Remove redundant Mutex from SharedMemoryReservation

[Dandandan]

Which issue does this PR close?

Rationale for this change

SharedMemoryReservation was defined as Arc<Mutex<MemoryReservation>>, but MemoryReservation is already internally thread-safe:

• Its size field uses AtomicUsize with atomic fetch_update/fetch_add/fetch_sub
• The underlying MemoryPool implementations (GreedyMemoryPool, FairSpillPool, UnboundedMemoryPool) all handle their own internal locking/atomics

The outer Mutex was therefore redundant and caused unnecessary lock contention. In the repartition operator specifically, this lock was acquired on every batch by every input partition (sender) plus the output partition (receiver), making it a serialization bottleneck that reduced CPU utilization during parallel query execution.

What changes are included in this PR?

• Changed SharedMemoryReservation type alias from Arc<Mutex<MemoryReservation>> to Arc<MemoryReservation>
• Removed .lock() calls at all usage sites (repartition operator and symmetric hash join)
• Removed unused parking_lot::Mutex imports

Are these changes tested?

Covered by existing tests — no behavioral change, only removal of redundant synchronization. All existing repartition and symmetric hash join tests continue to pass.

Are there any user-facing changes?

No. SharedMemoryReservation is pub(crate).

🤖 Generated with Claude Code

[Dandandan]

run benchmarks

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4260942677-1369-8k65s 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing remove-shared-memory-reservation-mutex (3bf05f8) to 5c653be (merge-base) diff using: tpcds
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4260942677-1368-454vc 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing remove-shared-memory-reservation-mutex (3bf05f8) to 5c653be (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4260942677-1370-7l9hn 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing remove-shared-memory-reservation-mutex (3bf05f8) to 5c653be (merge-base) diff using: tpch
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Details

