DataPower disclosure report

TETRA v0

Non-standard result. This run departs from DP-2026.1 in 6 ways, listed in section 9. Rank its figure only beside runs with the same departures.

Run 2026-11-01T20-24-39Z-standard-sf3m-s-tetra · scenario standard-sf3m-s-tetra · repetition 1 of 1 · spec DP-2026.1

520DP
dp-core SF-3M, envelope S, on the standard mix, blended 80% typical, 15% off-index, 5% worst-case
DP = (E × T) / (R × O) = (3.00 × 375.79) / (2.167 × 1.000)
3.00E · million data elements
375.79T · effective ops/s at k* = 4
2.167R · 2 cores + 1.33 GiB / 8 + 0.23 GiB / 200
1.000O · 1 + 0.05 × 0 surface points

2. Factors

FactorValue
Disk at rest / after work0.10 / 0.23 GiB
Bytes per element82.0
Log share of disk0.0%
Write amplification8.75
Memory ready, after import / repetition0.67 / 0.33 GiB
Peak memory2.15 GiB
Memory charge (M)1.33 GiB
Memory elasticity0.59
Held memory: ready / peak / charge0.33 / 2.13 / 1.31 GiB
Held memory elasticity0.60
Memory after the kernel reclaims0.59 GiB of 1.07
Memory floor (in-memory)8.00 GiB
CPU per standard operation2.94 ms
CPU throttled0.0%

Memory composition

Held memory is memory.current less the page cache, which the kernel hands to another tenant when the host needs it. The score charges memory.current, as spec section 8.5 says.

WhenTotalAnonymousSharedPage cacheKernel
idle1.070.620.000.020.00
peak2.151.690.000.020.00
ready0.670.430.000.150.00
ready_repetition0.330.320.000.000.00

Latency, warm single client

ClassOperationp50 msp99 msTarget ms
R1point0.342.6310
R2filter2.886.18200
R3neighbourhood0.520.6950
R4deep1.231.60500
R5path0.190.25500
R6pattern3.123.942,000
R7analytic50.1469.385,000
W1insert2.354.2020
W2insert edge1.641.9210
W3batch21.3123.42500
U1modify1.101.4620
U2rewire2.813.8630
D1delete edge2.523.1720
D2delete cascade3.918.05100
O1person by email0.440.8420
O2accounts by opening date1.302.38200
O3people by surname and city1.363.53100
S1amount band10.9211.501,000
S3text search3.904.472,000
J4neighbours alike1.023.54500
R1wpoint, worst case0.861.8410
R2wfilter, worst case9.1337.79200
R3wneighbourhood, worst case2.394.9250
R4wdeep, worst case3.1924.98500
R5wpath, worst case0.413.06500
R6wpattern, worst case2.354.102,000
R7wanalytic, worst case51.5581.285,000

Operational surface: 0 points

No surface items.

3. Host and system

SystemTETRA v0, adapter tetra
Imagelocalhost/dpbench-tetra@sha256:f2e7caf3623a883018810dd5fc42243221ea9bf20ab160308597b0c079849890
EnvelopeS: 2 cores, 8 GiB limit
HostAMD EPYC 7502P 32-Core Processor, 64 cores, SMT off, 252 GiB
Kernel and disk6.12.67 · /dev/md0, xfs
Runtimepodman 4.3.1, cgroup v2

4. Adapter manifest, DDL and configuration diff

# TETRA v0, linux/amd64.
#
# TETRA publishes no image, so the adapter builds one on the engine's host:
# `adapters/tetra/build-image.sh path/to/tetra-linux-amd64` (Containerfile and
# entrypoint.sh beside this file). The image is local, so `image` pins the
# digest that build printed; a host with another build pins its own.
#
# THE LOAD RUNS AT THE CONTAINER'S FIRST START. TETRA has no LOAD CSV; its
# bulk loader is `tetra convert`, which writes the database file the server
# then opens. The entrypoint stages the package mounted at /dataset into the
# loader's input (dp-tetra-stage) and converts it before `tetra serve` opens
# Bolt, inside the SUT's envelope, so the adapter's start time carries the
# load and its import call only counts what the database holds.
name: tetra
system: TETRA
version: "v0"
image: localhost/dpbench-tetra@sha256:f2e7caf3623a883018810dd5fc42243221ea9bf20ab160308597b0c079849890
model: property-graph
protocols: [bolt]
query_language: cypher

