReadMemStats latency benchmark. readMetrics will have more metrics added
to it in the future, and this benchmark will serve as a way to measure
the cost of adding additional metrics.
Change-Id: Ib05e3ed4afa49a70863fc0c418eab35b72263e24
Reviewed-on: https://go-review.googlesource.com/c/go/+/247042
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Emmanuel Odeke <emmanuel@orijtech.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
This change adds support for a variety of runtime memory metrics and
contains the base implementation of Read for the runtime/metrics
package, which lives in the runtime.
It also adds testing infrastructure for the metrics package, and a bunch
of format and documentation tests.
For #37112.
Change-Id: I16a2c4781eeeb2de0abcb045c15105f1210e2d8a
Reviewed-on: https://go-review.googlesource.com/c/go/+/247041
Run-TryBot: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Michael Pratt <mpratt@google.com>
Trust: Michael Knyszek <mknyszek@google.com>
