This is the full report of the run “Sub-second consensus and the mmap pack-file backend on the c3 Hyperdisk fleet”. Back to the run page.
r20261006-0053 · Fleet c3-hdb · c3-highcpu-8

Telcoin Network benchmark: mixed workload

Throughput is measured from blocks the chain produced (own senders vs every sender), resource use from Cloud Monitoring, Prometheus and the on-node sampler. Summaries cover the mixed phase. Hover any number for the JSON field it came from.

10 blaster(s), 6K senders, chain 32286, schema tn-blast-combined/v2 · mixed phase 2026-10-06 01:51–02:31 UTC · 1 observers, 10 validators

Preflight: WTEL from genesis (0x0000…37e1), v3 fee tier 3000, v4 available, Multicall3 present · Cooldown ended: idle_30s ×10

Headline numbers

Sustained mixed TPS (own)
7,239.4 tx/s
best 60-s mean of our own landed tx in the mixed phase
Sustained mixed TPS (chain)
7,239.4 tx/s
all tx in blocks, same window
Landed / accepted
99.4 %
10.7M of 10.8M accepted
Reverted (own)
0
0.00 % of landed
Latency p50
3,169 ms
submit → block timestamp; seen p50 8,600 ms
Latency p95
26,067 ms
seen p95 31,658 ms
Gas / s (own)
160M gas/s
chain 160M gas/s
Capacity at mix
6,709.8 tx/s
gas-limit basis 4,302.7 tx/s; block gas limit 30M

Per transaction type

Landed counts only our own senders; latency is submit → block timestamp.

TypeSubmittedAcceptedLandedRevertedUnlandedSkipsGas limitGas used avgp50p95
native_transfer3.3M3.3M3.28M020.1K024.1K21K3,178 ms43,647 ms
batched_self_send1.64M1.64M1.63M013K024.1K21K3,247 ms63,321 ms
uniswap_v2_swap1.35M1.35M1.35M06.76K1.06K180K106K3,116 ms14,659 ms
stablecoin_transfer1.19M1.19M1.19M06.4K66975K43.9K3,137 ms15,461 ms
wtel_wrap978K978K971K06.9K050K27.9K3,181 ms40,291 ms
wtel_unwrap630K630K626K03.29K74945K35.2K3,136 ms15,322 ms
stablecoin_approve490K490K487K03.46K060K31.8K3,179 ms39,365 ms
uniswap_v2_add_liquidity301K301K299K01.53K1.06K250K128K3,112 ms14,667 ms
contract_deploy245K245K243K01.76K0140K74.2K3,182 ms44,275 ms
uniswap_v4_swap221K221K220K01.03K1.15K250K124K3,110 ms14,643 ms
uniswap_v3_swap150K150K149K07231.09K220K120K3,117 ms14,480 ms
uniswap_v2_remove_liquidity147K147K147K07371.23K220K129K3,103 ms14,485 ms
faucet_drip113K113K112K01.08K294K150K107K3,344 ms350,229 ms

Submission by RPC node

NodeSubmittedAcceptedAccepted %Top errorsSend p50Send p95
bench-validator-01
bench-validator-01:8545
1.08M1.03M95.9 %known 22.2K8 ms30 ms
bench-validator-02
bench-validator-02:8545
1.04M989K95.4 %known 22.6K7 ms27 ms
bench-validator-03
bench-validator-03:8545
174K134K77.4 %known 15.2K12 ms52 ms
bench-validator-04
bench-validator-04:8545
165K126K76.1 %known 15.4K13 ms47 ms
bench-validator-05
bench-validator-05:8545
2.03M2M98.6 %known 12.5K, conn 2.16K8 ms27 ms
bench-validator-06
bench-validator-06:8545
2.56M2.54M99.1 %known 9.23K8 ms26 ms
bench-validator-07
bench-validator-07:8545
902K853K94.6 %known 22.6K7 ms25 ms
bench-validator-08
bench-validator-08:8545
981K934K95.2 %known 23.9K7 ms24 ms
bench-validator-09
bench-validator-09:8545
1.05M1M95.7 %known 18.9K8 ms27 ms
bench-validator-10
bench-validator-10:8545
1.26M1.22M96.9 %known 17.5K9 ms35 ms

Throughput over time

Shaded: phases outside the mixed window. Hairlines: epoch closes. Dashed orange: chaos events.

