Trt 1989 migration queries#3542
Conversation
|
Pipeline controller notification For optional jobs, comment This repository is configured in: automatic mode |
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughAdds Phase 2 index docs and Phase 3 query rules, adds GORM index tags, rewrites SQL/functions/views/queries to use denormalized prow_job_run_tests release/timestamp, updates API calls and benchmarks, and switches DB init to a pgx-backed connection pool. ChangesTRT-1989 Phase 2 & 3: Partitioning Preparation
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested labels
Suggested reviewers
🚥 Pre-merge checks | ✅ 19 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (19 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: neisw The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
openshift-ci
Bot
added
the
approved
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (1)
docs/plans/trt-1989-phase2-indexes.md (1)
14-16: ⚡ Quick winClarify the intentional index-order exception.
The doc says indexes mirror
(release, timestamp), butprow_job_run_testsis documented as(timestamp, release). Add an explicit “except forprow_job_run_tests” qualifier where the mirror rule is introduced.Also applies to: 41-43, 127-128
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/plans/trt-1989-phase2-indexes.md` around lines 14 - 16, Update the description that says indexes mirror the future partition key "(release, timestamp)" to explicitly note the intentional exception for the prow_job_run_tests index (which is documented as "(timestamp, release)"); add a parenthetical or sentence like "except for prow_job_run_tests, which intentionally uses (timestamp, release)" at the point where the mirror rule is introduced and make the same clarification in the other repeated occurrences of this rule later in the doc (the subsequent paragraph and the later section that repeats the mirror-index guidance).
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/plans/trt-1989-partitioning-prep.md`:
- Around line 86-88: The sentence incorrectly describes FK direction: change the
wording that currently reads "Tables with FKs from `prow_job_runs` to
non-partitioned tables (annotations, pull request join table)..." to clarify
that annotations and the pull-request join table hold FKs referencing
`prow_job_runs` (i.e., FKs to `prow_job_runs`), and therefore any tables that
reference `prow_job_runs` must be co-partitioned with it or have their FKs
dropped; update the line and any examples to use "tables with FKs to
`prow_job_runs` (annotations, pull request join table) must either be
co-partitioned or have their FKs dropped" and ensure surrounding text
consistently treats `prow_job_runs` as the referenced table.
In `@docs/plans/trt-1989-phase2-indexes.md`:
- Around line 36-37: Update the doc line that incorrectly references
ProwJobRunTest.ProwJobID: it should point to the prow_job_run_tests table /
ProwJobRunTests model field instead of prow_job_runs; replace the reference with
either "prow_job_run_tests" or "ProwJobRunTests.ProwJobID" so the standalone
index is correctly attributed to the prow_job_run_tests model.
In `@docs/plans/trt-1989-phase3-query-optimization.md`:
- Around line 28-31: The document's principle "Add filters, don't replace"
contradicts later rollout rules that replace/drop joins; update the principle
heading and first paragraph (the "Add filters, don't replace" paragraph) to
explicitly match the rollout: state that join-based filters are retained until
local columns are validated and tested, then replaced/dropped when safe, and
mirror this clarified wording in the other affected sections referenced
(sections covering the same guidance around lines 73-80, 81-86, and 126-132) so
the high-level principle and the detailed rollout rules are consistent.
---
Nitpick comments:
In `@docs/plans/trt-1989-phase2-indexes.md`:
- Around line 14-16: Update the description that says indexes mirror the future
partition key "(release, timestamp)" to explicitly note the intentional
exception for the prow_job_run_tests index (which is documented as "(timestamp,
release)"); add a parenthetical or sentence like "except for prow_job_run_tests,
which intentionally uses (timestamp, release)" at the point where the mirror
rule is introduced and make the same clarification in the other repeated
occurrences of this rule later in the doc (the subsequent paragraph and the
later section that repeats the mirror-index guidance).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Enterprise
Run ID: 44fd03d2-a25c-47af-9a09-37386bb12690
📒 Files selected for processing (16)
cmd/sippy/seed_data.godocs/plans/trt-1989-partitioning-prep.mddocs/plans/trt-1989-phase2-indexes.mddocs/plans/trt-1989-phase3-query-optimization.mdpkg/api/componentreadiness/dataprovider/postgres/provider.gopkg/api/job_runs_test.gopkg/api/recent_test_failures.gopkg/dataloader/prowloader/prow.gopkg/db/db.gopkg/db/functions.gopkg/db/models/prow.gopkg/db/query/build_clusters.gopkg/db/query/job_queries.gopkg/db/query/test_queries.gopkg/db/views.gopkg/sippyserver/pr_new_tests_worker_test.go
| Also added a standalone index on `ProwJobRunTest.ProwJobID` to support | ||
| variant queries that previously required joining through `prow_job_runs`. |
There was a problem hiding this comment.
