Sorry, you need to enable JavaScript to visit this website.

Linux Kernel Performance

Linux development evolves rapidly. The performance and scalability of the OS kernel has been a key part of its success. However, discussions have appeared on LKML (Linux Kernel Mailing List) regarding large performance regression between kernel versions. These discussions underscore the need for a systematic and disciplined way to characterize, improve, and test Linux kernel performance. Our goal is to work with the Linux community to further enhance the Linux kernel with consistent performance increases (avoiding degradations) across releases. The information available on this site gives community members better information about what 0-Day and LKP (Linux Kernel Performance) are doing to preserve performance integrity of the kernel.

0-Day CI Linux Kernel Performance Report (v5.4)

BY Rong Chen ON Dec 16, 2019
  1. Introduction

0-Day CI is an automated Linux kernel test service that provides comprehensive test coverage of the Linux kernel. It covers kernel build, static analysis, boot, functional, performance and power tests. This report shows the recent observations of kernel performance status on IA platform based on the test results from 0-Day CI service. It is structured in the following manner:

  • Section 2, merged regressions and improvements in v5.4 release candidates

  • Section 3, test parameter description

  • Section 4, captured regressions and improvements by shift-left testing during developers’ and maintainers’ tree during v5.4 release cycle

  • Section 5, performance comparison among different kernel releases

  • Section 6, test machine list

 

  1. Test parameters

Here are the descriptions for each parameter/field used in the tests. 

 

Classification

Name

Description

General

runtime

Run the test case within a certain time period (seconds or minutes)

 

nr_task

If it is an integer, which means the number of processes/threads (to run the workload) of this job. Default is 1.

If it is a percentage, e.g. 200% means the number of processes/threads is double of cpu number

 

nr_threads

Alias of nr_task

 

iterations

Number to repeat this job

 

test_size

Test disk size or memory size

 

set_nic_irq_affinity

Set NIC interrupt affinity

 

disable_latency_stats

Latency_stats may introduce too much noise if there are too many context switches, allow to disable it

 

transparent_hugepage

Set transparent hugepage policy (/sys/kernel/mm/transparent_hugepage)

 

boot_params:bp1_memmap

Boot parameters of memmap

 

disk:nr_pmem

number of pmem partitions used by test

 

swap:priority

Priority means the  priority of the swap device. priority is a value between -1 and 32767, the default is -1 and higher priority with higher value. 

Test Machine

model

Name of Intel processor microarchitecture

 

brand

Brand name of cpu

 

cpu_number

Number of cpu

 

memory

Size of memory


 

  1. Linux Kernel v5.4 Release Test

The 5.4 release of the Linux kernel was on November 25, 2019. Linus has released the 5.4 kernel. "Not a lot happened this last week, which is just how I like it". Significant features in this release include the haltpoll CPU governor, the iocost (formerly io.weight) I/O controller, the EROFS filesystem, an implementation of the exFAT filesystem that may yet be superseded by a better version, the fs-verity file integrity mechanism, support for the BPF compile once, run everywhere mechanism, the dm-clone device mapper target, the virtiofs filesystem, kernel lockdown support (at last), kernel symbol namespaces, and a new random-number generator meant to solve the early-boot entropy problem. See the KernelNewbies 5.4 page for a lot more details.

 

0-Day CI monitored the release closely to trace down the performance status on IA platform. 0-Day observed 7 regressions and 3 improvements during feature development phase for v5.4. We will share more detailed information together with correlated patches that led to the results. Note that the assessment is limited by the test coverage 0-Day has now. The list is summarized in the observation summary section.

    1. Observation Summary

0-Day CI observed 7 regressions and 3 improvements during feature development phase for v5.4, which is in the time frame from v5.4-rc1 to v5.4 release. 

