perf: optimize LID comparison in iterators by cheb0 · Pull Request #358 · ozontech/seq-db

cheb0 · 2026-02-17T07:26:29Z

Description

Adds a zero-cost comparison for LIDs in iterators, unblocks NextGEQ (need fast comparisons and min function for NextGEQ to be effective)

Details

Instead of calling the n.less comparator, we introduce a new type which hides all comparison logic. It's a struct node.LID (name can be changed).

Struct size is 64 bits. For default order (desc) we keep two fields:
lid: LID (32 bits), XOR mask: 0 (32 bits)
For reverse (order asc) we keep:
lid: LID ^ 0xFFFFFFFFF (32 bits), mask: 0xFFFFFFFFF (32 bits)
To unpack a LID we just do lid ^ mask.

This makes masked LID value always go in ascending way (both orders). i.e. for default order (docs sort desc) LIDs remain unchanged, but for reverse odder (docs sort asc) higher LID values are transformed to lower values in lid field in LID struct. Therefore, nodes no longer need to maintain reverse flag and execute same code for both orders. We can also effieciently compare values via ordinary <. We can also support efficient min/max function.

Leaf nodes (IteratorDesc/Asc, staticAsc/Desc) return terminal values. For default order we return the last LID as MaxUint32, for reverse order it's 0. Inversion makes both values equal (first 32 bits), we can always tell if it's null value just by comparing with MaxUint32.

Because null values are represented as MaxUint32 masked lid, we can eliminate unneeded if checks. Previously we had:
n.hasLeft && n.less(n.leftID, n.rightID)
Now we can just:
leftID.Less(rightID)
Because null values are represented as MaxUint32, this if check will never pass if leftID is null.

The encoded LID value is yielded directly from eval tree (search) and passed right to agg tree, where it can also be effectively compared to different values.

Measurements

Fractions taken from prod:

service:large_service, count by k8_pod (hot, data cached)
master: ~470 ms
fast cmp: ~420 ms

service:small_service, count by k8_pod (hot, data cached)
master: ~400 ms
fast cmp: ~330ms

I have read and followed all requirements in CONTRIBUTING.md;
I used LLM/AI assistance to make this pull request;

cheb0 · 2026-02-17T07:29:22Z

@seqbenchbot up main search-logbench

github-actions · 2026-02-17T07:34:50Z

🔴 Performance Degradation

Some benchmarks have degraded compared to the previous run.
Click on Show table button to see full list of degraded benchmarks.

Show table

Name	Previous	Current	Ratio	Verdict
`FindSequence_Random/small-4`	`b369fc`	`05d8ea`
	`4974.22 MB/s`	`4303.93 MB/s`	`0.87`	`🔴`

codecov-commenter · 2026-02-18T09:01:43Z

Codecov Report

❌ Patch coverage is 96.15385% with 5 lines in your changes missing coverage. Please review.
✅ Project coverage is 71.44%. Comparing base (158eee6) to head (8c12ab3).
⚠️ Report is 4 commits behind head on main.

Files with missing lines	Patch %	Lines
node/lid.go	84.00%	4 Missing ⚠️
frac/processor/search.go	50.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #358      +/-   ##
==========================================
- Coverage   71.51%   71.44%   -0.08%     
==========================================
  Files         205      205              
  Lines       14872    14921      +49     
==========================================
+ Hits        10636    10660      +24     
- Misses       3468     3486      +18     
- Partials      768      775       +7

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

github-actions · 2026-03-02T06:06:49Z

🔴 Performance Degradation

Some benchmarks have degraded compared to the previous run.
Click on Show table button to see full list of degraded benchmarks.

Show table

Name	Previous	Current	Ratio	Verdict
`AggDeep/size=1000-4`	`8aefcc`	`16a906`
	`4817.00 ns/op`	`5463.00 ns/op`	`1.13`	`🔴`
`AggDeep/size=1000000-4`	`8aefcc`	`16a906`
	`4837044.00 ns/op`	`5560985.00 ns/op`	`1.15`	`🔴`
`AggWide/size=10000-4`	`8aefcc`	`16a906`
	`47761.00 ns/op`	`54451.00 ns/op`	`1.14`	`🔴`
`AggWide/size=1000000-4`	`8aefcc`	`16a906`
	`516.00 B/op`	`580.00 B/op`	`1.12`	`🔴`
	`5419714.00 ns/op`	`6230424.00 ns/op`	`1.15`	`🔴`
`FindSequence_Random/medium-4`	`8aefcc`	`16a906`
	`10747.09 MB/s`	`9189.63 MB/s`	`0.86`	`🔴`
	`99.33 ns/op`	`111.40 ns/op`	`1.12`	`🔴`
`FindSequence_Random/small-4`	`8aefcc`	`16a906`
	`6638.44 MB/s`	`4563.10 MB/s`	`0.69`	`🔴`
	`46.45 ns/op`	`56.10 ns/op`	`1.21`	`🔴`