Correct the model/table reference for the standalone index.
The text points to ProwJobRunTest.ProwJobID, but this index is on prow_job_run_tests (ProwJobRunTests model field), not prow_job_runs.
Proposed doc fix
-Also added a standalone index on `ProwJobRunTest.ProwJobID` to support
+Also added a standalone index on `ProwJobRunTests.ProwJobID` to support📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| Also added a standalone index on `ProwJobRunTest.ProwJobID` to support | |
| variant queries that previously required joining through `prow_job_runs`. | |
| Also added a standalone index on `ProwJobRunTests.ProwJobID` to support | |
| variant queries that previously required joining through `prow_job_runs`. |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/plans/trt-1989-phase2-indexes.md` around lines 36 - 37, Update the doc
line that incorrectly references ProwJobRunTest.ProwJobID: it should point to
the prow_job_run_tests table / ProwJobRunTests model field instead of
prow_job_runs; replace the reference with either "prow_job_run_tests" or
"ProwJobRunTests.ProwJobID" so the standalone index is correctly attributed to
the prow_job_run_tests model.
|
Scheduling required tests: |
|
/hold |
openshift-ci
Bot
added
the
do-not-merge/hold
neisw
force-pushed
the
trt-1989-migration-queries
branch
from
9cefc7d to
66753c4
Compare
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (2)
docs/plans/trt-1989-phase3-query-optimization.md (1)
28-31:⚠️ Potential issue | 🟠 Major | ⚡ Quick winAlign the guiding principle with the rollout rules.
This principle conflicts with later sections that replace filters and drop joins after local-column validation. Please reword it to: keep join-based filters initially, then replace/drop when validated safe.
Proposed doc fix
-1. **Add filters, don't replace** — keep existing join-based filters - alongside the new local filters. The planner uses whichever is cheaper. - Removing them risks behavior change if denormalized data has gaps. +1. **Add filters first, then replace when validated** — keep existing + join-based filters alongside new local filters during rollout. + After local denormalized columns are validated, replace old filters + and drop no-longer-needed joins where safe.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/plans/trt-1989-phase3-query-optimization.md` around lines 28 - 31, Update the principle titled "Add filters, don't replace" so it matches the rollout rules: reword the sentence to state that join-based filters should be retained initially alongside new local filters and only replaced/dropped after local-column validation proves it safe; ensure the new wording explicitly says "keep join-based filters initially, then replace/drop when validated safe" and that it aligns with later sections that describe replacing filters and dropping joins post-validation.docs/plans/trt-1989-partitioning-prep.md (1)
86-88:⚠️ Potential issue | 🟠 Major | ⚡ Quick winFix inverted FK direction in migration constraints.
This still states FKs are from
prow_job_runsto annotations/PR join rows, but those tables referenceprow_job_runs. Please flip the direction to avoid incorrect partitioning/FK planning.Proposed doc fix
-3. Tables with FKs **from** `prow_job_runs` to non-partitioned tables - (annotations, pull request join table) must either be co-partitioned - or have their FKs dropped. +3. Tables with FKs **to** `prow_job_runs` from non-partitioned tables + (annotations, pull request join table) must either be co-partitioned + or have their FKs dropped.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/plans/trt-1989-partitioning-prep.md` around lines 86 - 88, The sentence incorrectly states foreign keys are "from prow_job_runs to annotations/pull request join table"; update the wording to say the annotations and pull request join table have FKs referencing prow_job_runs (i.e., FKs are to prow_job_runs from those tables) and therefore those referencing tables must be co-partitioned with prow_job_runs or have their FKs dropped; locate and change the phrase mentioning prow_job_runs, annotations, and pull request join table so the FK direction is flipped to "annotations/PR join rows -> prow_job_runs" and clarify the co-partition/drop requirement.