# TETRA acknowledges a commit once it is on disk, by default, so commits
# are durable without settings (spec §9.2). Each statement reads a
# snapshot; every DataPower operation is one statement.
durability:
  settings: {}
isolation: snapshot

# The adapter declares no secondary index, maintenance task or hand-sized
# cache. The canonical keys are uniqueness constraints on every id
# (spec §7.2), as in the Neo4j mapping.
declared_surface:
  services: 1
  runtime_dependencies: []
  secondary_indexes: []
  hand_sized_caches: []
  non_default_settings: {}
  maintenance_tasks: []
  storage_areas: [data]
  manual_steps: []

envelope:
  size: S
  memory_limit_gib: 8

plugin: tetra
container:
  port: 7687
  data_path: /data
  dataset_path: /dataset
  env:
    TETRA_ENCRYPTION_KEY: dpbench-key
    TETRA_API_KEY: dpbench-tetra
client:
  user: dpbench
  password: dpbench-tetra
  database: neo4j

Executed DDL

CREATE CONSTRAINT place_id IF NOT EXISTS FOR (n:Place) REQUIRE n.id IS UNIQUE;
CREATE CONSTRAINT person_id IF NOT EXISTS FOR (n:Person) REQUIRE n.id IS UNIQUE;
CREATE CONSTRAINT organization_id IF NOT EXISTS FOR (n:Organization) REQUIRE n.id IS UNIQUE;
CREATE CONSTRAINT account_id IF NOT EXISTS FOR (n:Account) REQUIRE n.id IS UNIQUE;
CREATE CONSTRAINT device_id IF NOT EXISTS FOR (n:Device) REQUIRE n.id IS UNIQUE;
CREATE CONSTRAINT tag_id IF NOT EXISTS FOR (n:Tag) REQUIRE n.id IS UNIQUE;
CREATE CONSTRAINT post_id IF NOT EXISTS FOR (n:Post) REQUIRE n.id IS UNIQUE;
CREATE CONSTRAINT knows_id IF NOT EXISTS FOR ()-[r:KNOWS]-() REQUIRE r.id IS UNIQUE;
CREATE CONSTRAINT works_at_id IF NOT EXISTS FOR ()-[r:WORKS_AT]-() REQUIRE r.id IS UNIQUE;
CREATE CONSTRAINT uses_id IF NOT EXISTS FOR ()-[r:USES]-() REQUIRE r.id IS UNIQUE;
CREATE CONSTRAINT transfer_id IF NOT EXISTS FOR ()-[r:TRANSFER]-() REQUIRE r.id IS UNIQUE;
CREATE CONSTRAINT interested_in_id IF NOT EXISTS FOR ()-[r:INTERESTED_IN]-() REQUIRE r.id IS UNIQUE;
CREATE CONSTRAINT likes_id IF NOT EXISTS FOR ()-[r:LIKES]-() REQUIRE r.id IS UNIQUE;
MATCH (n) RETURN labels(n)[0], count(*);
MATCH ()-[r]->() RETURN type(r), count(*);

Settings that differ from a fresh container of the same image

None.

5. Queries

The adapter runs these statements, with parameters bound as $n.