Landed transactions per second

own senders vs chain total, per block-timestamp second

Gas per second

own vs chain gas used, per block-timestamp second

CPU and memory per node

CPU utilization

compute.googleapis.com/instance/cpu/utilization, 60-s mean, % of all vCPUs; summaries over the mixed phase

Table view
NodeClassMeanp95Peak 60-s meanMax
bench-observer-11observer11.5 %14.9 %15.8 %15.8 %
bench-validator-01validator19.5 %26.4 %31.2 %31.2 %
bench-validator-02validator19.4 %26.2 %28.5 %28.5 %
bench-validator-03validator21.4 %27.8 %31.2 %31.2 %
bench-validator-04validator21.1 %27.1 %30.8 %30.8 %
bench-validator-05validator19.6 %26.8 %31.8 %31.8 %
bench-validator-06validator20.5 %27.0 %28.9 %28.9 %
bench-validator-07validator19.4 %25.5 %27.1 %27.1 %
bench-validator-08validator19.1 %24.8 %26.3 %26.3 %
bench-validator-09validator19.1 %25.2 %26.6 %26.6 %
bench-validator-10validator19.5 %27.3 %30.6 %30.6 %

CPU: mean vs peak 60-s mean

One row per node, over the mixed phase.

telcoin resident memory

agent processes/rss_usage summed over telcoin pids; summaries over the mixed phase

Table view
NodeClassMeanp95Peak 60-s meanMax
bench-observer-11observer1.71 GiB2.56 GiB2.59 GiB2.59 GiB
bench-validator-01validator5.15 GiB7.05 GiB7.08 GiB7.08 GiB
bench-validator-02validator4.96 GiB7.18 GiB7.22 GiB7.22 GiB
bench-validator-03validator5.81 GiB8.99 GiB9.17 GiB9.17 GiB
bench-validator-04validator5.18 GiB7.17 GiB7.27 GiB7.27 GiB
bench-validator-05validator3.93 GiB5.19 GiB5.24 GiB5.24 GiB
bench-validator-06validator5.13 GiB7.20 GiB7.24 GiB7.24 GiB
bench-validator-07validator4.93 GiB6.85 GiB6.90 GiB6.90 GiB
bench-validator-08validator4.91 GiB6.55 GiB6.59 GiB6.59 GiB
bench-validator-09validator4.88 GiB6.47 GiB6.52 GiB6.52 GiB
bench-validator-10validator4.40 GiB5.86 GiB5.93 GiB5.93 GiB

telcoin RSS: mean vs peak 60-s mean

One row per node, over the mixed phase.

Memory used

agent memory/percent_used, state=used; summaries over the mixed phase

Table view
NodeClassMeanp95Peak 60-s meanMax
bench-observer-11observer9.7 %12.3 %12.9 %12.9 %
bench-validator-01validator30.6 %37.4 %37.5 %37.5 %
bench-validator-02validator29.3 %38.1 %38.4 %38.4 %
bench-validator-03validator34.5 %49.9 %50.4 %50.4 %
bench-validator-04validator30.6 %38.3 %38.6 %38.6 %
bench-validator-05validator20.7 %27.7 %28.1 %28.1 %
bench-validator-06validator30.4 %38.3 %38.5 %38.5 %
bench-validator-07validator29.3 %36.1 %36.6 %36.6 %
bench-validator-08validator29.0 %34.3 %34.4 %34.4 %
bench-validator-09validator28.7 %33.9 %33.9 %33.9 %
bench-validator-10validator25.9 %30.3 %30.4 %30.4 %

Memory used: mean vs peak 60-s mean

One row per node, over the mixed phase.