🧹 Nitpick comments (1)
pkg/db/query/test_queries.go (1)
281-291: ⚡ Quick winAdd short inline comments for major query sections in changed builders.
The modified JOIN/WHERE/grouping sections are non-trivial and currently undocumented in-place; please add brief “why”-focused comments for the main sections.
As per coding guidelines, "BigQuery and SQL query-building code should have inline comments explaining the purpose of each major query section (CTEs, JOINs, window functions, WHERE clauses)."
Also applies to: 321-325, 336-339
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@pkg/db/query/test_queries.go` around lines 281 - 291, The query builder chains (the q := dbc.DB.Table(...) blocks that join prow_job_run_test_outputs -> prow_job_run_tests -> prow_job_runs -> prow_jobs and the grouped WHERE clauses using current_date - interval '14' day and release/test filters) need short inline “why” comments: add brief comments above the JOIN group explaining why these tables are joined and what relationship/intent each JOIN captures, and above the WHERE block explaining the purpose of the 14-day time filters and why release/test filters are applied; do the same for the other similar q := dbc.DB.Table(...) builders in this file (the other blocks that start the same chain and contain the WHERE/grouping logic) so each major section (JOINs, time-window WHEREs, release/test filters, and any grouping/aggregation sections) has a succinct purpose-focused comment.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@pkg/db/query/test_queries.go`:
- Around line 285-291: Remove the legacy parent-table predicates that
over-constrain the denormalized TestOutputs path: drop the
Where("prow_job_runs.timestamp > current_date - interval '14' day") and
Where("prow_jobs.release = ?", release) clauses from the query so that filtering
relies on the child-table fields
(prow_job_run_test_outputs.prow_job_run_test_timestamp,
prow_job_run_test_outputs.prow_job_run_test_release,
prow_job_run_tests.prow_job_run_timestamp,
prow_job_run_tests.prow_job_run_release, and prow_job_run_tests.test_id = (?))
and thus preserves the denormalized/partition/index benefits.
---
Duplicate comments:
In `@docs/plans/trt-1989-partitioning-prep.md`:
- Around line 86-88: The sentence incorrectly states foreign keys are "from
prow_job_runs to annotations/pull request join table"; update the wording to say
the annotations and pull request join table have FKs referencing prow_job_runs
(i.e., FKs are to prow_job_runs from those tables) and therefore those
referencing tables must be co-partitioned with prow_job_runs or have their FKs
dropped; locate and change the phrase mentioning prow_job_runs, annotations, and
pull request join table so the FK direction is flipped to "annotations/PR join
rows -> prow_job_runs" and clarify the co-partition/drop requirement.
In `@docs/plans/trt-1989-phase3-query-optimization.md`:
- Around line 28-31: Update the principle titled "Add filters, don't replace" so
it matches the rollout rules: reword the sentence to state that join-based
filters should be retained initially alongside new local filters and only
replaced/dropped after local-column validation proves it safe; ensure the new
wording explicitly says "keep join-based filters initially, then replace/drop
when validated safe" and that it aligns with later sections that describe
replacing filters and dropping joins post-validation.
---
Nitpick comments:
In `@pkg/db/query/test_queries.go`:
- Around line 281-291: The query builder chains (the q := dbc.DB.Table(...)