S3

MATCH (p:Post)
WHERE p.language = $language AND p.created_at >= $from AND p.created_at < $to AND p.content CONTAINS $word
RETURN count(p)

J2

MATCH (:Person {id: $id})-[:KNOWS]->(:Person)<-[:OWNED_BY]-(:Account)-[t:TRANSFER]->(b:Account)
WHERE t.ts >= $from AND t.ts < $to
MATCH (b)-[:OWNED_BY]->(:Person)-[:LIVES_IN]->(:Place)-[:PART_OF]->(region:Place)
WITH region, count(t) AS n, sum(t.amount) AS total
RETURN region.name, n, total

J4

MATCH (p:Person {id: $id})-[:LIVES_IN]->(:Place)<-[:LIVES_IN]-(o:Person)
WHERE o <> p AND EXISTS { (o)-[:WORKS_AT]->() } AND EXISTS { (p)-[:INTERESTED_IN]->(:Tag)<-[:INTERESTED_IN]-(o) }
RETURN count(DISTINCT o)

J5

MATCH (:Account {id: $id})-[t1:TRANSFER]->()-[t2:TRANSFER]->()-[t3:TRANSFER]->()-[t4:TRANSFER]->()
WHERE t1.ts >= $from AND t1.ts < $to AND t2.ts > t1.ts AND t3.ts > t2.ts AND t4.ts > t3.ts
  AND t4.ts < t1.ts + duration({days: 30})
RETURN count(*)

O2

MATCH (a:Account)
WHERE a.opened_at >= $from AND a.opened_at < $to AND a.balance >= $lo
RETURN a.id

J1

MATCH (p:Person {id: $id})-[:KNOWS*1..4]->(x:Person)
WHERE x <> p
RETURN count(DISTINCT x)

S2

MATCH (p:Person)
WHERE p.risk_score >= $risk AND p.birth_date >= date($from) AND p.birth_date < date($to)
RETURN p.id

S1

MATCH ()-[t:TRANSFER]->()
WHERE t.ts >= $from AND t.ts < $to AND t.channel = $channel AND t.amount >= $lo AND t.amount <= $hi
RETURN count(t), coalesce(sum(t.amount), 0)

O1

MATCH (p:Person {email: $email})
OPTIONAL MATCH (a:Account)-[:OWNED_BY]->(p)
RETURN p.id, p.first_name, p.last_name, a.id, a.balance, a.status

O3

MATCH (p:Person {last_name: $last})-[:LIVES_IN]->(:Place {id: $city})
OPTIONAL MATCH (a:Account)-[:OWNED_BY]->(p)
RETURN count(DISTINCT p), count(a), coalesce(sum(a.balance), 0)

J3

MATCH (p:Person {id: $id})-[:KNOWS]->(a:Person)-[:KNOWS]->(b:Person)-[:KNOWS]->(p)
WHERE a <> p AND b <> p AND a <> b
RETURN count(*)

S4

MATCH ()-[t:TRANSFER]->()
WHERE t.ts >= $from AND t.ts < $to
RETURN t.currency, t.channel, count(t), sum(t.amount)

R1

MATCH (p:Person {id: $id})
OPTIONAL MATCH (a:Account)-[:OWNED_BY]->(p)
RETURN p.id, p.first_name, p.last_name, a.id, a.balance, a.status

R2

MATCH (a:Account)
WHERE a.country = $country AND a.status = 'open' AND a.balance >= $lo AND a.balance <= $hi
RETURN a.id

R3

MATCH (:Person {id: $id})-[:KNOWS]->(f:Person)
OPTIONAL MATCH (a:Account)-[:OWNED_BY]->(f)
OPTIONAL MATCH (a)-[t:TRANSFER]->()
WHERE t.ts >= $from AND t.ts < $to
RETURN f.id, sum(t.amount)

R4

MATCH (s:Account {id: $id})-[ts:TRANSFER*1..3]->(x:Account)
WHERE all(t IN ts WHERE t.ts >= $from AND t.ts < $to) AND x <> s
RETURN DISTINCT x.id

R5

MATCH (a:Person {id: $src}), (b:Person {id: $dst})
MATCH p = shortestPath((a)-[:KNOWS*..6]->(b))
RETURN length(p)