Disk

Disk throttling (validator)
not collected –
metric type unavailable in project
Disk performance degraded (validator)
none –
any sample

Disk read + write throughput

instance/disk/{read,write}_bytes_count rate, all devices; summaries over the mixed phase

Table view
NodeClassMeanp95Peak 60-s meanMaxLimit
bench-observer-11observer282.9 MiB/s419.0 MiB/s426.6 MiB/s426.6 MiB/s800.0 MiB/s
bench-validator-01validator316.3 MiB/s455.3 MiB/s461.9 MiB/s461.9 MiB/s800.0 MiB/s
bench-validator-02validator316.2 MiB/s453.2 MiB/s466.1 MiB/s466.1 MiB/s800.0 MiB/s
bench-validator-03validator307.4 MiB/s453.4 MiB/s465.5 MiB/s465.5 MiB/s800.0 MiB/s
bench-validator-04validator316.2 MiB/s461.7 MiB/s463.6 MiB/s463.6 MiB/s800.0 MiB/s
bench-validator-05validator275.7 MiB/s399.2 MiB/s437.0 MiB/s437.0 MiB/s800.0 MiB/s
bench-validator-06validator318.5 MiB/s464.3 MiB/s470.3 MiB/s470.3 MiB/s800.0 MiB/s
bench-validator-07validator318.1 MiB/s460.9 MiB/s473.2 MiB/s473.2 MiB/s800.0 MiB/s
bench-validator-08validator317.2 MiB/s455.7 MiB/s475.0 MiB/s475.0 MiB/s800.0 MiB/s
bench-validator-09validator317.0 MiB/s455.6 MiB/s469.4 MiB/s469.4 MiB/s800.0 MiB/s
bench-validator-10validator316.5 MiB/s457.0 MiB/s468.1 MiB/s468.1 MiB/s800.0 MiB/s

Disk read + write IOPS

instance/disk/{read,write}_ops_count rate, all devices; summaries over the mixed phase

Table view
NodeClassMeanp95Peak 60-s meanMaxLimit
bench-observer-11observer1.74K IOPS4.32K IOPS4.62K IOPS4.62K IOPS20K IOPS
bench-validator-01validator1.57K IOPS2.24K IOPS2.26K IOPS2.26K IOPS20K IOPS
bench-validator-02validator1.57K IOPS2.21K IOPS2.28K IOPS2.28K IOPS20K IOPS
bench-validator-03validator1.81K IOPS3.68K IOPS4.28K IOPS4.28K IOPS20K IOPS
bench-validator-04validator1.56K IOPS2.26K IOPS2.27K IOPS2.27K IOPS20K IOPS
bench-validator-05validator2.55K IOPS5.88K IOPS6.58K IOPS6.58K IOPS20K IOPS
bench-validator-06validator1.56K IOPS2.27K IOPS2.3K IOPS2.3K IOPS20K IOPS
bench-validator-07validator1.56K IOPS2.25K IOPS2.31K IOPS2.31K IOPS20K IOPS
bench-validator-08validator1.56K IOPS2.21K IOPS2.32K IOPS2.32K IOPS20K IOPS
bench-validator-09validator1.56K IOPS2.25K IOPS2.29K IOPS2.29K IOPS20K IOPS
bench-validator-10validator1.56K IOPS2.24K IOPS2.29K IOPS2.29K IOPS20K IOPS
Disk limits used
NodeMachinevCPUDiskIOPS limitMiB/s limitBasis
bench-observer-11c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-01c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-02c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-03c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-04c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-05c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-06c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-07c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-08c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-09c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget
bench-validator-10c3-highcpu-88hyperdisk-balanced 100 GB20K IOPS800.0 MiB/shyperdisk-balanced 100 GB: provisioned 20,000 IOPS, provisioned 800 MiB/s; c3 8 vCPU cap 50,000 IOPS / 800 MiB/s; reads and writes share this budget

Network

Network sent

instance/network/sent_bytes_count rate; summaries over the mixed phase

Table view
NodeClassMeanp95Peak 60-s meanMax
bench-observer-11observer1.1 Mbps1.4 Mbps1.4 Mbps1.4 Mbps
bench-validator-01validator57.5 Mbps79.6 Mbps84.3 Mbps84.3 Mbps
bench-validator-02validator59.6 Mbps81.4 Mbps87.2 Mbps87.2 Mbps
bench-validator-03validator55.7 Mbps75.2 Mbps78.0 Mbps78.0 Mbps
bench-validator-04validator55.2 Mbps76.0 Mbps78.0 Mbps78.0 Mbps
bench-validator-05validator61.4 Mbps84.6 Mbps93.4 Mbps93.4 Mbps
bench-validator-06validator63.7 Mbps84.7 Mbps90.6 Mbps90.6 Mbps
bench-validator-07validator57.0 Mbps78.1 Mbps80.7 Mbps80.7 Mbps
bench-validator-08validator58.8 Mbps81.5 Mbps83.9 Mbps83.9 Mbps
bench-validator-09validator57.3 Mbps77.8 Mbps83.5 Mbps83.5 Mbps
bench-validator-10validator59.0 Mbps87.2 Mbps92.2 Mbps92.2 Mbps