Comparing HEAD and remove-shared-memory-reservation-mutex
--------------------
Benchmark tpcds_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                     HEAD ┃   remove-shared-memory-reservation-mutex ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │              6.67 / 7.19 ±0.79 / 8.77 ms │              6.72 / 7.24 ±0.80 / 8.85 ms │     no change │
│ QQuery 2  │        144.08 / 145.59 ±1.08 / 146.92 ms │        146.23 / 147.53 ±1.09 / 148.88 ms │     no change │
│ QQuery 3  │        114.01 / 114.75 ±0.56 / 115.42 ms │        114.67 / 115.80 ±0.62 / 116.57 ms │     no change │
│ QQuery 4  │    1339.82 / 1389.13 ±26.27 / 1413.52 ms │    1341.50 / 1376.01 ±17.59 / 1388.41 ms │     no change │
│ QQuery 5  │        172.68 / 174.72 ±2.82 / 180.25 ms │        172.87 / 174.16 ±0.66 / 174.68 ms │     no change │
│ QQuery 6  │       858.32 / 879.62 ±24.45 / 922.78 ms │       848.72 / 861.94 ±11.79 / 877.14 ms │     no change │
│ QQuery 7  │        343.61 / 346.91 ±3.66 / 352.38 ms │        342.18 / 344.48 ±1.28 / 345.99 ms │     no change │
│ QQuery 8  │        116.22 / 118.20 ±1.37 / 120.53 ms │        115.90 / 117.51 ±1.05 / 119.03 ms │     no change │
│ QQuery 9  │        105.41 / 108.88 ±3.27 / 115.08 ms │       101.84 / 111.34 ±12.04 / 135.11 ms │     no change │
│ QQuery 10 │        106.30 / 108.04 ±1.34 / 110.32 ms │        106.60 / 107.83 ±0.95 / 108.80 ms │     no change │
│ QQuery 11 │        965.63 / 974.40 ±7.95 / 988.14 ms │        963.47 / 970.53 ±6.57 / 981.75 ms │     no change │
│ QQuery 12 │           45.11 / 46.09 ±0.59 / 46.83 ms │           44.44 / 46.92 ±1.93 / 49.91 ms │     no change │
│ QQuery 13 │        404.42 / 410.71 ±4.26 / 416.44 ms │        403.20 / 404.52 ±1.07 / 406.22 ms │     no change │
│ QQuery 14 │     1002.67 / 1016.56 ±9.27 / 1029.25 ms │     1009.14 / 1018.31 ±5.06 / 1023.58 ms │     no change │
│ QQuery 15 │           15.56 / 16.61 ±1.12 / 18.78 ms │           15.64 / 16.90 ±1.27 / 18.91 ms │     no change │
│ QQuery 16 │              7.26 / 7.78 ±0.58 / 8.85 ms │              7.63 / 7.93 ±0.46 / 8.85 ms │     no change │
│ QQuery 17 │        230.37 / 232.03 ±2.18 / 236.31 ms │        228.95 / 230.98 ±1.74 / 233.67 ms │     no change │
│ QQuery 18 │        127.12 / 129.89 ±1.76 / 132.40 ms │        126.35 / 127.57 ±0.72 / 128.41 ms │     no change │
│ QQuery 19 │        153.84 / 157.06 ±1.64 / 158.30 ms │        155.76 / 157.00 ±1.23 / 158.71 ms │     no change │
│ QQuery 20 │           14.05 / 14.59 ±0.44 / 15.29 ms │           14.00 / 15.01 ±0.98 / 16.83 ms │     no change │
│ QQuery 21 │           19.43 / 19.80 ±0.25 / 20.15 ms │           19.60 / 20.26 ±0.35 / 20.55 ms │     no change │
│ QQuery 22 │        487.25 / 492.54 ±4.80 / 499.64 ms │        489.58 / 494.52 ±4.24 / 499.31 ms │     no change │
│ QQuery 23 │        887.76 / 893.35 ±5.75 / 903.46 ms │        878.21 / 882.22 ±2.51 / 885.73 ms │     no change │
│ QQuery 24 │        383.64 / 386.90 ±3.89 / 394.46 ms │        384.78 / 390.15 ±3.49 / 395.33 ms │     no change │