R6

MATCH p = (a:Account {id: $id})-[ts:TRANSFER*3..5]->(a)
WHERE all(t IN ts WHERE t.ts >= $from AND t.ts < $to)
WITH a, nodes(p)[1..-1] AS mid
WHERE NOT a IN mid AND all(i IN range(0, size(mid) - 2) WHERE NOT mid[i] IN mid[i + 1..])
RETURN count(*)

R7

MATCH (o:Organization)<-[:HELD_AT]-(:Account)
WITH o, count(*) AS held ORDER BY held DESC, o.id ASC LIMIT 20
MATCH (o)<-[:HELD_AT]-(sa:Account)-[t:TRANSFER]->(da:Account)
WHERE t.ts >= $from AND t.ts < $to
RETURN substring(toString(t.ts), 0, 7), sa.country, da.country, sum(t.amount)

W1

CREATE (p:Person {id: $pid, first_name: $fn, last_name: $ln, birth_date: date('1990-01-01'), created_at: $ts, risk_score: 0.5})
WITH p MATCH (home:Place {id: 1}) CREATE (p)-[:LIVES_IN]->(home)
CREATE (:Account {id: $aid, opened_at: $ts, balance: 0, status: 'open', country: 'ZZ'})-[:OWNED_BY]->(p)
WITH p UNWIND $knows AS k
MATCH (d:Person {id: k.dst})
CREATE (p)-[:KNOWS {id: k.id, since: date($ts), strength: 0.5}]->(d)

W2

MATCH (s:Account {id: $src}) MATCH (d:Account {id: $dst})
CREATE (s)-[:TRANSFER {id: $id, ts: $ts, amount: $amount, currency: $currency, channel: $channel}]->(d)

W3

UNWIND $batch AS b
MATCH (s:Account {id: b.src}) MATCH (d:Account {id: b.dst})
CREATE (s)-[:TRANSFER {id: b.id, ts: b.ts, amount: b.amount, currency: b.currency, channel: b.channel}]->(d)

U1

MATCH (a:Account {id: $id}) SET a.balance = $balance, a.status = $status

U2

MATCH (p:Person {id: $id})
OPTIONAL MATCH (p)-[w:WORKS_AT]->()
DELETE w
WITH DISTINCT p
MATCH (o:Organization {id: $org})
CREATE (p)-[:WORKS_AT {id: $wid, from_date: date($ts), role: 'engineer'}]->(o)

D1

MATCH ()-[t:TRANSFER {id: $id}]->() DELETE t

D2

MATCH (p:Person {id: $id})
OPTIONAL MATCH (a:Account)-[:OWNED_BY]->(p)
OPTIONAL MATCH (post:Post)-[:HAS_AUTHOR]->(p)
WITH p, collect(DISTINCT a) + collect(DISTINCT post) AS owned
FOREACH (n IN owned | DETACH DELETE n)
DETACH DELETE p

6. Concurrency ladder, mixed

kX ops/sQX × Q
1354.21.000354.2
4 k*581.60.646375.8
16558.40.366204.5
64552.00.17797.5

7. Memory over the duty cycle

memory.current of the median repetition, sampled every 100 ms. Shaded bands are the busy windows; the rest is idle.

0.0 GiB2.5 GiB5.0 GiB 0 s60 s120 s180 s240 s

8. Validation

0 invalid operation instances.

Write validation read back 200 account, 400 batch, 200 person alive, 200 person deleted, 200 transfer alive, 200 transfer deleted, 200 works, with 0 kinds failing.

9. Deviations

10. Phase detail

Import (P2): 3,000,015 rows in 24.5 s: load 0.0 s, keys 0.0 s, indexes 0.0 s. Peak memory during load 3.19 GiB.

Repetitions (P7, P8)

nTk*Q at k*M GiBAfter work GiB
1375.840.6461.330.23

Coefficient of variation of DataPower across repetitions: 0.0%.