forshev · 2026-03-02T13:12:58Z

frac/fraction_test.go

 			withAggQuery(processor.AggQuery{GroupBy: aggField("level")})),
 		[]map[string]uint64{
-			{"gateway": 3, "proxy": 2, "scheduler": 1},
+			{gateway: 3, proxy: 2, "scheduler": 1},


nit: use const scheduler here as well

forshev · 2026-03-02T13:55:53Z

node/lid.go

+}
+
+func (c LID) Eq(other LID) bool {
+	return c.lid == other.lid


nit: is it possible scenario when user of this method compares asc lid and desc lid? at first glance looks like no. however, do we need to take order into account here and check mask?

for example

descLid := NewLIDOrderDesc(5) ascLid := NewLIDOrderAsc(math.MaxUint32 - 5) descLid.Eq(ascLid) // produces true now

forshev · 2026-03-02T14:29:03Z

node/lid.go

+}
+
+// Less compares two values. It also does an implicit null check, since we store math.MaxUint32 for null values.
+// Which means if we call x.Less(y), then we now for sure that x is not null. Therefore, this Less call can work


nit: then we know for sure?

forshev · 2026-03-02T14:33:19Z

node/node_and.go

 			n.readLeft()
 		}
-		for n.hasLeft && n.hasRight && n.less(n.rightID, n.leftID) {
+		for !n.rightID.IsNull() && n.rightID.Less(n.leftID) {


nit: should it be !n.leftID.IsNull() && n.rightID.Less(n.leftID) so we check both ids for null?

forshev · 2026-03-02T14:42:46Z

node/lid.go

+// For reverse order LID is inverted as follows: "MaxUint32 - LID" formula using XOR mask. Terminal LID value is 0 instead
+// of MaxUint32 in reverse order, but 0 is XORed to MaxUint32. Which means, null value will always have lid field set to
+// 0xFFFFFFFF (math.MaxUint32) regardless of reverse (order) flag.
+type LID struct {


nit: maybe ComparableLID? a bit longer but gives more context imo

cheb0 · 2026-03-03T16:11:48Z

@seqbenchbot up main search-logbench --skip-bulk-comparison

seqbenchbot · 2026-03-03T16:11:51Z

Oh-oh, @cheb0 ('>o.o)'>!

Something went wrong and I couldn't process your request.
Please take a closer look at error message:

unknown flag --skip-bulk-comparison

cheb0 · 2026-03-03T16:32:23Z

@seqbenchbot up main search-logbench --skip-bulk-comparison

seqbenchbot · 2026-03-03T16:32:26Z

Nice, @cheb0 <(-^,^-)=b!

Your request was successfully served.
Identificator for your ongoing benchmark - 645dce7d.

Here is a list of helpful links:

Take a look at Grafana dashboard;
Live-tailing logs are also available;

Have a great time!

seqbenchbot · 2026-03-03T17:07:41Z

Nice, @cheb0 <(-^,^-)=b!

The benchmark with identificator 645dce7d was finished.
I've prepared a summary for you. Click on Show summary button to see it:

Show summary

Query	Type	`mean (ms)`			`stddev (ms)`			`p(50) (ms)`			`p(95) (ms)`			`p(99) (ms)`			`iterations`
Query	Type	base	comp	diff	base	comp	diff	base	comp	diff	base	comp	diff	base	comp	diff	base	comp	diff
`service:* \| group by (10s) \| count`	cold	`3049.20`	`2807.20`	`-7.94%`	`525.42`	`322.72`	`-38.58%`	`2729.00`	`2795.50`	`+2.44%`	`3582.50`	`3069.00`	`-14.33%`	`3582.50`	`3069.00`	`-14.33%`	`5.00`	`5.00`	`0.00%`
`service:* \| group by (10s) \| count`	warm	`395.88`	`336.12`	`-15.10%`	`47.87`	`44.20`	`-7.66%`	`378.50`	`331.00`	`-12.55%`	`483.00`	`410.50`	`-15.01%`	`509.00`	`437.00`	`-14.15%`	`25.00`	`25.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND message:"this error doesn't exist, do not try to find it" AND level:[0 to 3]`	cold	`739.80`	`679.20`	`-8.19%`	`91.35`	`68.77`	`-24.72%`	`682.00`	`663.50`	`-2.71%`	`832.50`	`742.50`	`-10.81%`	`832.50`	`742.50`	`-10.81%`	`5.00`	`5.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND message:"this error doesn't exist, do not try to find it" AND level:[0 to 3]`	warm	`4.44`	`4.76`	`+7.21%`	`0.65`	`1.09`	`+67.66%`	`4.00`	`4.00`	`0.00%`	`5.50`	`7.00`	`+27.27%`	`6.00`	`7.00`	`+16.67%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-us AND level:[0 to 3]`	cold	`126.00`	`112.20`	`-10.95%`	`63.62`	`34.71`	`-45.44%`	`99.00`	`93.00`	`-6.06%`	`173.00`	`144.00`	`-16.76%`	`173.00`	`144.00`	`-16.76%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-us AND level:[0 to 3]`	warm	`4.24`	`4.12`	`-2.83%`	`0.52`	`0.53`	`+0.61%`	`4.00`	`4.00`	`0.00%`	`5.00`	`5.00`	`0.00%`	`5.00`	`5.00`	`0.00%`	`25.00`	`25.00`	`0.00%`
`service:* \| group by (k8s_pod) \| count`	cold	`2054.20`	`1841.60`	`-10.35%`	`140.55`	`155.02`	`+10.29%`	`1978.00`	`1777.00`	`-10.16%`	`2200.50`	`1979.50`	`-10.04%`	`2200.50`	`1979.50`	`-10.04%`	`5.00`	`5.00`	`0.00%`
`service:* \| group by (k8s_pod) \| count`	warm	`901.48`	`737.04`	`-18.24%`	`74.97`	`55.44`	`-26.05%`	`881.00`	`730.00`	`-17.14%`	`1006.00`	`846.00`	`-15.90%`	`1052.50`	`855.00`	`-18.76%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-eu \| group by (k8s_pod) \| count`	cold	`1052.20`	`981.40`	`-6.73%`	`179.83`	`109.62`	`-39.04%`	`971.00`	`933.00`	`-3.91%`	`1191.00`	`1069.50`	`-10.20%`	`1191.00`	`1069.50`	`-10.20%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-eu \| group by (k8s_pod) \| count`	warm	`329.96`	`284.20`	`-13.87%`	`25.58`	`30.23`	`+18.17%`	`325.00`	`277.50`	`-14.62%`	`369.00`	`332.00`	`-10.03%`	`386.50`	`344.50`	`-10.87%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-eu \| group by (k8s_pod, 10s) \| min(level)`	cold	`3203.00`	`3102.00`	`-3.15%`	`392.04`	`530.85`	`+35.41%`	`3056.00`	`2764.00`	`-9.55%`	`3562.50`	`3667.00`	`+2.93%`	`3562.50`	`3667.00`	`+2.93%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-eu \| group by (k8s_pod, 10s) \| min(level)`	warm	`487.52`	`423.24`	`-13.19%`	`43.71`	`36.66`	`-16.13%`	`467.00`	`415.50`	`-11.03%`	`565.50`	`487.00`	`-13.88%`	`583.00`	`497.00`	`-14.75%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-eu \| group by (1s) \| count`	cold	`2358.00`	`2325.00`	`-1.40%`	`212.13`	`502.04`	`+136.66%`	`2270.00`	`2071.50`	`-8.74%`	`2558.00`	`2822.00`	`+10.32%`	`2558.00`	`2822.00`	`+10.32%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-eu \| group by (1s) \| count`	warm	`62.88`	`66.48`	`+5.73%`	`13.57`	`12.85`	`-5.28%`	`66.00`	`73.50`	`+11.36%`	`78.00`	`77.50`	`-0.64%`	`78.50`	`78.50`	`0.00%`	`25.00`	`25.00`	`0.00%`