Network received

instance/network/received_bytes_count rate; summaries over the mixed phase

Table view
NodeClassMeanp95Peak 60-s meanMax
bench-observer-11observer3.6 Mbps4.9 Mbps5.8 Mbps5.8 Mbps
bench-validator-01validator5.9 Mbps8.6 Mbps10.5 Mbps10.5 Mbps
bench-validator-02validator5.8 Mbps8.5 Mbps10.0 Mbps10.0 Mbps
bench-validator-03validator6.9 Mbps9.4 Mbps12.7 Mbps12.7 Mbps
bench-validator-04validator6.6 Mbps9.3 Mbps12.1 Mbps12.1 Mbps
bench-validator-05validator7.7 Mbps13.9 Mbps14.7 Mbps14.7 Mbps
bench-validator-06validator8.6 Mbps12.2 Mbps14.1 Mbps14.1 Mbps
bench-validator-07validator5.7 Mbps7.9 Mbps10.3 Mbps10.3 Mbps
bench-validator-08validator5.6 Mbps7.8 Mbps9.4 Mbps9.4 Mbps
bench-validator-09validator5.7 Mbps9.0 Mbps9.4 Mbps9.4 Mbps
bench-validator-10validator6.1 Mbps11.1 Mbps12.1 Mbps12.1 Mbps

Consensus health

MetricQueryClassNodesMedian of node meansWorst peak 60-s meanMax
tn_primary_commit_latency_secondsp95validator103,074 ms30.0 s30.0 s
tn_engine_execution_duration_secondsp95validator103,727 ms7,062 ms9,250 ms
tn_engine_execution_duration_secondsp95observer13,516 ms6,088 ms8,000 ms
tn_worker_batch_size_bytesp95validator10233.7 KiB246.4 KiB246.4 KiB
tn_worker_batch_transactionsp95validator105141K1K
tn_executor_output_transactionsp95validator101K1K1K
tn_primary_consensus_output_bytesmaxvalidator10673.7 KiB1.6 MiB2.4 MiB
tn_primary_consensus_output_bytesmaxobserver1692.3 KiB1.6 MiB2.1 MiB
tn_engine_queued_outputsmaxvalidator101.496.58
tn_engine_queued_outputsmaxobserver11.0156
tn_primary_roundmaxvalidator109001.79K1.79K
tn_primary_roundmaxobserver18931.78K1.78K
tn_primary_committed_roundmaxvalidator108971.78K1.79K
tn_primary_committed_roundmaxobserver18931.78K1.78K
tn_epoch_currentmaxvalidator102.433
tn_epoch_currentmaxobserver12.4133
tn_batch_builder_pending_pool_transactionsmaxvalidator103194.13K8.82K
tn_batch_builder_pending_pool_transactionsmaxobserver1000
reth_process_resident_memory_bytesmaxvalidator105.09 GiB9.29 GiB9.31 GiB
reth_process_resident_memory_bytesmaxobserver11.79 GiB2.70 GiB2.73 GiB
tn_primary_subdags_committed_totalratevalidator100.4690.8560.867
tn_primary_subdags_committed_totalrateobserver1000
tn_primary_round_laglagvalidator102.456
tn_primary_round_laglagobserver1000
tn_batch_builder_seal_failures_totalratevalidator7000
tn_node_modemaxvalidator10000
tn_node_modemaxobserver1000