Test Indicator

Report

Test Scenario

Test Machine

Development Base

Status

aim7.jobs-per-min

[LKP] [btrfs] 0096420adb: 18.3% improvement

disk: 1BRD_48G

fs: btrfs

test: disk_wrt

load: 1500

cpufreq_governor: performance


 

lkp-csl-2ap2

v5.3-rc8


 

merged at v5.4-rc1

aim7.jobs-per-min

[LKP] [btrfs] cb49511328: 3.1% improvement

disk: 4BRD_12G

md: RAID1

fs: btrfs

test: sync_disk_rw

load: 20

cpufreq_governor: performance

lkp-skl-2sp7

v5.3-rc8

merged at v5.4-rc1

aim9.dir_rtns_1.ops_per_sec

[LKP] d4f4de5e5e: -26.1% regression

testtime: 5s

test: all

cpufreq_governor: performance

lkp-ivb-d03

v5.3

merged at v5.4-rc3, but no performance regression of v5.4-rc3

apachebench.requests_per_second

[LKP] [net] 19f92a030c: -37.9% regression

runtime: 300s

concurrency: 4000

cluster: cs-localhost

cpufreq_governor: performance

lkp-bdw-de1

v5.4-rc3

merged at v5.4-rc6, the author doesn’t think it’s a problem

fsmark.files_per_sec

[LKP] [nfsd] 5920afa3c8: 35.8% improvement

iterations: 1x

nr_threads: 64t

disk: 1BRD_48G

fs: f2fs

fs2: nfsv4

filesize: 4M

test_size: 40G

sync_method: NoSync

cpufreq_governor: performance

lkp-ivb-ep01

v5.3-rc2

merged at v5.4-rc1

netpipe.bigger_5M_Mbps.avg

[LKP] [tcp] 1a9914884d: -8.0% regression

test: tcp

cluster: cs-localhost

cpufreq_governor: performance

lkp-ivb-d04

v5.3-rc3

merged at v5.4-rc1 no response from author yet

stress-ng.madvise.ops_per_sec

[LKP] [mm] 87eaceb3fa: -19.6% regression

nr_threads: 100%

disk: 1HDD

testtime: 1s

class: vm

cpufreq_governor: performance

lkp-skl-2sp8

v5.3

merged at v5.4-rc1, the author is working on it

vm-scalability.median

[LKP] [drm/mgag200] 90f479ae51: -18.8% regression

runtime: 300s

size: 8T

test: anon-cow-seq-hugetlb

cpufreq_governor: performance

lkp-knm01

v5.2-rc5

merged at v5.4-rc1, the author is working on it.

vm-scalability.median

[LKP] [drm/ast] 8a99de3dc0: -4.9% regression

runtime: 300s

size: 8T

test: anon-cow-seq

cpufreq_governor: performance

lkp-skl-fpga01

v5.2-rc5

merged at v5.4-rc1, no response from author yet

will-it-scale.per_process_ops

[LKP] [cpuidle] 259231a045: -12.6% regression

nr_task: 100%

mode: process

test: mmap1

cpufreq_governor: performance

lkp-knm01

v5.3-rc2

merged at v5.4-rc1 no response from author yet

    1. stress-ng.madvise.ops_per_sec

stress-ng will stress test a computer system in various selectable ways. It was designed to exercise various physical subsystems of a computer as well as the various operating system kernel interfaces.

 

      1. scenario: 100%-1HDD-1s-vm

 

Commit 87eaceb3fa was reported to have -19.6% regression of stress-ng.madvise.ops_per_sec when comparing to v5.3." It was merged to mainline at v5.4-rc1.

 

Correlated commits

87eaceb3fa

mm: thp: make deferred split shrinker memcg aware

branch

linus/master

report

[LKP] [mm] 87eaceb3fa: -19.6% regression

test scenario

nr_threads: 100%

disk: 1HDD

testtime: 1s

class: vm

cpufreq_governor: performance

test machine

lkp-skl-2sp8

status

merged at v5.4-rc1, the author is working on it

 

    1. vm-scalability.throughput

vm-scalability exercises functions and regions of the mm subsystem of the Linux kernel. We tested on multiple machines such as HSW EP server, during which we reported improvement on one test scenario.

    1. scenario: anon-cow-seq-hugetlb test

 

 

Commit 90f479ae51 was reported to have -18.8% regression of vm-scalability.median when comparing to v5.3-rc5." It was merged to mainline at v5.4-rc1.