│ QQuery 25 │        341.29 / 343.11 ±1.18 / 344.50 ms │        343.50 / 345.04 ±1.58 / 347.94 ms │     no change │
│ QQuery 26 │           80.02 / 81.21 ±0.89 / 82.36 ms │           80.25 / 82.67 ±1.28 / 83.94 ms │     no change │
│ QQuery 27 │              6.93 / 7.43 ±0.41 / 8.19 ms │              7.02 / 7.39 ±0.49 / 8.32 ms │     no change │
│ QQuery 28 │        150.49 / 151.54 ±0.92 / 152.96 ms │        149.24 / 150.39 ±1.14 / 152.12 ms │     no change │
│ QQuery 29 │        281.46 / 283.22 ±1.64 / 286.25 ms │        280.77 / 284.14 ±2.31 / 286.57 ms │     no change │
│ QQuery 30 │           42.70 / 46.03 ±1.94 / 48.12 ms │           43.61 / 44.93 ±0.96 / 46.60 ms │     no change │
│ QQuery 31 │        170.78 / 172.55 ±1.21 / 174.31 ms │        170.21 / 171.72 ±1.30 / 173.81 ms │     no change │
│ QQuery 32 │           56.27 / 57.33 ±1.04 / 59.31 ms │           56.08 / 56.87 ±1.09 / 59.02 ms │     no change │
│ QQuery 33 │        140.32 / 142.57 ±1.98 / 146.04 ms │        140.99 / 144.12 ±1.82 / 146.42 ms │     no change │
│ QQuery 34 │              7.05 / 7.30 ±0.23 / 7.69 ms │              6.90 / 7.15 ±0.28 / 7.67 ms │     no change │
│ QQuery 35 │        107.15 / 108.35 ±0.95 / 109.70 ms │        104.50 / 107.71 ±1.79 / 109.63 ms │     no change │
│ QQuery 36 │              6.66 / 6.85 ±0.18 / 7.17 ms │              6.85 / 7.04 ±0.22 / 7.46 ms │     no change │
│ QQuery 37 │              8.82 / 8.99 ±0.10 / 9.10 ms │             8.34 / 9.05 ±0.76 / 10.48 ms │     no change │
│ QQuery 38 │           84.70 / 87.32 ±3.10 / 93.24 ms │           84.94 / 88.14 ±3.42 / 94.26 ms │     no change │
│ QQuery 39 │        126.98 / 129.56 ±1.98 / 132.64 ms │        127.92 / 130.26 ±1.59 / 132.14 ms │     no change │
│ QQuery 40 │        108.22 / 114.69 ±6.76 / 127.42 ms │        110.42 / 116.40 ±7.05 / 129.70 ms │     no change │
│ QQuery 41 │           14.99 / 16.30 ±1.02 / 17.73 ms │           14.62 / 15.63 ±0.81 / 16.98 ms │     no change │
│ QQuery 42 │        107.94 / 109.94 ±1.69 / 111.87 ms │        107.41 / 109.33 ±1.05 / 110.53 ms │     no change │
│ QQuery 43 │              5.95 / 6.16 ±0.20 / 6.54 ms │              6.10 / 6.28 ±0.11 / 6.41 ms │     no change │
│ QQuery 44 │           11.75 / 12.22 ±0.49 / 13.16 ms │           11.90 / 12.74 ±0.98 / 14.64 ms │     no change │
│ QQuery 45 │           51.19 / 51.43 ±0.26 / 51.93 ms │           51.15 / 51.70 ±0.38 / 52.10 ms │     no change │
│ QQuery 46 │              8.63 / 8.85 ±0.16 / 9.00 ms │              8.63 / 8.81 ±0.19 / 9.08 ms │     no change │
│ QQuery 47 │        720.40 / 730.53 ±9.32 / 747.01 ms │        724.93 / 730.59 ±5.66 / 740.72 ms │     no change │
│ QQuery 48 │        285.84 / 291.81 ±3.58 / 296.03 ms │        286.09 / 290.83 ±3.11 / 295.74 ms │     no change │
│ QQuery 49 │        251.54 / 254.60 ±1.63 / 256.38 ms │        251.75 / 254.61 ±2.10 / 258.15 ms │     no change │
│ QQuery 50 │        225.21 / 229.94 ±3.84 / 236.64 ms │        220.26 / 229.82 ±5.61 / 236.12 ms │     no change │
│ QQuery 51 │        180.11 / 183.66 ±2.13 / 186.29 ms │        180.85 / 183.03 ±2.33 / 186.48 ms │     no change │
