sparse: lock the store when updating requirements config
Details
- Reviewers
Alphare - Group Reviewers
hg-reviewers - Commits
- rHG50330d481640: sparse: demonstrate a bug when used with safe-share
Diff Detail
- Repository
- rHG Mercurial
- Branch
- stable
- Lint
No Linters Available - Unit
No Unit Test Coverage
Event Timeline
Thanks for finding this.
However, this patch does not demonstrate a bug, but fixes one (that I had to check does exist). For the commit message to make sense, either split it in two patches, or update the message. Also, could you base this on stable instead? This is a bugfix and should go in the next minor release.
The patch does consist of two commits. I was under assumption that this is the way to review chains of commits. Should I in the future create a separate phabricator revision for each commit?
Oh. I've never seen this "squashed" presentation before. It does show 2 commits, but is useless in telling me the contents of either or their message. We usually send the stack we're working on with hg phabsend -r a::b, which creates linked diffs, one for each changeset.
Indeed. You can see the diff history on the "History" tab, but I'm guessing it only coincides with the commits because I pushed them one by one.
I rebased to the stable branch. I did hg phabsend --fold again to avoid changing things. Let me know if you'd like me to re-do the phabsend.
Looks like this results in a single commit as well on the import, please re-send unfolded.
Trying to send this, I get:
$ hg update 356d27775359 $ hg phabsend .^ . D11766 - updated - 48486:e53ef79cd9d5 "sparse: demonstrate a bug when used with safe-share" abort: Conduit Error (ERR-CONDUIT-CORE): Graph cycle detected (type=5, cycle=PHID-DREV-z7jbc5yf2jun6v2pbnqj, PHID-DREV-z7jbc5yf2jun6v2pbnqj). EXIT STATUS 255
@Alphare, I re-created the commit and was able to make a phabricator revision https://phab.mercurial-scm.org/D11817.
I took the liberty of assigning this as the parent of D11817 as if you did the phabsend of the range, this way it's more obvious for other reviewers/archival reasons. You can see the stack tab appeared