blocks that join prow_job_run_test_outputs -> prow_job_run_tests ->
prow_job_runs -> prow_jobs and the grouped WHERE clauses using current_date -
interval '14' day and release/test filters) need short inline “why” comments:
add brief comments above the JOIN group explaining why these tables are joined
and what relationship/intent each JOIN captures, and above the WHERE block
explaining the purpose of the 14-day time filters and why release/test filters
are applied; do the same for the other similar q := dbc.DB.Table(...) builders
in this file (the other blocks that start the same chain and contain the
WHERE/grouping logic) so each major section (JOINs, time-window WHEREs,
release/test filters, and any grouping/aggregation sections) has a succinct
purpose-focused comment.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Enterprise
Run ID: 1d655e29-3ac0-40c3-bada-f206e2d07cf1
📒 Files selected for processing (16)
cmd/sippy/seed_data.godocs/plans/trt-1989-partitioning-prep.mddocs/plans/trt-1989-phase2-indexes.mddocs/plans/trt-1989-phase3-query-optimization.mdpkg/api/componentreadiness/dataprovider/postgres/provider.gopkg/api/job_runs_test.gopkg/api/recent_test_failures.gopkg/dataloader/prowloader/prow.gopkg/db/db.gopkg/db/functions.gopkg/db/models/prow.gopkg/db/query/build_clusters.gopkg/db/query/job_queries.gopkg/db/query/test_queries.gopkg/db/views.gopkg/sippyserver/pr_new_tests_worker_test.go
✅ Files skipped from review due to trivial changes (1)
- docs/plans/trt-1989-phase2-indexes.md
🚧 Files skipped from review as they are similar to previous changes (12)
- pkg/api/job_runs_test.go
- pkg/db/query/job_queries.go
- pkg/api/componentreadiness/dataprovider/postgres/provider.go
- pkg/db/functions.go
- pkg/db/db.go
- pkg/api/recent_test_failures.go
- cmd/sippy/seed_data.go
- pkg/sippyserver/pr_new_tests_worker_test.go
- pkg/db/query/build_clusters.go
- pkg/db/views.go
- pkg/db/models/prow.go
- pkg/dataloader/prowloader/prow.go
|
Scheduling required tests: |
1 similar comment
|
Scheduling required tests: |
openshift-ci
Bot
added
the
needs-rebase
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@pkg/flags/postgres_benchmarking_test.go`:
- Around line 77-85: The code currently treats an empty benchmarking_file_path
as "/" and may write to root; change the guard so you only append a trailing
slash and attempt writing when benchmarking_file_path is non-empty: check
len(benchmarkFilePath) > 0 immediately after reading
os.Getenv("benchmarking_file_path") and return/skip writing if it's empty; when
non-empty, normalize the path (use filepath.Join or ensure a single separator)
before building filename and calling os.WriteFile with
benchmarkFilePath+filename (or filepath.Join(benchmarkFilePath, filename));
update the conditions that control writing (the connName != "" &&
len(benchmarkFilePath) > 0 check) to run only when the env var was set.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Enterprise
Run ID: 283306bf-07cc-4e29-836a-9ce3b0189ce9
📒 Files selected for processing (8)
config/openshift-customizations.yamlconfig/openshift.yamlpkg/api/job_runs.gopkg/db/functions.gopkg/db/query/pull_request_queries.gopkg/db/query/repository_queries.gopkg/flags/postgres_benchmarking_test.gopkg/variantregistry/snapshot.yaml
✅ Files skipped from review due to trivial changes (1)
- config/openshift-customizations.yaml
neisw
force-pushed
the
trt-1989-migration-queries
branch
from
6d7b778 to
a2b4e6c
Compare
openshift-ci
Bot
removed
the
needs-rebase
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/plans/trt-1989-phase2-indexes.md`:
- Around line 31-37: The documentation incorrectly places the standalone index
note for prow_job_run_tests.prow_job_id under the prow_job_runs section; move
the two lines describing the index on prow_job_run_tests.prow_job_id (and the
index name if mentioned) out from under the "### prow_job_runs" header and place
them under the "### prow_job_run_tests" header (or create a short subsection
there) so the descriptive text matches the SQL shown later for the idx on
prow_job_run_tests.prow_job_id.
In `@pkg/db/models/prow.go`:
- Line 106: The ProwJobID field currently uses a generic GORM `index` tag which
lets GORM auto-generate the index name; update the struct tag for ProwJobID
(symbol: ProwJobID) to use an explicit index name
`idx_prow_job_run_tests_prow_job_id` (e.g.