│ QQuery 52 │        107.56 / 108.84 ±1.05 / 110.51 ms │        107.39 / 109.53 ±1.74 / 112.14 ms │     no change │
│ QQuery 53 │        101.90 / 103.23 ±0.88 / 104.66 ms │        102.73 / 103.98 ±0.84 / 104.86 ms │     no change │
│ QQuery 54 │        147.25 / 149.74 ±1.66 / 151.58 ms │        146.51 / 147.11 ±0.48 / 147.67 ms │     no change │
│ QQuery 55 │        106.82 / 108.05 ±0.97 / 109.26 ms │        107.39 / 108.75 ±1.69 / 111.79 ms │     no change │
│ QQuery 56 │        140.66 / 141.41 ±0.71 / 142.42 ms │        141.25 / 141.64 ±0.53 / 142.67 ms │     no change │
│ QQuery 57 │        173.18 / 175.87 ±2.08 / 178.23 ms │        173.53 / 175.11 ±1.68 / 178.08 ms │     no change │
│ QQuery 58 │        305.43 / 314.80 ±8.20 / 329.11 ms │        291.36 / 299.32 ±9.16 / 317.10 ms │     no change │
│ QQuery 59 │        199.06 / 200.51 ±0.97 / 201.83 ms │        197.21 / 199.69 ±1.79 / 202.18 ms │     no change │
│ QQuery 60 │        143.65 / 144.63 ±0.90 / 146.15 ms │        143.32 / 145.24 ±1.72 / 147.48 ms │     no change │
│ QQuery 61 │           13.10 / 13.36 ±0.19 / 13.67 ms │           13.27 / 13.47 ±0.13 / 13.65 ms │     no change │
│ QQuery 62 │       912.77 / 939.64 ±19.43 / 972.46 ms │       901.21 / 935.99 ±26.55 / 982.58 ms │     no change │
│ QQuery 63 │        103.23 / 107.19 ±4.14 / 114.79 ms │        104.78 / 106.26 ±1.12 / 107.60 ms │     no change │
│ QQuery 64 │        683.15 / 691.68 ±4.84 / 696.80 ms │        687.61 / 690.93 ±2.72 / 694.24 ms │     no change │
│ QQuery 65 │        253.38 / 257.71 ±2.92 / 261.54 ms │        253.96 / 260.59 ±4.34 / 267.38 ms │     no change │
│ QQuery 66 │        251.57 / 264.34 ±9.41 / 276.54 ms │       229.31 / 255.49 ±17.71 / 277.97 ms │     no change │
│ QQuery 67 │        307.69 / 319.31 ±6.06 / 323.99 ms │        313.65 / 322.52 ±7.52 / 333.58 ms │     no change │
│ QQuery 68 │             8.76 / 9.78 ±0.57 / 10.34 ms │            8.87 / 11.44 ±2.06 / 13.31 ms │  1.17x slower │
│ QQuery 69 │        101.84 / 105.25 ±2.02 / 107.75 ms │        102.36 / 103.04 ±0.51 / 103.61 ms │     no change │
│ QQuery 70 │        343.02 / 351.24 ±9.93 / 370.69 ms │       344.02 / 356.53 ±10.54 / 371.76 ms │     no change │
│ QQuery 71 │        133.81 / 136.60 ±2.00 / 138.86 ms │        135.47 / 138.25 ±1.67 / 140.59 ms │     no change │
│ QQuery 72 │        607.99 / 619.61 ±7.80 / 627.90 ms │        617.80 / 622.63 ±4.21 / 628.40 ms │     no change │
│ QQuery 73 │              7.18 / 7.81 ±0.45 / 8.43 ms │              6.78 / 7.34 ±0.48 / 8.22 ms │ +1.06x faster │
│ QQuery 74 │        603.48 / 606.20 ±2.58 / 610.23 ms │        598.66 / 608.31 ±7.00 / 617.16 ms │     no change │
│ QQuery 75 │        275.67 / 278.45 ±2.27 / 282.35 ms │        276.74 / 280.00 ±3.11 / 285.13 ms │     no change │
│ QQuery 76 │        132.48 / 134.58 ±1.69 / 136.54 ms │        131.38 / 133.55 ±1.46 / 135.20 ms │     no change │
│ QQuery 77 │        188.75 / 190.14 ±1.03 / 191.38 ms │        190.26 / 192.90 ±2.48 / 196.04 ms │     no change │
│ QQuery 78 │        345.49 / 348.18 ±2.34 / 351.88 ms │        344.18 / 349.56 ±4.00 / 353.97 ms │     no change │