Commit latency p95

tn_primary_commit_latency_seconds

Round lag

tn_primary_round − tn_primary_committed_round

Engine queued outputs

tn_engine_queued_outputs, max by node

On-node sampler

NodeClassPeak RssAnonPeak RssFilePeak cachePSI memPSI ioPSI cpudb growthstatic_files growthRoot usedOOM Δ
bench-observer-11observer1.08 GiB2.12 GiB64 MiB 6.3 %0.0 %22.8 %0.8 %0 B2.42 GiB12.0 %0
bench-validator-01validator5.08 GiB2.12 GiB64 MiB 6.3 %0.0 %30.8 %3.5 %0 B2.42 GiB12.0 %0
bench-validator-02validator5.25 GiB2.12 GiB64 MiB 6.3 %0.0 %28.9 %3.5 %0 B2.42 GiB12.0 %0
bench-validator-03validator7.21 GiB2.11 GiB64 MiB 6.3 %0.0 %26.8 %3.4 %0 B2.42 GiB12.0 %0
bench-validator-04validator5.28 GiB2.12 GiB64 MiB 6.3 %0.0 %30.9 %3.8 %0 B2.42 GiB12.0 %0
bench-validator-05validator3.57 GiB2.09 GiB64 MiB 6.3 %0.0 %26.7 %3.8 %0 B2.42 GiB12.0 %0
bench-validator-06validator5.24 GiB2.12 GiB64 MiB 6.3 %0.0 %33.6 %3.8 %0 B2.42 GiB12.0 %0
bench-validator-07validator4.90 GiB2.12 GiB64 MiB 6.3 %0.0 %30.5 %3.5 %0 B2.42 GiB12.0 %0
bench-validator-08validator4.62 GiB2.12 GiB64 MiB 6.3 %0.0 %31.7 %3.2 %0 B2.42 GiB12.0 %0
bench-validator-09validator4.51 GiB2.12 GiB64 MiB 6.3 %0.0 %28.8 %2.6 %0 B2.42 GiB12.0 %0
bench-validator-10validator3.93 GiB2.12 GiB64 MiB 6.3 %0.0 %31.2 %3.7 %0 B2.42 GiB12.0 %0

RssAnon vs RssFile

/proc/<pid>/status of the telcoin process on the node with the largest RSS

consensus-db/cache size

du -sb of consensus-db/cache vs the 1 GiB ceiling

Pressure stall (some, avg10)

/proc/pressure on the node with the highest memory PSI

Headroom

Per role and per node, from sizing.json (p95 over the landed window; PSI and RssAnon max over the whole sampler run). The lines follow the hardware doc's tier rules: CPU p95 over 70 % of vCPUs; memory used p95 over 75 % of RAM, or telcoin RSS p95 over 85 % of RAM; disk write p95 over 60 % of the PD MiB/s limit, or write IOPS p95 over 60 % of the IOPS limit; IO pressure over 20 % or memory pressure over 5 % (PSI some avg10, max); network p95 over 50 % of 1 Gbps; root disk over 80 %. A line crossed on any node puts the role at the limit; a nonzero reading within 15 points of its line is tight; otherwise the role has headroom. OOM kills, disk throttling and degraded disk performance are flagged too.

SignalClassWorst nodeValueShare of capacityLineNodes over / tightStatus
CPU p95validatorbench-validator-0328.2 %28.2 %> 70 %0 / 0 headroom
Memory used p95validatorbench-validator-0350.5 %50.5 %> 75 %0 / 0 headroom
telcoin RSS p95validatorbench-validator-0310.12 GB58.9 %> 85 %0 / 0 headroom
PSI memory maxvalidatorbench-validator-010.0 %0.0 %> 5 %0 / 0 headroom
RssAnon peakvalidatorbench-validator-037.76 GB45.1 %info– info
Disk write p95validatorbench-validator-10555 MB/s66.2 %> 60 %8 / 2 at the limit
Write IOPS p95validatorbench-validator-056,74433.7 %> 60 %0 / 0 headroom
PSI io maxvalidatorbench-validator-0633.6 %33.6 %> 20 %10 / 0 at the limit
Root disk maxvalidatorbench-validator-1012.4 %12.4 %> 80 %0 / 0 headroom
Network p95validatorbench-validator-0687 Mbps8.7 %> 50 %0 / 0 headroom
Consensus cache peakvalidatorbench-validator-010.06 GiB6.3 %info– info
OOM killsvalidator––anyany– none
Disk throttlingvalidator––metric type unavailable in projectany– not collected
Disk performance degradedvalidator––any sampleany– none
CPU p95observerbench-observer-1114.9 %14.9 %> 70 %0 / 0 headroom
Memory used p95observerbench-observer-1112.3 %12.3 %> 75 %0 / 0 headroom
telcoin RSS p95observerbench-observer-112.99 GB17.4 %> 85 %0 / 0 headroom
PSI memory maxobserverbench-observer-110.0 %0.0 %> 5 %0 / 0 headroom
RssAnon peakobserverbench-observer-111.16 GB6.8 %info– info
Disk write p95observerbench-observer-11439 MB/s52.4 %> 60 %0 / 1 tight
Write IOPS p95observerbench-observer-115,61728.1 %> 60 %0 / 0 headroom
PSI io maxobserverbench-observer-1122.8 %22.8 %> 20 %1 / 0 at the limit
Root disk maxobserverbench-observer-1112.1 %12.1 %> 80 %0 / 0 headroom
Network p95observerbench-observer-116 Mbps0.6 %> 50 %0 / 0 headroom
Consensus cache peakobserverbench-observer-110.06 GiB6.3 %info– info
OOM killsobserver––anyany– none
Disk throttlingobserver––metric type unavailable in projectany– not collected
Disk performance degradedobserver––any sampleany– none

