Repository navigation
Conversation
jkaczman
force-pushed
the
jk-unnest-insert-split
branch
from
November 9, 2026 21:34
55d1328 to
58d7a9c
Compare
Contributor
|
Metal bench (arm64) failed. 76 of 475 measures outside bounds.
Counters per txn
Microbench: 386 of 462 measures within bounds. See verdict.json for the rest. Microbench latency: 1 benches changed more than 3%
Hot code per txn
pooler:
sharding-w2:
Logslb, microbench, pooler, sharding-w2, sharding-w8, verdict.json Compared fae0376 with 0b7e835 on c8g.metal-24xl (on-demand). |
Contributor
|
Metal bench (arm64) failed. build failed to run. LogsRan 58d7a9c on c8g.metal-24xl (on-demand). |
Contributor
|
Metal bench (x86) failed. 72 of 475 measures outside bounds.
Counters per txn
Microbench: 390 of 462 measures within bounds. See verdict.json for the rest. Microbench latency: 9 benches changed more than 3%
Hot code per txn
pooler:
sharding-w2:
Logslb, microbench, pooler, sharding-w2, sharding-w8, verdict.json Compared fae0376 with 0b7e835 on c7i.metal-48xl (on-demand). |
Contributor
|
Metal bench (x86) failed. build failed to run. LogsRan 58d7a9c on m7i.metal-48xl (spot). |
jkaczman
force-pushed
the
jk-unnest-insert-split
branch
3 times, most recently
from
November 9, 2026 21:55
631fb17 to
939a0dd
Compare
Codecov Report❌ Patch coverage is 📢 Thoughts on this report? Let us know! |
jkaczman
force-pushed
the
jk-unnest-insert-split
branch
from
November 9, 2026 23:50
fae0376 to
ddcd6bc
Compare
jkaczman
force-pushed
the
jk-unnest-insert-split
branch
from
November 9, 2026 23:52
ddcd6bc to
45edc35
Compare
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds functionality to split
INSERT INTO <sharded table> .. SELECT * FROM unnest($1, ..)by how the rows from unnest resolve to Shards if split_inserts is set to rewriteE.g., if we have a statement such as
with
$1 = {1,2,3,4}and$2 = {a,b,c,d}, Postgres inserts the rows(1, a),(2, b),(3, c)and(4, d).If we get one of these INSERTs, we split the INSERT by shard, as follows:
int8frompg_catalog._int8).$1 = {1,3}and$2 = {a,c}, and Shard B will get$1 = {2,4}and$2 = {b,d}.Otherwise notable:
SELECT * FROM unnest(..)where all arguments are parameters with a cast to an array type that we can decode (e.g.,_bool,_int2,_int4,_int8...) without any clauses (e.g., LIMIT) present.Router::querycall per row), which is slow for large arrays. We could compute the shards of the rows from the array of the sharding key directly instead.