│ QQuery 79 │        237.01 / 239.20 ±2.27 / 243.58 ms │        233.10 / 236.90 ±2.47 / 239.52 ms │     no change │
│ QQuery 80 │        322.06 / 324.05 ±1.80 / 327.43 ms │        321.62 / 324.13 ±1.32 / 325.36 ms │     no change │
│ QQuery 81 │           26.49 / 29.17 ±1.97 / 31.34 ms │           26.29 / 27.96 ±1.12 / 29.35 ms │     no change │
│ QQuery 82 │        198.47 / 199.53 ±0.93 / 200.93 ms │        197.94 / 201.05 ±2.12 / 203.44 ms │     no change │
│ QQuery 83 │           38.90 / 39.89 ±1.18 / 42.19 ms │           38.55 / 39.72 ±0.92 / 41.37 ms │     no change │
│ QQuery 84 │           48.29 / 49.02 ±0.92 / 50.81 ms │           48.69 / 49.97 ±1.41 / 52.09 ms │     no change │
│ QQuery 85 │        148.19 / 149.63 ±1.25 / 151.23 ms │        147.55 / 148.70 ±0.92 / 149.63 ms │     no change │
│ QQuery 86 │           40.20 / 40.72 ±0.56 / 41.75 ms │           38.81 / 40.30 ±1.28 / 42.49 ms │     no change │
│ QQuery 87 │           86.98 / 89.52 ±2.26 / 93.51 ms │           86.01 / 88.17 ±2.63 / 93.21 ms │     no change │
│ QQuery 88 │         99.37 / 100.27 ±0.71 / 101.51 ms │        100.24 / 101.80 ±1.28 / 103.54 ms │     no change │
│ QQuery 89 │        117.83 / 119.61 ±1.51 / 121.75 ms │        121.53 / 122.20 ±0.56 / 122.88 ms │     no change │
│ QQuery 90 │           24.07 / 24.27 ±0.17 / 24.56 ms │           23.97 / 24.67 ±0.52 / 25.28 ms │     no change │
│ QQuery 91 │           61.66 / 63.77 ±1.14 / 64.78 ms │           63.92 / 64.69 ±0.52 / 65.30 ms │     no change │
│ QQuery 92 │           58.40 / 58.69 ±0.18 / 58.96 ms │           58.15 / 58.73 ±0.59 / 59.82 ms │     no change │
│ QQuery 93 │        186.87 / 188.90 ±1.58 / 191.55 ms │        188.45 / 189.47 ±0.67 / 190.41 ms │     no change │
│ QQuery 94 │           62.47 / 63.20 ±0.60 / 63.98 ms │           61.36 / 62.88 ±1.16 / 64.75 ms │     no change │
│ QQuery 95 │        129.19 / 130.48 ±0.88 / 131.57 ms │        128.49 / 129.39 ±0.54 / 129.91 ms │     no change │
│ QQuery 96 │           73.53 / 74.29 ±0.50 / 75.05 ms │           73.64 / 74.80 ±0.99 / 76.53 ms │     no change │
│ QQuery 97 │        125.64 / 126.87 ±0.93 / 128.31 ms │        124.68 / 127.89 ±2.53 / 132.30 ms │     no change │
│ QQuery 98 │        155.62 / 157.50 ±1.87 / 160.22 ms │        156.22 / 157.85 ±1.05 / 159.26 ms │     no change │
│ QQuery 99 │ 10789.15 / 10826.74 ±23.47 / 10861.60 ms │ 10785.59 / 10831.57 ±36.29 / 10882.63 ms │     no change │
└───────────┴──────────────────────────────────────────┴──────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 31758.34ms │
│ Total Time (remove-shared-memory-reservation-mutex)   │ 31715.07ms │
│ Average Time (HEAD)                                   │   320.79ms │
│ Average Time (remove-shared-memory-reservation-mutex) │   320.35ms │
│ Queries Faster                                        │          1 │
│ Queries Slower                                        │          1 │
│ Queries with No Change                                │         97 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