 

Correlated commits

90f479ae51

drm/mgag200: Replace struct mga_fbdev with generic framebuffer emulation

branch

linus/master

report

[LKP] [drm/mgag200] 90f479ae51: -18.8% regression

test scenario

runtime: 300s

size: 8T

test: anon-cow-seq-hugetlb

cpufreq_governor: performance

test machine

lkp-knm01

status

merged at v5.4-rc1, the author is working on it.

 

  1. apachebench.requests_per_second

apachebench is a tool for benchmarking your Apache Hypertext Transfer Protocol (HTTP) server. It is designed to give you an impression of how your current Apache installation performs. This especially shows you how many requests per second your Apache installation is capable of serving.

 

Scenario: cs-localhost test

 

 

Commit 19f92a030c was reported to have -37.9% of apachebench.requests_per_second when comparing to v5.4-rc3." It was merged to mainline at v5.4-rc6.

 

Correlated commits

19f92a030c

net: increase SOMAXCONN to 4096

branch

linus/master

report

[LKP] [net] 19f92a030c: -37.9% regression

test scenario

runtime: 300s

concurrency: 4000

cluster: cs-localhost

cpufreq_governor: performance

test machine

lkp-bdw-de1

status

merged at v5.4-rc6, the author don’t think it’s a problem

 

    1. will-it-scale.per_thread_ops

Will-it-scale takes a test case and runs it from 1 through to n parallel copies to see if the test case will scale. It builds both process and threads based tests in order to see any differences between the two.

Scenario: thread malloc1

 

 

Commit 259231a045 was reported to have -12.6% regression of will-it-scale.per_process_ops when comparing to v5.3-rc2." It was merged to mainline at v5.4-rc1.

 

Correlated commits

259231a045

cpuidle: add poll_limit_ns to cpuidle_device structure

branch

linus/master

report

[LKP] [cpuidle] 259231a045: -12.6% regression

test scenario

nr_task: 100%

mode: process

test: mmap1

cpufreq_governor: performance

test machine

lkp-ivb-d02

status

merged at v5.4-rc1


 

  1. Shift-Left Testing

Beyond testing trees in the upstream kernel, 0-Day CI also tests developers’ and maintainers’ trees, which can catch issues earlier and reduce wider impact. We call it “shift-left” testing. During the v5.4 release cycle, 0-Day CI had reported 14 major performance regressions and 16 major improvements by doing shift-left testing. We will share more detailed information together with possible code changes that led to this result for some of these, though the assessment is limited by the test coverage we have now. The whole list is summarized at report summary section.

    1. Report Summary

0-Day CI had reported 14 performance regressions and 16 improvements by doing shift-left testing on developer and maintainer repos.

 

