Skip to content

/prometheus

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

`predict_linear` could be more predictive. #1401

Closed
beorn7 opened this Issue Feb 17, 2016 · 2 comments

Comments

Assignees

@beorn7 beorn7

Labels
None yet
Projects
None yet
Milestone
No milestone
2 participants
@beorn7 @juliusv
@beorn7
Copy link
Member

beorn7 commented Feb 17, 2016

See attached image. Essentially, we are calculating the slope with sophisticated regression analysis, and then we are not starting at the value predicted for the end of the range but at the last sample value within the range.
img_20160217_162506

@beorn7 beorn7 added the enhancement label Feb 17, 2016

@beorn7 beorn7 self-assigned this Feb 17, 2016

@juliusv

This comment has been minimized.

Sign in to view
Copy link
Member

juliusv commented Feb 17, 2016

Every issue should now contain whiteboard snapshots. <3

beorn7 added a commit that referenced this issue Feb 18, 2016

@beorn7
Streamline series iterator creation 
This will fix issue #1035 and will also help to make issue #1264 less
bad.

The fundamental problem in the current code:

In the preload phase, we quite accurately determine which chunks will
be used for the query being executed. However, in the subsequent step
of creating series iterators, the created iterators are referencing
_all_ in-memory chunks in their series, even the un-pinned ones. In
iterator creation, we copy a pointer to each in-memory chunk of a
series into the iterator. While this creates a certain amount of
allocation churn, the worst thing about it is that copying the chunk
pointer out of the chunkDesc requires a mutex acquisition. (Remember
that the iterator will also reference un-pinned chunks, so we need to
acquire the mutex to protect against concurrent eviction.) The worst
case happens if a series doesn't even contain any relevant samples for
the query time range. We notice that during preloading but then we
will still create a series iterator for it. But even for series that
do contain relevant samples, the overhead is quite bad for instant
queries that retrieve a single sample from each series, but still go
through all the effort of series iterator creation. All of that is
particularly bad if a series has many in-memory chunks.

This commit addresses the problem from two sides:

First, it merges preloading and iterator creation into one step,
i.e. the preload call returns an iterator for exactly the preloaded
chunks.

Second, the required mutex acquisition in chunkDesc has been greatly
reduced. That was enabled by a side effect of the first step, which is
that the iterator is only referencing pinned chunks, so there is no
risk of concurrent eviction anymore, and chunks can be accessed
without mutex acquisition.

To simplify the code changes for the above, the long-planned change of
ValueAtTime to ValueAtOrBefore time was performed at the same
time. (It should have been done first, but it kind of accidentally
happened while I was in the middle of writing the series iterator
changes. Sorry for that.) So far, we actively filtered the up to two
values that were returned by ValueAtTime, i.e. we invested work to
retrieve up to two values, and then we invested more work to throw one
of them away.

The SeriesIterator.BoundaryValues method can be removed once #1401 is
fixed. But I really didn't want to load even more changes into this
PR.

Benchmarks:

The BenchmarkFuzz.* benchmarks run 83% faster (i.e. about six times
faster) and allocate 95% fewer bytes. The reason for that is that the
benchmark reads one sample after another from the time series and
creates a new series iterator for each sample read.

To find out how much these improvements matter in practice, I have
mirrored a beefy Prometheus server at SoundCloud that suffers from
both issues #1035 and #1264. To reach steady state that would be
comparable, the server needs to run for 15d. So far, it has run for
1d. The test server currently has only half as many memory time series
and 60% of the memory chunks the main server has. The 90th percentile
rule evaluation cycle time is ~11s on the main server and only ~3s on
the test server. However, these numbers might get much closer over
time.

In addition to performance improvements, this commit removes about 150
LOC.
Loading status checks…
2a7ee8e

@beorn7 beorn7 referenced this issue Feb 18, 2016

Merged

Streamline series iterator creation #1405

beorn7 added a commit that referenced this issue Feb 19, 2016

@beorn7
Streamline series iterator creation 
This will fix issue #1035 and will also help to make issue #1264 less
bad.

