Skip to content

statsitstics: avoid sync load column which is skiped type to analyze #57144

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.

Sign up for GitHub

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

Merged
merged 5 commits into from
Nov 21, 2024
Merged

statsitstics: avoid sync load column which is skiped type to analyze #57144

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
86b1312
statsitstics: avoid sync load column which is skiped to analyze
hawkingrei Nov 13, 2024
e5ac14e
update
hawkingrei Nov 13, 2024
0df546c
update
hawkingrei Nov 15, 2024
74bed03
fix
hawkingrei Nov 19, 2024
f5d8d26
fix
hawkingrei Nov 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion pkg/statistics/handle/syncload/BUILD.bazel
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@ go_library(
"//pkg/parser/mysql",
"//pkg/sessionctx",
"//pkg/sessionctx/stmtctx",
"//pkg/sessionctx/variable",
"//pkg/statistics",
"//pkg/statistics/handle/storage",
"//pkg/statistics/handle/types",
Expand All @@ -35,7 +36,7 @@ go_test(
srcs = ["stats_syncload_test.go"],
flaky = True,
race = "on",
shard_count = 5,
shard_count = 6,
deps = [
":syncload",
"//pkg/config",
Expand Down
17 changes: 17 additions & 0 deletions pkg/statistics/handle/syncload/stats_syncload.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@ import (
"github.com/pingcap/tidb/pkg/parser/mysql"
"github.com/pingcap/tidb/pkg/sessionctx"
"github.com/pingcap/tidb/pkg/sessionctx/stmtctx"
"github.com/pingcap/tidb/pkg/sessionctx/variable"
"github.com/pingcap/tidb/pkg/statistics"
"github.com/pingcap/tidb/pkg/statistics/handle/storage"
statstypes "github.com/pingcap/tidb/pkg/statistics/handle/types"
Expand Down Expand Up @@ -300,6 +301,14 @@ func (s *statsSyncLoad) handleOneItemTask(task *statstypes.NeededItemTask) (err
s.statsHandle.SPool().Put(se)
}
}()
var skipTypes map[string]struct{}
val, err := sctx.GetSessionVars().GlobalVarsAccessor.GetGlobalSysVar(variable.TiDBAnalyzeSkipColumnTypes)
if err != nil {
logutil.BgLogger().Warn("failed to get global variable", zap.Error(err))
} else {
skipTypes = variable.ParseAnalyzeSkipColumnTypes(val)
}

item := task.Item.TableItemID
tbl, ok := s.statsHandle.Get(item.TableID)

Expand Down Expand Up @@ -335,6 +344,13 @@ func (s *statsSyncLoad) handleOneItemTask(task *statstypes.NeededItemTask) (err
// so we have to get the column info from the domain.
wrapper.colInfo = tblInfo.Meta().GetColumnByID(item.ID)
}
if skipTypes != nil {
_, skip := skipTypes[types.TypeToStr(wrapper.colInfo.FieldType.GetType(), wrapper.colInfo.FieldType.GetCharset())]
if skip {
return nil
}
}

// If this column is not analyzed yet and we don't have it in memory.
// We create a fake one for the pseudo estimation.
if loadNeeded && !analyzed {
Expand All @@ -348,6 +364,7 @@ func (s *statsSyncLoad) handleOneItemTask(task *statstypes.NeededItemTask) (err
return nil
}
}
failpoint.Inject("handleOneItemTaskPanic", nil)
t := time.Now()
needUpdate := false
wrapper, err = s.readStatsForOneItem(sctx, item, wrapper, isPkIsHandle, task.Item.FullLoad)
Expand Down
16 changes: 16 additions & 0 deletions pkg/statistics/handle/syncload/stats_syncload_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,22 @@ func TestSyncLoadSkipUnAnalyzedItems(t *testing.T) {
failpoint.Disable("github.com/pingcap/tidb/pkg/statistics/handle/syncload/assertSyncLoadItems")
}

func TestSyncLoadSkipAnalyzSkipColumnItems(t *testing.T) {
store, dom := testkit.CreateMockStoreAndDomain(t)
tk := testkit.NewTestKit(t, store)
tk.MustExec("use test")
tk.MustExec("drop table if exists t")
tk.MustExec("create table t(`id` bigint(20) NOT NULL AUTO_INCREMENT,content text,PRIMARY KEY (`id`))")
h := dom.StatsHandle()
h.SetLease(1)

tk.MustExec("analyze table t")
tk.MustExec("set @@session.tidb_analyze_skip_column_types = 'json, text, blob'") // text is not default.
require.NoError(t, failpoint.Enable("github.com/pingcap/tidb/pkg/statistics/handle/syncload/handleOneItemTaskPanic", `panic`))
tk.MustQuery("trace plan select * from t where content ='ab'")
require.NoError(t, failpoint.Disable("github.com/pingcap/tidb/pkg/statistics/handle/syncload/handleOneItemTaskPanic"))
}

func TestConcurrentLoadHist(t *testing.T) {
store, dom := testkit.CreateMockStoreAndDomain(t)

Expand Down