Test Indicator

Mail

Test Scenario

Test Machine

Status

aim7.jobs-per-min

[LKP] [xfs] 646a9fb7fb: -33.0% regression

disk: 4BRD_12G

md: RAID0

fs: xfs

test: disk_wrt

load: 3000

cpufreq_governor: performance

lkp-skl-2sp7

currently not merged, no response from author yet

aim7.jobs-per-min

[LKP] [xfs] fdbb8c5b80: 3.9% improvement

disk: 1BRD_48G

fs: xfs

test: disk_wrt

load: 3000

cpufreq_governor: performance

lkp-skl-2sp7

merged at v5.5-rc1

aim7.jobs-per-min

[LKP] [btrfs] c6bbf24815: -80.1% regression

disk: 4BRD_12G

md: RAID0

fs: btrfs

test: disk_wrt

load: 1500

cpufreq_governor: performance

lkp-csl-2ap2

currently not merged, patch will be discarded

aim7.jobs-per-min

[LKP] [f2fs] fe1897eaa6: -60.9% regression

disk: 4BRD_12G

md: RAID1

fs: f2fs

test: sync_disk_rw

load: 200

cpufreq_governor: performance

lkp-ivb-2ep1

merged at v5.5-rc1, no response from author yet

fio.read_bw_MBps

[LKP] [fs/dax] a70e8083a9: 523.2% improvement

disk: 2pmem

fs: ext4

mount_option: dax

runtime: 200s

nr_task: 50%

time_based: tb

rw: rw

bs: 4k

ioengine: mmap

test_size: 200G

cpufreq_governor: performance

lkp-csl-2sp6

currently not merged

fio.write_bw_MBps

[LKP] [blk] a70e8083a9: -9.3% regression

runtime: 300s

disk: 1HDD

fs: ext4

nr_task: 100%

test_size: 128G

rw: write

bs: 4k

ioengine: sync

cpufreq_governor: performance

lkp-skl-2sp8

currently not merged, no response from author yet

fio.write_bw_MBps

[LKP] [writeback] 2b871886bb: 40.6% improvement

runtime: 300s

disk: 1SSD

fs: xfs

nr_task: 100%

test_size: 128G

rw: write

bs: 4k

ioengine: sync

cpufreq_governor: performance

fs2: nfsv4

lkp-bdw-ex2

currently not merged

fsmark.files_per_sec

[LKP] [writeback] e4f9eb2268: 48.8% improvement

iterations: 1x

nr_threads: 32t

disk: 1HDD

fs: f2fs

filesize: 16MB

test_size: 60G

sync_method: NoSync

nr_directories: 16d

nr_files_per_directory: 256fpd

cpufreq_governor: performance

lkp-csl-2sp7

currently not merged

hackbench.throughput

[LKP] [pipe] 975832d6ec: 15.8% improvement

nr_threads: 100%

mode: process

ipc: pipe

cpufreq_governor: performance

lkp-ivb-d04

currently not merged

hackbench.throughput

[LKP] [sched/fair] b0fb1eb4f0: 1.4% improvement

nr_threads: 50%

mode: process

ipc: socket

cpufreq_governor: performance

lkp-bdw-ep6

merged at v5.5-rc1

lmbench3.PIPE.bandwidth.MB/sec

[LKP] [pipe] 3c0edea9b2: -17.0% regression

test_memory_size: 50%

nr_threads: 100%

mode: development

test: PIPE

cpufreq_governor: performance

lkp-bdw-de1

merged at v5.5-rc1, the regression has been fixed

netperf.Throughput_total_tps

[LKP] [perf/core] 66d258c5b0: 16.7% improvement

ip: ipv4

runtime: 300s

nr_threads: 1

cluster: cs-localhost

test: TCP_CRR

cpufreq_governor: performance

lkp-csl-2ap3

merged at v5.5-rc1

phoronix-test-suite.glmark2.0.score

[LKP] [x86/mm/pat] 8d04a5f97a: -23.7% regression

need_x: true

test: glmark2-1.1.0

cpufreq_governor: performance

lkp-csl-2sp8

merged at v5.5-rc1, the author sent a patch to fix it

phoronix-test-suite.mbw.0.mib_s

[LKP] [perf] 06e0dbcfd3: 12.6% improvement

test: mbw-1.0.0

cpufreq_governor: performance

lkp-nhm-2ep1

currently not merged

phoronix-test-suite.noise-level.0.activity_level

[LKP] [pipe] d60337eff1: 144.0% improvement

test: noise-level-1.1.0

cpufreq_governor: performance

lkp-nhm-2ep1

currently not merged

reaim.jobs_per_min

[LKP] [mm/lru] 29c9588c52: -40.7% regression

runtime: 300s

nr_task: 1000

test: mem_rtns_1

cpufreq_governor: performance

lkp-hsw-ep4

currently not merged, no response from author yet

stress-ng.icache.ops_per_sec

[LKP] [rcu] ed93dfc6bc: -15.0% regression

nr_threads: 100%

disk: 1HDD

testtime: 1s

class: cpu-cache

cpufreq_governor: performance

lkp-csl-2sp5

merged at v5.5-rc1, the author sent a patch to fix it

stress-ng.membarrier.ops_per_sec

[LKP] [rcu] 7107a600da: -39.5% regression

nr_threads: 100%

disk: 1HDD

testtime: 30s

class: cpu-cache

cpufreq_governor: performance

lkp-csl-2sp5

currently not merged, same problem with  [LKP] [rcu] ed93dfc6bc: -15.0% regression