`k8s_pod:payment-* \| group by (10s) \| count`	cold	`2921.80`	`2860.80`	`-2.09%`	`262.72`	`1442.25`	`+448.97%`	`2767.00`	`2196.50`	`-20.62%`	`3174.50`	`3923.50`	`+23.59%`	`3174.50`	`3923.50`	`+23.59%`	`5.00`	`5.00`	`0.00%`
`k8s_pod:payment-* \| group by (10s) \| count`	warm	`365.08`	`284.08`	`-22.19%`	`33.40`	`33.67`	`+0.82%`	`354.00`	`275.00`	`-22.32%`	`431.00`	`332.50`	`-22.85%`	`436.00`	`354.50`	`-18.69%`	`25.00`	`25.00`	`0.00%`
`service:api-gateway-us \| group by (method) \| avg(size)`	cold	`3246.60`	`3337.00`	`+2.78%`	`119.04`	`212.72`	`+78.69%`	`3224.00`	`3287.00`	`+1.95%`	`3345.50`	`3539.00`	`+5.78%`	`3345.50`	`3539.00`	`+5.78%`	`5.00`	`5.00`	`0.00%`
`service:api-gateway-us \| group by (method) \| avg(size)`	warm	`1917.60`	`1890.48`	`-1.41%`	`37.84`	`37.45`	`-1.02%`	`1909.00`	`1878.50`	`-1.60%`	`1968.00`	`1952.00`	`-0.81%`	`2001.00`	`1977.00`	`-1.20%`	`25.00`	`25.00`	`0.00%`
`k8s_namespace:prod AND level:[0 to 3] \| group by (15s) \| count`	cold	`2570.60`	`2155.00`	`-16.17%`	`787.33`	`274.03`	`-65.19%`	`2111.00`	`2096.50`	`-0.69%`	`3298.00`	`2388.00`	`-27.59%`	`3298.00`	`2388.00`	`-27.59%`	`5.00`	`5.00`	`0.00%`
`k8s_namespace:prod AND level:[0 to 3] \| group by (15s) \| count`	warm	`116.20`	`106.08`	`-8.71%`	`19.92`	`14.29`	`-28.29%`	`121.50`	`106.00`	`-12.76%`	`145.00`	`130.00`	`-10.34%`	`148.00`	`130.50`	`-11.82%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-eu \| group by (k8s_pod) \| min(level)`	cold	`1423.00`	`1256.00`	`-11.74%`	`160.24`	`102.27`	`-36.18%`	`1341.50`	`1195.50`	`-10.88%`	`1583.00`	`1361.00`	`-14.02%`	`1583.00`	`1361.00`	`-14.02%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-eu \| group by (k8s_pod) \| min(level)`	warm	`454.04`	`374.44`	`-17.53%`	`35.70`	`29.23`	`-18.13%`	`441.50`	`375.00`	`-15.06%`	`515.50`	`418.50`	`-18.82%`	`531.50`	`426.50`	`-19.76%`	`25.00`	`25.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND transaction_id:'needle'`	cold	`1187.40`	`1162.20`	`-2.12%`	`88.06`	`152.73`	`+73.44%`	`1160.00`	`1106.50`	`-4.61%`	`1268.00`	`1294.50`	`+2.09%`	`1268.00`	`1294.50`	`+2.09%`	`5.00`	`5.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND transaction_id:'needle'`	warm	`113.28`	`109.08`	`-3.71%`	`15.50`	`15.07`	`-2.79%`	`116.00`	`107.00`	`-7.76%`	`134.00`	`133.00`	`-0.75%`	`137.00`	`140.50`	`+2.55%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-eu AND level:[0 to 3] \| group by (10s) \| count`	cold	`2318.20`	`2277.40`	`-1.76%`	`273.60`	`333.42`	`+21.86%`	`2206.00`	`2092.50`	`-5.15%`	`2549.00`	`2610.00`	`+2.39%`	`2549.00`	`2610.00`	`+2.39%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-eu AND level:[0 to 3] \| group by (10s) \| count`	warm	`63.72`	`56.68`	`-11.05%`	`10.57`	`12.87`	`+21.72%`	`67.50`	`59.50`	`-11.85%`	`74.00`	`70.50`	`-4.73%`	`75.00`	`71.50`	`-4.67%`	`25.00`	`25.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND transaction_id:'tx-needle-*'`	cold	`631.80`	`592.20`	`-6.27%`	`77.55`	`67.82`	`-12.55%`	`620.50`	`570.50`	`-8.06%`	`701.50`	`642.50`	`-8.41%`	`701.50`	`642.50`	`-8.41%`	`5.00`	`5.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND transaction_id:'tx-needle-*'`	warm	`13.64`	`11.40`	`-16.42%`	`1.44`	`1.00`	`-30.55%`	`13.00`	`11.00`	`-15.38%`	`15.50`	`13.00`	`-16.13%`	`17.50`	`14.00`	`-20.00%`	`25.00`	`25.00`	`0.00%`