tpcds — base (merge-base)

Metric	Value
Wall time	159.1s
Peak memory	5.6 GiB
Avg memory	4.6 GiB
CPU user	261.8s
CPU sys	17.9s
Peak spill	0 B

tpcds — branch

Metric	Value
Wall time	158.9s
Peak memory	5.6 GiB
Avg memory	4.5 GiB
CPU user	261.4s
CPU sys	17.2s
Peak spill	0 B

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Details

Comparing HEAD and remove-shared-memory-reservation-mutex
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ remove-shared-memory-reservation-mutex ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.33 / 4.76 ±6.63 / 18.02 ms │           1.27 / 4.70 ±6.60 / 17.89 ms │     no change │
│ QQuery 1  │        15.02 / 15.52 ±0.25 / 15.71 ms │         15.42 / 15.79 ±0.22 / 16.11 ms │     no change │
│ QQuery 2  │        45.52 / 45.99 ±0.44 / 46.55 ms │         46.14 / 46.49 ±0.47 / 47.40 ms │     no change │
│ QQuery 3  │        45.89 / 46.74 ±0.76 / 47.85 ms │         45.31 / 47.98 ±2.17 / 51.33 ms │     no change │
│ QQuery 4  │     306.56 / 318.11 ±8.47 / 329.21 ms │      341.45 / 347.92 ±6.21 / 356.01 ms │  1.09x slower │
│ QQuery 5  │     341.92 / 350.67 ±6.09 / 360.45 ms │     339.45 / 351.70 ±10.89 / 370.98 ms │     no change │
│ QQuery 6  │          5.31 / 8.42 ±4.22 / 16.70 ms │            5.68 / 6.82 ±0.87 / 7.97 ms │ +1.24x faster │
│ QQuery 7  │        16.88 / 17.26 ±0.29 / 17.63 ms │         16.61 / 17.55 ±0.71 / 18.76 ms │     no change │
│ QQuery 8  │    406.24 / 424.64 ±14.82 / 450.63 ms │     416.79 / 434.17 ±15.52 / 454.86 ms │     no change │
│ QQuery 9  │    719.04 / 733.85 ±13.04 / 753.23 ms │     640.36 / 684.22 ±50.08 / 751.83 ms │ +1.07x faster │
│ QQuery 10 │       96.58 / 98.87 ±2.19 / 102.65 ms │        97.46 / 99.19 ±1.64 / 102.04 ms │     no change │
│ QQuery 11 │     110.51 / 112.30 ±1.22 / 114.07 ms │      109.82 / 110.60 ±0.58 / 111.54 ms │     no change │
│ QQuery 12 │    378.47 / 389.43 ±10.67 / 409.77 ms │      375.83 / 382.97 ±3.91 / 386.76 ms │     no change │
│ QQuery 13 │    456.35 / 475.19 ±22.49 / 517.92 ms │     520.62 / 541.06 ±19.07 / 576.02 ms │  1.14x slower │
│ QQuery 14 │     337.98 / 342.15 ±3.81 / 349.04 ms │      336.73 / 349.52 ±7.49 / 357.90 ms │     no change │
│ QQuery 15 │    348.52 / 368.02 ±23.39 / 413.91 ms │     356.50 / 369.20 ±13.87 / 391.39 ms │     no change │
│ QQuery 16 │    702.46 / 716.52 ±13.35 / 739.84 ms │     718.01 / 734.42 ±19.34 / 769.44 ms │     no change │
│ QQuery 17 │    702.37 / 726.82 ±26.09 / 773.19 ms │      714.61 / 717.36 ±1.74 / 720.09 ms │     no change │
│ QQuery 18 │ 1395.48 / 1521.47 ±82.92 / 1619.86 ms │  1428.47 / 1526.31 ±80.98 / 1671.73 ms │     no change │
│ QQuery 19 │        38.01 / 41.10 ±2.66 / 45.20 ms │         38.91 / 44.51 ±7.71 / 59.69 ms │  1.08x slower │
│ QQuery 20 │    720.91 / 758.18 ±27.80 / 804.65 ms │     742.46 / 759.65 ±14.06 / 783.51 ms │     no change │
│ QQuery 21 │     769.54 / 775.24 ±4.34 / 781.80 ms │      774.25 / 783.72 ±6.68 / 790.70 ms │     no change │