`gorm:"index:idx_prow_job_run_tests_prow_job_id"`) so the created index name
matches the documentation and other composite indexes in this file.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Enterprise
Run ID: dd119370-9d91-4bd1-82eb-8a245a901131
📒 Files selected for processing (17)
docs/plans/trt-1989-partitioning-prep.mddocs/plans/trt-1989-phase2-indexes.mddocs/plans/trt-1989-phase3-query-optimization.mdpkg/api/componentreadiness/dataprovider/postgres/provider.gopkg/api/job_analysis.gopkg/api/job_runs.gopkg/api/recent_test_failures.gopkg/api/tests.gopkg/db/functions.gopkg/db/models/prow.gopkg/db/query/build_clusters.gopkg/db/query/job_queries.gopkg/db/query/pull_request_queries.gopkg/db/query/repository_queries.gopkg/db/query/test_queries.gopkg/db/views.gopkg/flags/postgres_benchmarking_test.go
✅ Files skipped from review due to trivial changes (1)
- docs/plans/trt-1989-phase3-query-optimization.md
| ### prow_job_runs | ||
|
|
||
| Added composite index `idx_prow_job_runs_release_timestamp` across | ||
| `ProwJobRelease` and `Timestamp`. | ||
|
|
||
| Also added a standalone index on `ProwJobRunTest.ProwJobID` to support | ||
| variant queries that previously required joining through `prow_job_runs`. |
There was a problem hiding this comment.
Move the standalone index documentation to the correct section.
Lines 36-37 describe an index on prow_job_run_tests.prow_job_id, but they appear under the ### prow_job_runs section header. This creates confusion about which table is being indexed.
📝 Proposed reorganization
Move lines 36-37 to appear under the ### prow_job_run_tests section (after line 38), or create a separate subsection if this index deserves its own explanation distinct from the composite release-timestamp index.
The SQL at lines 79-80 correctly shows this index on prow_job_run_tests, so the documentation sections should match the SQL organization.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/plans/trt-1989-phase2-indexes.md` around lines 31 - 37, The
documentation incorrectly places the standalone index note for
prow_job_run_tests.prow_job_id under the prow_job_runs section; move the two
lines describing the index on prow_job_run_tests.prow_job_id (and the index name
if mentioned) out from under the "### prow_job_runs" header and place them under
the "### prow_job_run_tests" header (or create a short subsection there) so the
descriptive text matches the SQL shown later for the idx on
prow_job_run_tests.prow_job_id.
35565d2 to
6e7dde0
Compare
|
Scheduling required tests: |
|
Capturing results verifying the refactored TestOutputs queries results match |
|
Scheduling required tests: |
neisw
force-pushed
the
trt-1989-migration-queries
branch
from
0e1bda0 to
912c2fa
Compare
|
@neisw: The following test failed, say
Full PR test history. Your PR dashboard. DetailsInstructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here. |
|
/test images |
|
@coderabbitai refresh your review based on the latest updates |
|
✅ Action performedFull review finished. |
|
Scheduling required tests: |
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
pkg/sippyserver/pr_new_tests_worker.go (1)
235-244:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winCache key may not account for release-scoped historical counts.
The
historicalTestCountcache usesrun.ProwJob.IDas the key (line 243), butProwJobHistoricalTestCountsnow returns release-scoped counts. If the same job ID is queried for different releases, the cached value from the first release will be incorrectly reused.Consider using a composite key that includes both job ID and release.
🔧 Proposed fix
type pgJobRunFilter struct { dbc *db.DB - historicalTestCount map[uint]int // in-memory cache of historical test counts per job id + historicalTestCount map[string]int // in-memory cache of historical test counts per job id + release }And update the cache key usage:
+ cacheKey := fmt.Sprintf("%d:%s", run.ProwJob.ID, run.ProwJob.Release) - historicalCount, ok := jrf.historicalTestCount[run.ProwJob.ID] + historicalCount, ok := jrf.historicalTestCount[cacheKey] if !ok { var err error historicalCount, err = query.ProwJobHistoricalTestCounts(jrf.dbc, run.ProwJobID, run.ProwJob.Release) if err != nil { logger.WithError(err).Error("Error determining historical job test count, ignoring this run") return true } - jrf.historicalTestCount[run.ProwJob.ID] = historicalCount + jrf.historicalTestCount[cacheKey] = historicalCount }🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@pkg/sippyserver/pr_new_tests_worker.go` around lines 235 - 244, The cache currently keys jrf.historicalTestCount by run.ProwJob.ID but ProwJobHistoricalTestCounts(jrf.dbc, run.ProwJobID, run.ProwJob.Release) returns release-scoped counts, so create a composite key that includes both run.ProwJob.ID and run.ProwJob.Release (e.g. fmt.Sprintf("%s|%s", run.ProwJob.ID, run.ProwJob.Release) or a small struct key) and use that key when reading from and writing to jrf.historicalTestCount; update the lookup and assignment around the historicalTestCount variable and any other places that access jrf.historicalTestCount to use the new composite key so cached counts are release-specific.
