diff options
author | Lunny Xiao <xiaolunwen@gmail.com> | 2025-02-17 11:28:37 -0800 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-02-17 11:28:37 -0800 |
commit | 7df09e31fa2700454beecbaf3c0721e13d6086f4 (patch) | |
tree | 57b732016e3f5f57135957c7675779bae4c8c03d /routers/api/v1/repo/git_ref.go | |
parent | f5a81f96362a873a4337b395de36d3bb9d91879c (diff) | |
download | gitea-7df09e31fa2700454beecbaf3c0721e13d6086f4.tar.gz gitea-7df09e31fa2700454beecbaf3c0721e13d6086f4.zip |
Move issue pin to an standalone table for querying performance (#33452)
Noticed a SQL in gitea.com has a bigger load. It seems both `is_pull`
and `pin_order` are not indexed columns in the database.
```SQL
SELECT `id`, `repo_id`, `index`, `poster_id`, `original_author`, `original_author_id`, `name`, `content`, `content_version`, `milestone_id`, `priority`, `is_closed`, `is_pull`, `num_comments`, `ref`, `pin_order`, `deadline_unix`, `created_unix`, `updated_unix`, `closed_unix`, `is_locked`, `time_estimate` FROM `issue` WHERE (repo_id =?) AND (is_pull = 0) AND (pin_order > 0) ORDER BY pin_order
```
I came across a comment
https://github.com/go-gitea/gitea/pull/24406#issuecomment-1527747296
from @delvh , which presents a more reasonable approach. Based on this,
this PR will migrate all issue and pull request pin data from the
`issue` table to the `issue_pin` table. This change benefits larger
Gitea instances by improving scalability and performance.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Diffstat (limited to 'routers/api/v1/repo/git_ref.go')
0 files changed, 0 insertions, 0 deletions