unixbench.score

[LKP] [cpuidle] 331b89c842: 5.6% improvement

runtime: 300s

nr_task: 1

test: shell8

cpufreq_governor: performance

lkp-bdw-ex2

currently not merged

vm-scalability.median

[LKP] [sched/fair] 0b0695f2b3: 3.1% improvement

runtime: 300s

size: 8T

test: anon-cow-seq

cpufreq_governor: performance

lkp-skl-fpga01

merged at v5.5-rc1

vm-scalability.median

[LKP] 3e05ad861b: -86.3% regression

thp_enabled: never

thp_defrag: never

nr_task: 8

nr_pmem: 4

priority: 1

test: swap-w-seq

cpufreq_governor: performance

lkp-hsw-4ex1

currently not merged, no response from author yet

will-it-scale.per_process_ops

[LKP] [mm] 0f5b256b2c: -1.2% regression

nr_task: 100%

mode: process

test: page_fault2

cpufreq_governor: performance

lkp-bdw-ep6

currently not merged, no response from author yet

will-it-scale.per_process_ops

[LKP] [mm] e0e7df8d5b: -7.3% regression

nr_task: 100%

mode: process

test: open1

cpufreq_governor: performance

lkp-bdw-ep6

currently not merged, the author is working on it

will-it-scale.per_process_ops

[LKP] [mm/page_alloc.c] 550521d945: 13.4% improvement

nr_task: 100%

mode: process

test: page_fault2

cpufreq_governor: performance

lkp-skl-2sp8

currently not merged

will-it-scale.per_process_ops

[LKP] [mm] 2eca680594: -2.5% regression

nr_task: 100%

mode: process

test: page_fault2

cpufreq_governor: performance

lkp-bdw-ep6

currently not merged, no response from author yet

will-it-scale.per_process_ops

[LKP] 24480897e7: 36.4% improvement

nr_task: 100%

mode: process

test: getppid1

cpufreq_governor: performance

lkp-knm01

currently not merged

will-it-scale.per_process_ops

[LKP] [mm, meminit] 0d5ac202b7: 24.0% improvement

nr_task: 100%

mode: process

test: page_fault2

cpufreq_governor: performance

lkp-skl-2sp8

currently not merged

will-it-scale.per_process_ops

[LKP] [mm/swap] f7234972f2: -2.3% regression

nr_task: 50%

mode: process

test: brk1

cpufreq_governor: performance

lkp-csl-2ap3

currently not merged, no response from author yet

will-it-scale.per_thread_ops

[LKP] [sched] 2802bafd8f: 2.0% improvement

nr_task: 100%

mode: thread

test: sched_yield

cpufreq_governor: performance

lkp-skl-fpga01

currently not merged

will-it-scale.per_thread_ops

[LKP] [sched/core] 5d7d605642: 2.0% improvement

nr_task: 16

mode: thread

test: sched_yield

cpufreq_governor: performance

lkp-bdw-ep6

merged at v5.5-rc1

    1. aim7.jobs-per-min

aim7 is a traditional UNIX system level benchmark suite which is used to test and measure the performance of a multiuser system. 

 

      1. scenario: sync_disk_rw test on f2fs

 

Commit fe1897eaa6 was reported to have -60.9% regression of aim7.jobs-per-min when comparing to v5.4-rc1." It was merged to mainline at v5.5-rc1.

 

Correlated commits

fe1897eaa6

f2fs: fix to update time in lazytime mode

branch

linus/master

report

[LKP] [f2fs] fe1897eaa6: -60.9% regression

test scenario

disk: 4BRD_12G

md: RAID1

fs: f2fs

test: sync_disk_rw

load: 200

cpufreq_governor: performance

test machine

lkp-ivb-2ep1

status

merged at v5.5-rc1, no response from author yet

 

    1. netperf.Throughput_total_tps

Netperf is a benchmark that can be used to measure the performance of many different types of networking. It provides tests for both unidirectional throughput, and end-to-end latency.