♻️ Duplicate comments (2)
docs/plans/trt-1989-partitioning-prep.md (2)
31-37:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winMove standalone index documentation to the correct section.
Lines 36-37 describe an index on
prow_job_run_tests.prow_job_id, but they appear under the### prow_job_runssection header (line 31). The SQL at lines 79-80 correctly creates this index on theprow_job_run_teststable.Move lines 36-37 to appear under the
### prow_job_run_testssection (after line 38) so the descriptive text matches the SQL organization and table scope.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/plans/trt-1989-partitioning-prep.md` around lines 31 - 37, The two-line description about the standalone index for prow_job_run_tests.prow_job_id is misplaced under the "### prow_job_runs" section; move that description so it appears under the "### prow_job_run_tests" header (immediately after that section header) so it matches the SQL that creates the index for prow_job_run_tests.prow_job_id; update the prose only—no SQL changes—and keep the same wording so the documentation aligns with the existing CREATE INDEX statement.
36-37:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winClarify table/model reference for the standalone index.
The text references
ProwJobRunTest.ProwJobID(Go struct field), but in the context of database index documentation it would be clearer to reference the table name directly:prow_job_run_tests.prow_job_idto match the SQL convention used throughout the rest of this doc.📝 Proposed clarification
-Also added a standalone index on `ProwJobRunTest.ProwJobID` to support +Also added a standalone index on `prow_job_run_tests.prow_job_id` to support🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/plans/trt-1989-partitioning-prep.md` around lines 36 - 37, Update the doc to reference the DB column/table name instead of the Go struct field: replace or augment the mention of ProwJobRunTest.ProwJobID with the SQL-style name prow_job_run_tests.prow_job_id (or include both, e.g., "prow_job_run_tests.prow_job_id (Go: ProwJobRunTest.ProwJobID)") so the index documentation consistently uses table/column naming like the rest of the document.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@go.mod`:
- Line 23: Update the pinned pgx dependency in go.mod from
github.com/jackc/pgx/v4 v4.18.2 to v4.18.3, and add a short TODO note in the
repo (e.g., in README or a migration planning doc) to plan migrating from pgx v4
to pgx v5 before the v4 EOL date; search for the module string
"github.com/jackc/pgx/v4" and change the version to "v4.18.3" and create/update
a migration task referencing pgx v5.
---
Outside diff comments:
In `@pkg/sippyserver/pr_new_tests_worker.go`:
- Around line 235-244: The cache currently keys jrf.historicalTestCount by
run.ProwJob.ID but ProwJobHistoricalTestCounts(jrf.dbc, run.ProwJobID,
run.ProwJob.Release) returns release-scoped counts, so create a composite key
that includes both run.ProwJob.ID and run.ProwJob.Release (e.g.
fmt.Sprintf("%s|%s", run.ProwJob.ID, run.ProwJob.Release) or a small struct key)
and use that key when reading from and writing to jrf.historicalTestCount;
update the lookup and assignment around the historicalTestCount variable and any
other places that access jrf.historicalTestCount to use the new composite key so
cached counts are release-specific.
---
Duplicate comments:
In `@docs/plans/trt-1989-partitioning-prep.md`:
- Around line 31-37: The two-line description about the standalone index for
prow_job_run_tests.prow_job_id is misplaced under the "### prow_job_runs"
section; move that description so it appears under the "### prow_job_run_tests"
header (immediately after that section header) so it matches the SQL that
creates the index for prow_job_run_tests.prow_job_id; update the prose only—no
SQL changes—and keep the same wording so the documentation aligns with the
existing CREATE INDEX statement.