The fundamental problem in the current code:

In the preload phase, we quite accurately determine which chunks will
be used for the query being executed. However, in the subsequent step
of creating series iterators, the created iterators are referencing
_all_ in-memory chunks in their series, even the un-pinned ones. In
iterator creation, we copy a pointer to each in-memory chunk of a
series into the iterator. While this creates a certain amount of
allocation churn, the worst thing about it is that copying the chunk
pointer out of the chunkDesc requires a mutex acquisition. (Remember
that the iterator will also reference un-pinned chunks, so we need to
acquire the mutex to protect against concurrent eviction.) The worst
case happens if a series doesn't even contain any relevant samples for
the query time range. We notice that during preloading but then we
will still create a series iterator for it. But even for series that
do contain relevant samples, the overhead is quite bad for instant
queries that retrieve a single sample from each series, but still go
through all the effort of series iterator creation. All of that is
particularly bad if a series has many in-memory chunks.

This commit addresses the problem from two sides:

First, it merges preloading and iterator creation into one step,
i.e. the preload call returns an iterator for exactly the preloaded
chunks.

Second, the required mutex acquisition in chunkDesc has been greatly
reduced. That was enabled by a side effect of the first step, which is
that the iterator is only referencing pinned chunks, so there is no
risk of concurrent eviction anymore, and chunks can be accessed
without mutex acquisition.

To simplify the code changes for the above, the long-planned change of
ValueAtTime to ValueAtOrBefore time was performed at the same
time. (It should have been done first, but it kind of accidentally
happened while I was in the middle of writing the series iterator
changes. Sorry for that.) So far, we actively filtered the up to two
values that were returned by ValueAtTime, i.e. we invested work to
retrieve up to two values, and then we invested more work to throw one
of them away.

The SeriesIterator.BoundaryValues method can be removed once #1401 is
fixed. But I really didn't want to load even more changes into this
PR.

Benchmarks:

The BenchmarkFuzz.* benchmarks run 83% faster (i.e. about six times
faster) and allocate 95% fewer bytes. The reason for that is that the
benchmark reads one sample after another from the time series and
creates a new series iterator for each sample read.

To find out how much these improvements matter in practice, I have
mirrored a beefy Prometheus server at SoundCloud that suffers from
both issues #1035 and #1264. To reach steady state that would be
comparable, the server needs to run for 15d. So far, it has run for
1d. The test server currently has only half as many memory time series
and 60% of the memory chunks the main server has. The 90th percentile
rule evaluation cycle time is ~11s on the main server and only ~3s on
the test server. However, these numbers might get much closer over
time.

In addition to performance improvements, this commit removes about 150
LOC.
0e202da

beorn7 added a commit that referenced this issue Feb 24, 2016

@beorn7
Improve predict_linear 
Fixes #1401

This remove the last (and in fact bogus) use of BoundaryValues.

Thus, a whole lot of unused (and arguably sub-optimal / ugly) code can
be removed here, too.
Loading status checks…
1183dcf

@beorn7 beorn7 referenced this issue Feb 24, 2016

Merged

Improve predict_linear #1426

@beorn7 beorn7 closed this in c740789 Mar 9, 2016

gouthamve pushed a commit to gouthamve/promql that referenced this issue Mar 28, 2018

@beorn7
Improve predict_linear 
Fixes prometheus/prometheus#1401

This remove the last (and in fact bogus) use of BoundaryValues.

Thus, a whole lot of unused (and arguably sub-optimal / ugly) code can
be removed here, too.
8fe23e0
@lock

This comment has been minimized.

Sign in to view
Copy link

lock bot commented Mar 24, 2019

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.

@lock lock bot locked and limited conversation to collaborators Mar 24, 2019

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
You can’t perform that action at this time.