Per node

NodeClassCPU p95Memory used p95telcoin RSS p95PSI memory maxRssAnon peakDisk write p95Write IOPS p95PSI io maxRoot disk maxNetwork p95Consensus cache peak
Line> 70 %> 75 %> 85 %> 5 %info> 60 %> 60 %> 20 %> 80 %> 50 %info
bench-validator-01validator26.4 %37.5 %7.85 GB 46 %0.0 %5.47 GB 32 %547 MB/s 65 %3,048 15 %31.8 %12.3 %80 Mbps 8 %0.06 GiB 6 %
bench-validator-02validator26.2 %38.8 %8.05 GB 47 %0.0 %5.71 GB 33 %542 MB/s 65 %3,369 17 %32.1 %12.3 %81 Mbps 8 %0.06 GiB 6 %
bench-validator-03validator28.2 %50.5 %10.12 GB 59 %0.0 %7.76 GB 45 %475 MB/s 57 %5,253 26 %26.8 %12.3 %75 Mbps 8 %0.06 GiB 6 %
bench-validator-04validator27.7 %38.8 %8.08 GB 47 %0.0 %5.70 GB 33 %532 MB/s 63 %3,518 18 %31.4 %12.3 %76 Mbps 8 %0.06 GiB 6 %
bench-validator-05validator27.8 %27.7 %6.04 GB 35 %0.0 %3.83 GB 22 %419 MB/s 50 %6,744 34 %26.7 %12.2 %86 Mbps 9 %0.06 GiB 6 %
bench-validator-06validator27.4 %38.4 %7.99 GB 46 %0.0 %5.62 GB 33 %543 MB/s 65 %2,615 13 %33.6 %12.3 %87 Mbps 9 %0.06 GiB 6 %
bench-validator-07validator25.5 %36.7 %7.69 GB 45 %0.0 %5.29 GB 31 %548 MB/s 65 %2,625 13 %33.0 %12.3 %78 Mbps 8 %0.06 GiB 6 %
bench-validator-08validator24.8 %34.7 %7.35 GB 43 %0.0 %4.96 GB 29 %553 MB/s 66 %2,642 13 %32.2 %12.3 %81 Mbps 8 %0.06 GiB 6 %
bench-validator-09validator25.2 %34.0 %7.26 GB 42 %0.0 %4.87 GB 28 %554 MB/s 66 %2,640 13 %32.6 %12.3 %78 Mbps 8 %0.06 GiB 6 %
bench-validator-10validator27.3 %30.5 %6.63 GB 39 %0.0 %4.23 GB 25 %555 MB/s 66 %2,634 13 %32.8 %12.4 %87 Mbps 9 %0.06 GiB 6 %
bench-observer-11observer14.9 %12.3 %2.99 GB 17 %0.0 %1.16 GB 7 %439 MB/s 52 %5,617 28 %22.8 %12.1 %6 Mbps 1 %0.06 GiB 6 %

Small figures are the share of capacity: RAM for RSS, the PD limit for disk write (VM cap applied), 1 Gbps for network. Hover a cell for its JSON path.