      1. scenario: TCP_CRR test on cs-localhost

 

Commit 66d258c5b0 was reported to have 16.7% improvement of netperf.Throughput_total_tps when comparing to v5.4-rc5. It was merged to mainline at v5.5-rc1.

 

Correlated commits

66d258c5b0

perf/core: Optimize perf_init_event()

branch

linux-next/master

report

[LKP] [perf/core] 66d258c5b0: 16.7% improvement

test scenario

ip: ipv4

runtime: 300s

nr_threads: 1

cluster: cs-localhost

test: TCP_CRR

cpufreq_governor: performance

test machine

lkp-csl-2ap3

status

merged at v5.5-rc1

 

    1. vm-scalability.median

vm-scalability exercises functions and regions of the mm subsystem of the Linux kernel. We tested on multiple machines such as HSW EP server, during which we reported improvement on one test scenario.

Scenario: swap-w-seq test

 

 

Commit 3e05ad861b was reported to have -86.3% regression of vm-scalability.median when comparing to v5.4.

 

Correlated commits

3e05ad861b

ZEN: Implement zen-tune v5.4

branch

zen-kernel-zen-kernel/5.4/zen-sauce

report

[LKP] 3e05ad861b: -86.3% regression

test scenario

thp_enabled: never

thp_defrag: never

nr_task: 8

nr_pmem: 4

priority: 1

test: swap-w-seq

cpufreq_governor: performance

test machine

lkp-hsw-4ex1

status

currently not merged, no response from author yet

 

  1. Latest Release Performance Comparing

 

This session gives some information about the performance difference among different kernel releases, especially between v5.4 and v5.3. There are 50+ performance benchmarks running in 0-Day CI, and we selected 9 benchmarks which historically showed the most regressions/improvements reported by 0-Day CI. Some typical configuration/parameters are used to run the test. For some of the regressions from the comparing, 0-Day did not successfully bisect it thus no related report sent out during the release development period, but it is still worth to check. The root cause to cause the regressions won’t be covered in this session. 

 

In the following figures, the value on the Y-axis is the relative performance number. We used the v5.3 data as the base (performance number is 100).

    1. test suite: vm-scalability

vm-scalability exercises functions and regions of the mm subsystem of the Linux kernel. Below 4 tests show the typical test results. 

 

vm-scalability Test 1

vm-scalability Test 2

vm-scalability Test 3

vm-scalability Test 4

 

Here are the test configuration and performance test summary for above tests:                                                                                                                                                                                                           

 

vm-scalability Test 1 

vm-scalability Test 2 

vm-scalability Test 3

vm-scalability Test 4

test machine

model: Skylake

cpu_number: 104

memory: 192G

model: Skylake

cpu_number: 104

memory: 192G

model: Skylake

cpu_number: 104

memory: 192G

model: Skylake

cpu_number: 104

memory: 192G

runtime

300s

300s

300s

300s

size

512G

8T

No requirement

No requirement

vm-scalability test parameter

test case: anon-w-rand

test case: anon-w-seq


 

test case: lru-file-readonce


 

test case: lru-file-mmap-read

performance summary

vm-scalability.throughput on kernel v5.4 has -6.71% regression when comparing to v5.3

vm-scalability.throughput on kernel v5.4 has -6.19% regression when comparing to v5.3

vm-scalability.throughput on kernel v5.4 has 4.68% improvement when comparing to v5.3

vm-scalability.throughput on kernel v5.4 has 7.6% improvement when comparing to v5.3

 

    1. test suite: will-it-scale

Will-it-scale takes a test case and runs it from 1 through to n parallel copies to see if the test case will scale. It builds both process and threads based tests in order to see any differences between the two.