`service:api-gateway-us AND method:'GET' AND status:200 AND size:[990 TO *] AND resource:'/assets/css/bootstrap.css'`	cold	`379.40`	`369.80`	`-2.53%`	`63.24`	`49.17`	`-22.25%`	`356.00`	`355.00`	`-0.28%`	`441.50`	`413.50`	`-6.34%`	`441.50`	`413.50`	`-6.34%`	`5.00`	`5.00`	`0.00%`
`service:api-gateway-us AND method:'GET' AND status:200 AND size:[990 TO *] AND resource:'/assets/css/bootstrap.css'`	warm	`94.76`	`86.76`	`-8.44%`	`8.47`	`7.62`	`-9.97%`	`94.50`	`86.00`	`-8.99%`	`108.00`	`97.00`	`-10.19%`	`110.00`	`102.00`	`-7.27%`	`25.00`	`25.00`	`0.00%`
`service:api-gateway-us \| group by (method) \| avg(size)`	cold	`3277.20`	`3337.00`	`+1.82%`	`135.97`	`212.72`	`+56.44%`	`3236.50`	`3287.00`	`+1.56%`	`3398.50`	`3539.00`	`+4.13%`	`3398.50`	`3539.00`	`+4.13%`	`5.00`	`5.00`	`0.00%`
`service:api-gateway-us \| group by (method) \| avg(size)`	warm	`1903.72`	`1890.48`	`-0.70%`	`40.04`	`37.45`	`-6.47%`	`1897.50`	`1878.50`	`-1.00%`	`1964.50`	`1952.00`	`-0.64%`	`2006.00`	`1977.00`	`-1.45%`	`25.00`	`25.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND level:[3 to 7] AND NOT message:'health check' AND NOT message:'payment authorized'`	cold	`75.20`	`71.20`	`-5.32%`	`5.81`	`7.19`	`+23.86%`	`75.50`	`69.50`	`-7.95%`	`79.50`	`77.50`	`-2.52%`	`79.50`	`77.50`	`-2.52%`	`5.00`	`5.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND level:[3 to 7] AND NOT message:'health check' AND NOT message:'payment authorized'`	warm	`4.12`	`4.60`	`+11.65%`	`0.67`	`2.22`	`+233.02%`	`4.00`	`4.00`	`0.00%`	`5.50`	`5.00`	`-9.09%`	`6.00`	`10.00`	`+66.67%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-us AND NOT message:'payment authorization failed' AND NOT message:'authentication failed' AND NOT message:'payment gateway timeout'`	cold	`85.00`	`74.60`	`-12.24%`	`9.75`	`25.26`	`+159.21%`	`84.00`	`62.00`	`-26.19%`	`93.50`	`97.50`	`+4.28%`	`93.50`	`97.50`	`+4.28%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-us AND NOT message:'payment authorization failed' AND NOT message:'authentication failed' AND NOT message:'payment gateway timeout'`	warm	`3.76`	`4.04`	`+7.45%`	`0.52`	`0.54`	`+3.00%`	`4.00`	`4.00`	`0.00%`	`4.00`	`4.50`	`+12.50%`	`4.50`	`5.50`	`+22.22%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-eu \| group by (k8s_pod, 10s) \| count`	cold	`2954.00`	`2592.00`	`-12.25%`	`336.08`	`416.88`	`+24.04%`	`2838.00`	`2497.50`	`-12.00%`	`3221.50`	`2917.00`	`-9.45%`	`3221.50`	`2917.00`	`-9.45%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-eu \| group by (k8s_pod, 10s) \| count`	warm	`371.56`	`319.12`	`-14.11%`	`34.89`	`32.05`	`-8.15%`	`366.50`	`319.00`	`-12.96%`	`423.50`	`365.50`	`-13.70%`	`451.00`	`386.50`	`-14.30%`	`25.00`	`25.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND transaction_id:'tx-needle-0000'`	cold	`407.20`	`446.60`	`+9.68%`	`12.52`	`83.49`	`+566.99%`	`404.50`	`419.50`	`+3.71%`	`419.00`	`517.50`	`+23.51%`	`419.00`	`517.50`	`+23.51%`	`5.00`	`5.00`	`0.00%`
`k8s_pod:payment-backend-us-* AND transaction_id:'tx-needle-0000'`	warm	`3.92`	`3.68`	`-6.12%`	`1.00`	`0.56`	`-44.14%`	`4.00`	`4.00`	`0.00%`	`5.50`	`4.00`	`-27.27%`	`6.50`	`4.50`	`-30.77%`	`25.00`	`25.00`	`0.00%`
`service:payment-backend-us`	cold	`48.60`	`53.80`	`+10.70%`	`14.59`	`27.68`	`+89.75%`	`40.50`	`39.50`	`-2.47%`	`61.00`	`77.00`	`+26.23%`	`61.00`	`77.00`	`+26.23%`	`5.00`	`5.00`	`0.00%`
`service:payment-backend-us`	warm	`3.84`	`3.88`	`+1.04%`	`0.69`	`0.93`	`+34.79%`	`4.00`	`4.00`	`0.00%`	`5.00`	`5.50`	`+10.00%`	`5.00`	`6.00`	`+20.00%`	`25.00`	`25.00`	`0.00%`