Verdict

Fleet A vs Fleet B

A = Fleet c3-hdb · c3-highcpu-8 · r20261006-0053
B = Fleet c3-hdb · c3-highcpu-8 · r20260929-1647

Verdict

at the limit c3-highcpu-8 validators at 7,239 sustained TPS: at the limit on disk. Disk at the limit: write p95 532–555 MB/s, up to 66.2 % of the 800 MiB/s limit, over the 60 % line on 8 of 10 validators (bench-validator-01, 02, 04, 06, 07, 08, 09, 10); IO pressure (PSI some avg10) max 26.7–33.6 %, over the 20 % line on all 10 validators (bench-validator-01, 02, 03, 04, 05, 06, 07, 08, 09, 10). CPU has headroom: CPU p95 28.2 % of 8 vCPUs (bench-validator-03). Memory has headroom: memory used p95 50.5 % of RAM (bench-validator-03); telcoin RSS p95 10.12 GB, 58.9 % of 16 GiB RAM (bench-validator-03); memory pressure (PSI some avg10) max 0.0 % (bench-validator-01). Network has headroom: network p95 87 Mbps, 8.7 % of 1 Gbps (bench-validator-06). Next step: a faster volume (pd-ssd adds 30 IOPS and 0.48 MiB/s per GB up to the per-VM cap; past the cap, a larger VM).

at the limit c3-highcpu-8 observers at 7,239 sustained TPS: at the limit on disk. Disk at the limit: IO pressure (PSI some avg10) max 22.8 % on bench-observer-11, over the 20 % line; write p95 439 MB/s, 52.4 % of the 800 MiB/s limit (bench-observer-11), tight against the 60 % line. CPU has headroom: CPU p95 14.9 % of 8 vCPUs (bench-observer-11). Memory has headroom: memory used p95 12.3 % of RAM (bench-observer-11); telcoin RSS p95 2.99 GB, 17.4 % of 16 GiB RAM (bench-observer-11); memory pressure (PSI some avg10) max 0.0 % (bench-observer-11). Network has headroom: network p95 6 Mbps, 0.6 % of 1 Gbps (bench-observer-11). Next step: a faster volume (pd-ssd adds 30 IOPS and 0.48 MiB/s per GB up to the per-VM cap; past the cap, a larger VM).

at the limit c3-highcpu-8 validators at 6,561 sustained TPS: at the limit on disk. Disk at the limit: IO pressure (PSI some avg10) max 24.0–30.3 %, over the 20 % line on all 10 validators (bench-validator-01, 02, 03, 04, 05, 06, 07, 08, 09, 10); write p95 494 MB/s, 58.9 % of the 800 MiB/s limit (bench-validator-09), tight against the 60 % line; write IOPS p95 11,076, 55.4 % of the 20,000 IOPS limit (bench-validator-05), tight against the 60 % line. Memory tight: memory pressure (PSI some avg10) max 0.0 % (bench-validator-05), tight against the 5 % line. CPU has headroom: CPU p95 32.8 % of 8 vCPUs (bench-validator-03). Network has headroom: network p95 112 Mbps, 11.2 % of 1 Gbps (bench-validator-06). Next step: a faster volume (pd-ssd adds 30 IOPS and 0.48 MiB/s per GB up to the per-VM cap; past the cap, a larger VM).

at the limit c3-highcpu-8 observers at 6,561 sustained TPS: at the limit on disk. Disk at the limit: IO pressure (PSI some avg10) max 26.9 % on bench-observer-11, over the 20 % line; write p95 434 MB/s, 51.8 % of the 800 MiB/s limit (bench-observer-11), tight against the 60 % line. CPU has headroom: CPU p95 15.7 % of 8 vCPUs (bench-observer-11). Memory has headroom: memory used p95 10.4 % of RAM (bench-observer-11); telcoin RSS p95 3.57 GB, 20.8 % of 16 GiB RAM (bench-observer-11); memory pressure (PSI some avg10) max 0.0 % (bench-observer-11). Network has headroom: network p95 5 Mbps, 0.5 % of 1 Gbps (bench-observer-11). Next step: a faster volume (pd-ssd adds 30 IOPS and 0.48 MiB/s per GB up to the per-VM cap; past the cap, a larger VM).