- Around line 36-37: Update the doc to reference the DB column/table name
instead of the Go struct field: replace or augment the mention of
ProwJobRunTest.ProwJobID with the SQL-style name prow_job_run_tests.prow_job_id
(or include both, e.g., "prow_job_run_tests.prow_job_id (Go:
ProwJobRunTest.ProwJobID)") so the index documentation consistently uses
table/column naming like the rest of the document.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Enterprise
Run ID: 2e60b60d-7d5e-49fc-85e5-327cf0b469a2
📒 Files selected for processing (22)
docs/plans/trt-1989-partitioning-prep.mddocs/plans/trt-1989-phase2-indexes.mddocs/plans/trt-1989-phase3-query-optimization.mdgo.modpkg/api/componentreadiness/dataprovider/postgres/provider.gopkg/api/job_analysis.gopkg/api/job_runs.gopkg/api/jobs.gopkg/api/recent_test_failures.gopkg/api/test_analysis.gopkg/api/tests.gopkg/db/db.gopkg/db/functions.gopkg/db/models/prow.gopkg/db/query/build_clusters.gopkg/db/query/job_queries.gopkg/db/query/pull_request_queries.gopkg/db/query/repository_queries.gopkg/db/query/test_queries.gopkg/db/views.gopkg/flags/postgres_benchmarking_test.gopkg/sippyserver/pr_new_tests_worker.go
| github.com/gorilla/websocket v1.5.3 | ||
| github.com/hashicorp/go-version v1.7.0 | ||
| github.com/jackc/pgtype v1.14.0 | ||
| github.com/jackc/pgx/v4 v4.18.2 |
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
What is the latest stable version of github.com/jackc/pgx/v4 and are there any known CVEs for v4.18.2?
💡 Result:
The latest stable version of github.com/jackc/pgx/v4 is v4.18.3 [1][2][3]. Regarding version v4.18.2, there are no known CVEs specifically targeting this version; rather, v4.18.2 was the patched release that addressed two specific security vulnerabilities [4][5]. These vulnerabilities affected versions prior to v4.18.2 [4][5]: 1. CVE-2024-27289: An SQL injection vulnerability that could occur when using the non-default simple protocol with specific parameter placements [4][6]. 2. CVE-2024-27304: An SQL injection vulnerability caused by an integer overflow in the calculated protocol message size when a query or bind message exceeded 4 GB [5]. As of June 3, 2026, it should be noted that pgx v4 has reached its end-of-life, which occurred on July 1, 2025 [7][8]. Users are encouraged to upgrade to v5 [1][7][3].
Citations:
- 1: https://github.com/jackc/pgx/tree/v4.18.3
- 2: https://github.com/jackc/pgx/blob/v4.18.3/CHANGELOG.md
- 3: https://pkg.go.dev/github.com/jackc/pgx/v4
- 4: GHSA-m7wr-2xf7-cm9p
- 5: GHSA-mrww-27vc-gghv
- 6: https://osv.dev/vulnerability/CVE-2024-27289
- 7: https://github.com/jackc/pgx/tree/v4
- 8: Update github.com/jackc/pgx/v4 to v5 quay/clair#2238
Upgrade pgx/v4 from v4.18.2 to v4.18.3 and plan v5 migration (v4 EOL)
go.modpinsgithub.com/jackc/pgx/v4 v4.18.2; no known CVEs specifically affectv4.18.2(CVE-2024-27289 and CVE-2024-27304 were fixed in prior releases includingv4.18.2).- Latest stable
pgx/v4isv4.18.3, andpgxv4 is end-of-life (July 1, 2025) → upgrade and plan migration topgxv5.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@go.mod` at line 23, Update the pinned pgx dependency in go.mod from
github.com/jackc/pgx/v4 v4.18.2 to v4.18.3, and add a short TODO note in the
repo (e.g., in README or a migration planning doc) to plan migrating from pgx v4
to pgx v5 before the v4 EOL date; search for the module string
"github.com/jackc/pgx/v4" and change the version to "v4.18.3" and create/update
a migration task referencing pgx v5.
1 participant
Depends on #3541, updates queries to use new indexes.
Summary by CodeRabbit
Documentation
Performance Improvements
Behavior Changes
Tests