Memory floor (P9)

Limit GiBQOutcome
80.646ran
40.463ran

Cold (P3) and warm (P5) single-client latency, ms

ClassOperationCold p50Cold p99Warm p50Warm p99
R1point0.7312.550.342.63
R2filter2.644.962.886.18
R3neighbourhood0.5817.170.520.69
R4deep1.351.431.231.60
R5path0.275.670.190.25
R6pattern2.3113.523.123.94
R7analytic49.7664.9650.1469.38
W1insert3.925.072.354.20
W2insert edge1.291.811.641.92
W3batch15.5715.8821.3123.42
U1modify0.751.051.101.46
U2rewire0.889.992.813.86
D1delete edge0.901.282.523.17
D2delete cascade3.2936.833.918.05
O1person by email0.5915.910.440.84
O2accounts by opening date1.693.821.302.38
O3people by surname and city1.629.701.363.53
S1amount band5.185.6410.9211.50
S3text search4.035.063.904.47
J4neighbours alike1.0410.511.023.54
R1wpoint, worst case0.800.910.861.84
R2wfilter, worst case11.2112.749.1337.79
R3wneighbourhood, worst case3.435.952.394.92
R4wdeep, worst case2.8111.633.1924.98
R5wpath, worst case0.403.090.413.06
R6wpattern, worst case1.832.792.354.10
R7wanalytic, worst case50.1450.9151.5581.28

Ladder (P6): read

kX ops/sErrorsDriver CPU
1392.404.6%
4864.807.6%
16813.607.8%
64755.007.5%

Ladder (P6): insert

kX ops/sErrorsDriver CPU
1257.002.3%
4223.002.0%
16172.201.6%
64139.401.4%

Ladder (P6): modify-delete

kX ops/sErrorsDriver CPU
1215.001.3%
4273.201.6%
16261.401.5%
64275.401.7%

Ladder (P6): write

kX ops/sErrorsDriver CPU
1139.401.2%
4146.801.2%
16138.801.2%
64134.001.2%

11. Run timeline

The run from its first phase to its last, every second. The driver counts every operation, ramps and warm-ups included, and the probe samples the SUT's cgroup every 100 ms. Bands mark the phases; P3, the cold run, and P4, the warm-up, stand out in teal. After the duty cycle the run asks the kernel to reclaim everything the SUT holds, and the drop in memory shows what the system gives back.

Throughput Valid operations per second, ramps and warm-ups included.
P0P1P1P2P2P3P4P5P6P6P7P7P9P10P10P11P11P12050010001500ops/s0:002:004:006:008:0010:0012:00
Latency p99 of every operation in each second, all classes together, on a log scale.
P0P1P1P2P2P3P4P5P6P6P7P7P9P10P10P11P11P1210301003001000ms0:002:004:006:008:0010:0012:00
Memory The SUT's cgroup memory, stacked: what the processes hold, shared memory such as a buffer pool, and the page cache the kernel can reclaim. The envelope allows 8 GiB.
process (anon)shared memorypage cachekernel
P0P1P1P2P2P3P4P5P6P6P7P7P9P10P10P11P11P1201234GiB0:002:004:006:008:0010:0012:00kernelpage cacheshared memoryprocess (anon)
CPU Cores the SUT kept busy.
P0P1P1P2P2P3P4P5P6P6P7P7P9P10P10P11P11P120123cores0:002:004:006:008:0010:0012:00envelope 2 cores
Disk Bytes the SUT read from and wrote to its block devices.
readwritten
P0P1P1P2P2P3P4P5P6P6P7P7P9P10P10P11P11P12050100150200MB/s0:002:004:006:008:0010:0012:00readwritten
PhaseStartsSecondsOperationsops/sCPU coresPeak GiBPage cache at end GiB
P0 environment check0 s0.800.00.000.000.00
P1 schema definition1 s106.300.01.833.190.15
P2 import107 s31.800.00.800.860.15
P3 cold single-client run139 s18.11357.50.190.530.15
P4 warm-up157 s10.47,365705.51.611.170.15
P5 warm single-client run167 s4.3821190.60.871.150.15
P6 read, write and modify ladders172 s114.736,735320.21.372.160.17
P7 mixed ladder286 s288.864,694224.00.952.120.00
P9 memory floor search575 s7.61,621212.51.581.410.00
P10 validation reads583 s77.700.01.971.840.00
P11 final footprint and surface audit661 s107.600.00.011.810.00
P12 teardown768 s1.400.00.000.650.00

12. From the cold restart

P3 restarts the SUT with an empty page cache and runs every class from one client. P4 warms the system up under load, and P5 runs every class again. These charts start at the restart, so they show how long the system takes to reach its warm speed and what it holds while it gets there.