Validators: Fleet A (c3-highcpu-8) is at the limit on disk, with headroom on CPU, memory and network; Fleet B (c3-highcpu-8) is at the limit on disk, tight on memory, with headroom on CPU and network. The same disk limit binds both fleets: every validator runs a 100 GB hyperdisk-balanced, which allows 20,000 IOPS on both; its throughput limit is 800 MiB/s on both. Disk is at the limit on both (Fleet A (c3-highcpu-8): write p95 555 MB/s, 66.2 % of the 800 MiB/s limit, IO pressure (PSI some avg10) max 33.6 %; Fleet B (c3-highcpu-8): IO pressure (PSI some avg10) max 30.3 %). Changing the machine shape did not clear it; the volume is the binding resource.

Observers: Fleet A (c3-highcpu-8) is at the limit on disk, with headroom on CPU, memory and network; Fleet B (c3-highcpu-8) is at the limit on disk, with headroom on CPU, memory and network. The same disk limit binds both fleets: every observer runs a 100 GB hyperdisk-balanced, which allows 20,000 IOPS on both; its throughput limit is 800 MiB/s on both. Disk is at the limit on both (Fleet A (c3-highcpu-8): IO pressure (PSI some avg10) max 22.8 %; Fleet B (c3-highcpu-8): IO pressure (PSI some avg10) max 26.9 %). Changing the machine shape did not clear it; the volume is the binding resource.

KPIFleet AFleet BB ÷ A
Sustained mixed TPS (own)7,239.4 tx/s6,561.4 tx/s0.91×
Sustained mixed TPS (chain)7,239.4 tx/s6,561.4 tx/s0.91×
Landed / accepted99.4 %99.7 %1.00×
Reverted (own)00–
Latency p503,169 ms4,036 ms1.27×
Latency p9526,067 ms14,363 ms0.55×
Gas / s (own)160M gas/s208M gas/s1.30×
Capacity at mix6,709.8 tx/s7,745.9 tx/s1.15×

Headroom, worst node per class

SignalClassFleet AFleet BLine
CPU p95validator28.2 % headroom32.8 % headroom> 70 %
Memory used p95validator50.5 % headroom44.5 % headroom> 75 %
telcoin RSS p95validator10.12 GB 58.9 % headroom10.58 GB 61.6 % headroom> 85 %
PSI memory maxvalidator0.0 % headroom0.0 % tight> 5 %
Disk write p95validator555 MB/s 66.2 % at the limit494 MB/s 58.9 % tight> 60 %
Write IOPS p95validator6,744 33.7 % headroom11,076 55.4 % tight> 60 %
PSI io maxvalidator33.6 % at the limit30.3 % at the limit> 20 %
Root disk maxvalidator12.4 % headroom15.0 % headroom> 80 %
Network p95validator87 Mbps 8.7 % headroom112 Mbps 11.2 % headroom> 50 %
CPU p95observer14.9 % headroom15.7 % headroom> 70 %
Memory used p95observer12.3 % headroom10.4 % headroom> 75 %
telcoin RSS p95observer2.99 GB 17.4 % headroom3.57 GB 20.8 % headroom> 85 %
PSI memory maxobserver0.0 % headroom0.0 % headroom> 5 %
Disk write p95observer439 MB/s 52.4 % tight434 MB/s 51.8 % tight> 60 %
Write IOPS p95observer5,617 28.1 % headroom7,149 35.7 % headroom> 60 %
PSI io maxobserver22.8 % at the limit26.9 % at the limit> 20 %
Root disk maxobserver12.1 % headroom13.7 % headroom> 80 %
Network p95observer6 Mbps 0.6 % headroom5 Mbps 0.5 % headroom> 50 %

Own TPS, trailing 60-s mean

aligned on each fleet's mixed-phase start

CPU, hottest validator

aligned on each fleet's mixed-phase start

Memory used, hottest validator

aligned on each fleet's mixed-phase start

telcoin RSS, hottest validator

aligned on each fleet's mixed-phase start

Disk MiB/s, hottest validator

aligned on each fleet's mixed-phase start

Network sent, hottest validator

aligned on each fleet's mixed-phase start

Reference chains

Not collected: reference chains.