│ QQuery 22 │ 1128.97 / 1143.92 ±18.08 / 1178.07 ms │   1135.79 / 1139.30 ±2.59 / 1143.30 ms │     no change │
│ QQuery 23 │ 3141.29 / 3229.43 ±57.19 / 3310.92 ms │  3182.58 / 3249.13 ±58.50 / 3330.58 ms │     no change │
│ QQuery 24 │     102.53 / 103.75 ±1.42 / 106.01 ms │       98.07 / 102.98 ±3.89 / 109.20 ms │     no change │
│ QQuery 25 │     136.85 / 140.58 ±2.43 / 144.38 ms │      140.28 / 141.96 ±1.65 / 144.99 ms │     no change │
│ QQuery 26 │      99.66 / 102.24 ±2.05 / 104.77 ms │       96.99 / 100.67 ±2.30 / 103.98 ms │     no change │
│ QQuery 27 │     848.13 / 855.89 ±8.69 / 869.72 ms │      852.29 / 859.64 ±9.82 / 878.02 ms │     no change │
│ QQuery 28 │ 3266.91 / 3307.63 ±37.09 / 3359.95 ms │  3275.04 / 3315.72 ±37.64 / 3369.51 ms │     no change │
│ QQuery 29 │        49.89 / 55.65 ±6.27 / 67.41 ms │       52.82 / 97.90 ±52.56 / 188.78 ms │  1.76x slower │
│ QQuery 30 │     361.01 / 365.69 ±3.31 / 371.23 ms │      368.03 / 378.09 ±8.73 / 392.31 ms │     no change │
│ QQuery 31 │    378.61 / 396.92 ±14.50 / 415.44 ms │     390.11 / 432.61 ±26.36 / 465.45 ms │  1.09x slower │
│ QQuery 32 │ 1277.75 / 1392.72 ±67.48 / 1489.20 ms │  1307.47 / 1400.61 ±79.88 / 1539.80 ms │     no change │
│ QQuery 33 │ 1571.54 / 1615.11 ±33.33 / 1651.31 ms │  1530.84 / 1663.18 ±85.32 / 1747.90 ms │     no change │
│ QQuery 34 │ 1492.51 / 1532.32 ±41.84 / 1593.41 ms │  1509.34 / 1564.15 ±58.35 / 1669.36 ms │     no change │
│ QQuery 35 │     388.18 / 396.52 ±6.28 / 407.37 ms │      386.89 / 390.04 ±3.68 / 397.26 ms │     no change │
│ QQuery 36 │     123.30 / 125.75 ±2.55 / 129.81 ms │      120.39 / 122.42 ±1.46 / 124.75 ms │     no change │
│ QQuery 37 │        49.97 / 51.59 ±1.13 / 53.41 ms │         50.05 / 51.65 ±1.28 / 53.52 ms │     no change │
│ QQuery 38 │        76.49 / 78.63 ±1.63 / 80.88 ms │         77.15 / 79.27 ±1.62 / 81.33 ms │     no change │
│ QQuery 39 │     220.19 / 229.23 ±8.85 / 245.22 ms │      209.35 / 220.65 ±8.97 / 235.88 ms │     no change │
│ QQuery 40 │        25.58 / 27.78 ±1.26 / 29.02 ms │         25.49 / 27.33 ±1.56 / 29.77 ms │     no change │
│ QQuery 41 │        21.97 / 23.07 ±0.95 / 24.43 ms │         20.42 / 22.21 ±1.40 / 24.61 ms │     no change │
│ QQuery 42 │        21.35 / 21.64 ±0.28 / 22.14 ms │         21.66 / 22.30 ±0.69 / 23.63 ms │     no change │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 23487.31ms │
│ Total Time (remove-shared-memory-reservation-mutex)   │ 23757.61ms │
│ Average Time (HEAD)                                   │   546.22ms │
│ Average Time (remove-shared-memory-reservation-mutex) │   552.50ms │
│ Queries Faster                                        │          2 │
│ Queries Slower                                        │          5 │
│ Queries with No Change                                │         36 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric	Value
Wall time	118.6s
Peak memory	42.9 GiB
Avg memory	29.5 GiB
CPU user	1102.4s
CPU sys	101.9s
Peak spill	0 B