 

will-it-scale  Test 1

Will-it-scale Test 2

will-it-scale  Test 3

will-it-scale  Test 4

 

Here are the parameters and performance test summary for above tests:                                                                                                                                                                                                                          

 

will-it-scale Test 1 

will-it-scale Test 2 

will-it-scale Test 3 

will-it-scale Test 4 

test machine

model: Knights Mill

brand: Intel(R) Xeon Phi(TM) CPU 7295 @ 1.50GHz

cpu_number: 288

memory: 80G

model: Knights Mill

brand: Intel(R) Xeon Phi(TM) CPU 7295 @ 1.50GHz

cpu_number: 288

memory: 80G

model: Broadwell-EP

brand: Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz

cpu_number: 88

memory: 128G

model: Ivy Bridge

brand: Intel(R) Core(TM) i3-3220 CPU @ 3.30GHz

cpu_number: 4

memory: 8G

nr_task

100%

100%

16

16

will-it-scale test parameter

mode: thread

test: pwrite3

mode: process

test: writeseek2

mode: thread

test: page_fault3

mode: thread

test: malloc1

summary

will-it-scale.per_thread_ops on kernel v5.4 has -66.18% regression when comparing to v5.3

will-it-scale.per_process_ops on kernel v5.4 has -50.62% regression when comparing to v5.3

will-it-scale.per_thread_ops on kernel v5.4 has 24.61% improvement when comparing to v5.3

will-it-scale.per_thread_ops on kernel v5.4 has 169.02% improvement when comparing to v5.3

 

    1. test suite: unixbench

UnixBench is a system benchmark to provide a basic indicator of the performance of a Unix-like system.

 

Unixbench Test 1

 

 

Here are the test configuration and performance test summary for above tests:                                                                                                                                                                                                           

 

Unixbench Test 1 

test machine

model: Coffee Lake

brand: Intel(R) Xeon(R) E-2278G CPU @ 3.40GHz

cpu_number: 16

memory: 32G

disable_latency_stats

1

runtime

300s

nr_task

30%

unixbench test parameter

testcase: syscall

performance summary

unixbench.score on kernel v5.4 is almost the same as that in v5.3

 

    1. test suite: reaim

reaim updates and improves the existing Open Source AIM 7 benchmark. aim7 is a traditional UNIX system level benchmark suite which is used to test and measure the performance of a multiuser system.

 

reaim Test 1                             

reaim Test 2


 

Here are the test configuration and performance test summary for above tests:                                                                                                                                                                                                                      

 

reaim Test 1 

reaim Test 2 

test machine

model: Haswell-EP

brand: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz

cpu_number: 72

memory: 256G

model: Ivy Bridge-EP

brand: Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz

cpu_number: 48

memory: 64G

runtime

300s

300s

nr_task

100%

300t

reaim test parameter

nr_job: 1500

test: five_sec

test: disk_wrt

performance  summary

reaim.jobs_per_min on kernel v5.4 has -78.94% regression when comparing to v5.3

reaim.jobs_per_min on kernel v5.4 has 166.38% improvement when comparing to v5.3

                                                                                                                                                                                                     

    1. test suite: pigz

pigz, which stands for Parallel Implementation of GZip, is a fully functional replacement for gzip that exploits multiple processors and multiple cores to the hilt when compressing data.

pigz Test 1 


 

 

Here are the test configuration and performance test summary for above tests:          

 

 

pigz Test 1

test machine

model: Ivy Bridge

brand: Intel(R) Core(TM) i3-3220 CPU @ 3.30GHz

cpu_number: 4

memory: 4G

nr_threads

100%

pigz Test parameter

blocksize: 512K

performance  summary

pigz.throughput on kernel v5.4 is almost the same as that in v5.3

            

  1. test suite: netperf

Netperf is a benchmark that can be used to measure the performance of many different types of networking. It provides tests for both unidirectional throughput, and end-to-end latency.

 

netperf Test 1

 

Here are the test configuration and performance test summary for above tests:                                                                                                                                                                                                                          

 

netperf Test 1 

test machine

model: Broadwell-EX

brand: Intel(R) Xeon(R) CPU E7-8890 v4 @ 2.20GHz

cpu_number: 160

memory: 256G

disable_latency_stats

1

set_nic_irq_affinity

1

runtime

900s

nr_threads

200%

ip

ipv4

netperf test parameter

test case: TCP_MAERTS

performance  summary

netperf.Throughput_total_Mbps on kernel v5.4 has 27.62% improvement when comparing to v5.3

 