Have a great time!

fast lid representation for optimized comparison

6b42af1

add tests

c4d671e

cheb0 changed the title ~~perf: fast lid representation for optimized comparison in iterators~~ perf: new lid representation for optimized comparison in iterators Feb 17, 2026

cheb0 marked this pull request as draft February 17, 2026 13:26

remove reverse flag from node_range.go, delete unneeded null checks

ad98152

ozontech deleted a comment from seqbenchbot Feb 18, 2026

cheb0 changed the title ~~perf: new lid representation for optimized comparison in iterators~~ perf: new lid representation for efficient comparison in iterators Feb 18, 2026

cheb0 marked this pull request as ready for review February 18, 2026 07:02

cheb0 added 2 commits February 18, 2026 11:11

Merge branch 'refs/heads/main' into 0-fast-cmp-xor

6d5bbab

Merge branch 'refs/heads/main' into 0-fast-cmp-xor

5288d49

cheb0 changed the title ~~perf: new lid representation for efficient comparison in iterators~~ perf: implement new LID representation for efficient comparison in iterators Feb 18, 2026

cheb0 force-pushed the 0-fast-cmp-xor branch from b47b8ee to ea92b83 Compare February 18, 2026 09:30

linter fixes

7de3263

cheb0 force-pushed the 0-fast-cmp-xor branch from ea92b83 to 7de3263 Compare February 18, 2026 09:35

cheb0 changed the title ~~perf: implement new LID representation for efficient comparison in iterators~~ perf: optimize LID comparison in iterators Feb 20, 2026

cheb0 mentioned this pull request Feb 20, 2026

perf: implement NextGEQ #345

Open

2 tasks

cheb0 added 4 commits February 20, 2026 09:48

const masks

368d6c4

rename node.CmpLID => node.LID

08efdb7

rename node.CmpLID => node.LID

6035a9c

rename node.CmpLID => node.LID (filename)

8c12ab3

ozontech deleted a comment from github-actions bot Mar 2, 2026

eguguchkin added this to the v0.69.0 milestone Mar 2, 2026

eguguchkin requested review from dkharms, eguguchkin and forshev and removed request for dkharms March 2, 2026 10:29

forshev approved these changes Mar 2, 2026

View reviewed changes

ozontech deleted a comment from seqbenchbot Mar 3, 2026

Conversation

cheb0 commented Feb 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Details

Measurements

Uh oh!

cheb0 commented Feb 17, 2026

Uh oh!

github-actions bot commented Feb 17, 2026

🔴 Performance Degradation

Uh oh!

codecov-commenter commented Feb 18, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

github-actions bot commented Mar 2, 2026

🔴 Performance Degradation

Uh oh!

forshev Mar 2, 2026

Choose a reason for hiding this comment

Uh oh!

forshev Mar 2, 2026

Choose a reason for hiding this comment

Uh oh!

forshev Mar 2, 2026

Choose a reason for hiding this comment

Uh oh!

forshev Mar 2, 2026

Choose a reason for hiding this comment

Uh oh!

forshev Mar 2, 2026

Choose a reason for hiding this comment

Uh oh!

cheb0 commented Mar 3, 2026

Uh oh!

seqbenchbot commented Mar 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

cheb0 commented Mar 3, 2026

Uh oh!

seqbenchbot commented Mar 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

seqbenchbot commented Mar 3, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

cheb0 commented Feb 17, 2026 •

edited

Loading

codecov-commenter commented Feb 18, 2026 •

edited

Loading

seqbenchbot commented Mar 3, 2026 •

edited

Loading

seqbenchbot commented Mar 3, 2026 •

edited

Loading