clickbench_partitioned — branch

Metric	Value
Wall time	119.9s
Peak memory	40.5 GiB
Avg memory	28.1 GiB
CPU user	1109.5s
CPU sys	109.7s
Peak spill	0 B

---

File an issue against this benchmark runner

[Dandandan]

run benchmark tpch_mem

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4261104766-1372-qmr75 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing remove-shared-memory-reservation-mutex (3bf05f8) to 5c653be (merge-base) diff using: tpch_mem
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Details

Comparing HEAD and remove-shared-memory-reservation-mutex
--------------------
Benchmark tpch_mem_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                             HEAD ┃ remove-shared-memory-reservation-mutex ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │   27.82 / 28.02 ±0.35 / 28.72 ms │         27.74 / 27.92 ±0.27 / 28.46 ms │     no change │
│ QQuery 2  │    9.99 / 10.23 ±0.20 / 10.56 ms │          9.87 / 10.07 ±0.24 / 10.54 ms │     no change │
│ QQuery 3  │   10.05 / 10.21 ±0.13 / 10.38 ms │           9.73 / 9.96 ±0.13 / 10.12 ms │     no change │
│ QQuery 4  │   15.17 / 15.87 ±1.10 / 18.06 ms │         14.91 / 15.96 ±1.38 / 18.69 ms │     no change │
│ QQuery 5  │   25.07 / 26.51 ±0.85 / 27.71 ms │         25.52 / 26.52 ±0.73 / 27.55 ms │     no change │
│ QQuery 6  │      6.52 / 6.69 ±0.19 / 7.03 ms │            6.34 / 6.53 ±0.22 / 6.94 ms │     no change │
│ QQuery 7  │   45.68 / 48.75 ±2.25 / 51.98 ms │         46.17 / 48.53 ±1.60 / 50.72 ms │     no change │
│ QQuery 8  │   13.28 / 14.00 ±0.49 / 14.76 ms │         12.89 / 13.21 ±0.27 / 13.69 ms │ +1.06x faster │
│ QQuery 9  │   28.39 / 29.84 ±1.32 / 31.92 ms │         28.62 / 29.64 ±0.96 / 31.39 ms │     no change │
│ QQuery 10 │   18.68 / 19.26 ±0.29 / 19.45 ms │         18.72 / 19.23 ±0.36 / 19.77 ms │     no change │
│ QQuery 11 │      5.54 / 5.80 ±0.23 / 6.20 ms │            5.50 / 5.72 ±0.22 / 6.13 ms │     no change │
│ QQuery 12 │   17.11 / 17.79 ±0.61 / 18.93 ms │         16.68 / 17.26 ±0.51 / 18.09 ms │     no change │
│ QQuery 13 │   14.33 / 14.60 ±0.17 / 14.87 ms │         13.91 / 14.65 ±0.47 / 15.19 ms │     no change │
│ QQuery 14 │      5.21 / 5.34 ±0.21 / 5.75 ms │            4.96 / 5.17 ±0.17 / 5.47 ms │     no change │
│ QQuery 15 │    9.95 / 10.17 ±0.24 / 10.58 ms │           9.82 / 9.98 ±0.13 / 10.18 ms │     no change │
│ QQuery 16 │    9.89 / 10.07 ±0.13 / 10.27 ms │          9.78 / 10.09 ±0.33 / 10.73 ms │     no change │
│ QQuery 17 │   38.59 / 39.00 ±0.34 / 39.42 ms │         39.20 / 39.77 ±0.50 / 40.67 ms │     no change │
│ QQuery 18 │   64.22 / 65.43 ±1.77 / 68.93 ms │         63.21 / 66.11 ±1.95 / 68.92 ms │     no change │
│ QQuery 19 │   13.88 / 14.56 ±0.63 / 15.38 ms │         13.56 / 14.31 ±0.70 / 15.50 ms │     no change │
│ QQuery 20 │   14.47 / 16.01 ±2.42 / 20.77 ms │         14.09 / 14.43 ±0.22 / 14.75 ms │ +1.11x faster │
│ QQuery 21 │ 96.79 / 101.54 ±6.80 / 114.94 ms │      105.40 / 108.85 ±4.37 / 117.38 ms │  1.07x slower │
│ QQuery 22 │      8.30 / 8.49 ±0.26 / 9.00 ms │            8.14 / 8.40 ±0.27 / 8.92 ms │     no change │
└───────────┴──────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃          ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 518.18ms │
│ Total Time (remove-shared-memory-reservation-mutex)   │ 522.33ms │
│ Average Time (HEAD)                                   │  23.55ms │
│ Average Time (remove-shared-memory-reservation-mutex) │  23.74ms │
│ Queries Faster                                        │        2 │
│ Queries Slower                                        │        1 │
│ Queries with No Change                                │       19 │
│ Queries with Failure                                  │        0 │
└───────────────────────────────────────────────────────┴──────────┘

Resource Usage

tpch_mem — base (merge-base)

Metric	Value
Wall time	3.8s
Peak memory	6.6 GiB
Avg memory	4.4 GiB
CPU user	19.9s
CPU sys	0.7s
Peak spill	0 B

tpch_mem — branch

Metric	Value
Wall time	3.8s
Peak memory	6.8 GiB
Avg memory	4.5 GiB
CPU user	20.4s
CPU sys	0.7s
Peak spill	0 B

---

File an issue against this benchmark runner