    1. test suite: hackbench

Hackbench is both a benchmark and a stress test for the Linux kernel scheduler. It's  main job is to create a specified number of pairs of schedulable entities (either threads or traditional processes) which communicate via either sockets or pipes and time how long  it takes for each pair to send data back and forth.

hackbench Test 1


 

hackbench Test 2

Here are the test configuration and performance test summary for above tests:                                                                                                                                                                                                           

 

Hackbench Test 1 

Hackbench Test 2 

test machine

model: Skylake

brand: 

cpu_number: 104

memory: 192G

model: Haswell-EP

brand: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz

cpu_number: 72

memory: 256G

disable_latency_stats

1

1

nr_task

100%

1600%

unixbench test parameter

mode: process

ipc: pipe

iterations: 18

mode: threads

ipc: pipe

performance summary

hackbench.throughput on kernel v5.4 has -12.93% regression when comparing to v5.3

hackbench.throughput on kernel v5.4 has -11.8% regression when comparing to v5.3

            

    1. test suite: fio

Fio was originally written to save me the hassle of writing special test case programs when I wanted to test a specific workload, either for performance reasons or to find/reproduce a bug.

fio Test 1 

  

fio Test 2

Here are the test configuration and performance test summary for above tests:                                                                                                                                                                                                                          

 

fio Test 1

fio Test 2

test machine

model: Cascade Lake

brand: Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz

cpu_number: 96

memory: 256G

model: Cascade Lake

brand: Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz

cpu_number: 96

memory: 256G

runtime

200s

200s

file system

ext4

ext4

disk

2pmem

2pmem

boot_params

bp1_memmap: 104G!8G

bp2_memmap: 104G!132G

bp1_memmap: 104G!8G

bp2_memmap: 104G!132G

nr_task

50%

50%

time_based

tb

tb

fio test parameter

fio-setup-basic:

  rw: rw

  bs: 4k

  ioengine: sync

  test_size: 200G

fio-setup-basic:

  rw: read

  bs: 4k

  ioengine: sync

  test_size: 200G

performance  summary

fio.write_bw_MBps on kernel v5.4 has 3.64% improvement when comparing to v5.3

fio.read_bw_MBps on kernel v5.4 has 13.04% improvement when comparing to v5.3

 

    1. test suite: ebizzy

ebizzy is designed to generate a workload resembling common web application server workloads. It is highly threaded, has a large in-memory working set, and allocates and deallocates memory frequently.

ebizzy Test 1

 

 

Here are the test configuration and performance test summary for above test:                                                                                                                                                                                                                          

 

ebizzy Test 1

test machine

model: Broadwell-EX

brand: Intel(R) Xeon(R) CPU E7-8890 v4 @ 2.20GHz

cpu_number: 160

memory: 256G

nr_threads

200%

iterations

100x

ebizzy test parameter

duration: 10s

performance  summary

ebizzy.throughput on kernel v5.4 has 3.19% improvement when comparing to v5.3


 

  1. Test Machines

    1. IVB Desktop

model

Ivy Bridge

brand

Intel(R) Core(TM) i3-3220 CPU @ 3.30GHz

cpu number

8

memory

16G

 

model

Ivy Bridge

brand

Intel(R) Core(TM) i3-3220 CPU @ 3.30GHz

cpu number

4

memory

8G

 

    1. SKL SP

model

Skylake

brand

Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz

cpu number

80

memory

64G

 

    1. BDW EP

model

Broadwell-EP

brand

Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz

cpu number

88

memory

128G

 

    1. HSW EP

model

Haswell-EP

brand

Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz

cpu number

72

memory

128G

 

    1. IVB EP

model

Ivy Bridge-EP

brand

Intel(R) Xeon(R) CPU E5-2690 v2 @ 3.00GHz

cpu number

40

memory

384G

 

model

Ivytown Ivy Bridge-EP

brand

Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz

cpu number

48

memory

64G

 

    1. HSX EX

model

Brickland Haswell-EX

brand

Intel(R) Xeon(R) CPU E7-8890 v3 @ 2.50GHz

cpu number

144

memory

512G

 

cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discount nba jerseys cheap nba jerseys wholesale nba jerseys discont nba jerseys