Every single-client operation Each dot is one operation, on a log scale. P3 runs every class in turn on an empty page cache; P5 runs them again after the warm-up.
P3 coldP5 warm
0.10.3131030100ms0:000:050:100:150:200:250:300:35
Throughput Valid operations per second, ramps and warm-ups included.
coldwarm-upwarm-upwarmwarm02505007501000ops/s0:000:050:100:150:200:250:300:35
Latency p99 of every operation in each second, all classes together, on a log scale.
coldwarm-upwarm-upwarmwarm10301003001000ms0:000:050:100:150:200:250:300:35
Memory The SUT's cgroup memory, stacked: what the processes hold, shared memory such as a buffer pool, and the page cache the kernel can reclaim. The envelope allows 8 GiB.
process (anon)shared memorypage cachekernel
coldwarm-upwarm-upwarmwarm00.250.50.751GiB0:000:050:100:150:200:250:300:35kernelpage cacheshared memoryprocess (anon)
CPU Cores the SUT kept busy.
coldwarm-upwarm-upwarmwarm0123cores0:000:050:100:150:200:250:300:35envelope 2 cores
Disk Bytes the SUT read from and wrote to its block devices.
readwritten
coldwarm-upwarm-upwarmwarm050100150200MB/s0:000:050:100:150:200:250:300:35readwritten
Cold and warm medians Each class's p50 on an empty page cache (P3) and after the warm-up (P5), log scale. The longer the line, the more the class depends on a warm cache.
P3 coldP5 warm
0.1 ms0.3 ms1 ms3 ms10 ms30 ms100 msR1R1 warm p50 0.34 msR1 cold p50 0.73 msR1wR1w warm p50 0.86 msR1w cold p50 0.80 msR2R2 warm p50 2.88 msR2 cold p50 2.64 msR2wR2w warm p50 9.13 msR2w cold p50 11.21 msR3R3 warm p50 0.52 msR3 cold p50 0.58 msR3wR3w warm p50 2.39 msR3w cold p50 3.43 msR4R4 warm p50 1.23 msR4 cold p50 1.35 msR4wR4w warm p50 3.19 msR4w cold p50 2.81 msR5R5 warm p50 0.19 msR5 cold p50 0.27 msR5wR5w warm p50 0.41 msR5w cold p50 0.40 msR6R6 warm p50 3.12 msR6 cold p50 2.31 msR6wR6w warm p50 2.35 msR6w cold p50 1.83 msR7R7 warm p50 50.14 msR7 cold p50 49.76 msR7wR7w warm p50 51.55 msR7w cold p50 50.14 msS1S1 warm p50 10.92 msS1 cold p50 5.18 msS3S3 warm p50 3.90 msS3 cold p50 4.03 msJ4J4 warm p50 1.02 msJ4 cold p50 1.04 msO1O1 warm p50 0.44 msO1 cold p50 0.59 msO2O2 warm p50 1.30 msO2 cold p50 1.69 msO3O3 warm p50 1.36 msO3 cold p50 1.62 msW1W1 warm p50 2.35 msW1 cold p50 3.92 msW2W2 warm p50 1.64 msW2 cold p50 1.29 msW3W3 warm p50 21.31 msW3 cold p50 15.57 msU1U1 warm p50 1.10 msU1 cold p50 0.75 msU2U2 warm p50 2.81 msU2 cold p50 0.88 msD1D1 warm p50 2.52 msD1 cold p50 0.90 msD2D2 warm p50 3.91 msD2 cold p50 3.29 ms