Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 04 Jun 2021 14:59:19 +0000
From:      bugzilla-noreply@freebsd.org
To:        virtualization@FreeBSD.org
Subject:   [Bug 216759] [kern] Memory speed with small blocks (1K) up to 35 times slower than host system (under QEMU emulation, but not only)
Message-ID:  <bug-216759-27103-VUvSuxvFqi@https.bugs.freebsd.org/bugzilla/>
In-Reply-To: <bug-216759-27103@https.bugs.freebsd.org/bugzilla/>
References:  <bug-216759-27103@https.bugs.freebsd.org/bugzilla/>

next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D216759

--- Comment #24 from rainer@ultra-secure.de ---
I still have very slow IO in FreeBSD 13.0 amd64 on KVM.

Even with this kvmclock driver (compile from ports as of today).

Host:

ii  qemu-system-x86                      1:2.11+dfsg-1ubuntu7.23=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20
amd64        QEMU full system emulation binaries (x86)
Linux ewos1-com17-prod 5.8.0-48-generic #54~20.04.1-Ubuntu SMP Sat Mar 20
13:40:25 UTC 2021 x86_64 x86_64 x86_64 GNU/Linux


Guest:

(freebsd <tests>) 0 # uname -a
FreeBSD freebsd 13.0-RELEASE-p1 FreeBSD 13.0-RELEASE-p1 #0: Wed May 26 22:1=
5:09
UTC 2021=20=20=20=20
root@amd64-builder.daemonology.net:/usr/obj/usr/src/amd64.amd64/sys/GENERIC=
=20
amd64


(freebsd </root>) 1 # kldload kvmclock=20
(freebsd </root>) 0 # sysctl kern.timecounter
kern.timecounter.tsc_shift: 1
kern.timecounter.smp_tsc_adjust: 0
kern.timecounter.smp_tsc: 0
kern.timecounter.invariant_tsc: 0
kern.timecounter.fast_gettime: 1
kern.timecounter.tick: 1
kern.timecounter.choice: kvmclock(975) i8254(0) ACPI-fast(900) TSC-low(-100)
dummy(-1000000)
kern.timecounter.hardware: kvmclock
kern.timecounter.alloweddeviation: 5
kern.timecounter.timehands_count: 2
kern.timecounter.stepwarnings: 0
kern.timecounter.tc.kvmclock.quality: 975
kern.timecounter.tc.kvmclock.frequency: 1000000000
kern.timecounter.tc.kvmclock.counter: 2592740499
kern.timecounter.tc.kvmclock.mask: 4294967295
kern.timecounter.tc.i8254.quality: 0
kern.timecounter.tc.i8254.frequency: 1193182
kern.timecounter.tc.i8254.counter: 56633
kern.timecounter.tc.i8254.mask: 65535
kern.timecounter.tc.ACPI-fast.quality: 900
kern.timecounter.tc.ACPI-fast.frequency: 3579545
kern.timecounter.tc.ACPI-fast.counter: 15142699
kern.timecounter.tc.ACPI-fast.mask: 16777215
kern.timecounter.tc.TSC-low.quality: -100
kern.timecounter.tc.TSC-low.frequency: 1300025233
kern.timecounter.tc.TSC-low.counter: 3482345276
kern.timecounter.tc.TSC-low.mask: 4294967295
(freebsd </root>) 0 # time dc3dd wipe=3D/dev/vtbd1

dc3dd 7.2.646 started at 2021-06-04 14:54:43 +0200
compiled options:
command line: dc3dd wipe=3D/dev/vtbd1
device size: 209715200 sectors (probed),   107,374,182,400 bytes
sector size: 512 bytes (probed)
  2559508480 bytes ( 2.4 G ) copied (  2% ),  145 s, 17 M/s=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20

input results for pattern `00':
   4999040 sectors in

output results for device `/dev/vtbd1':
   4999040 sectors out

dc3dd aborted at 2021-06-04 14:57:07 +0200

dc3dd wipe=3D/dev/vtbd1  0.79s user 1.55s system 1% cpu 2:24.62 total


(freebsd </root>) 1 # sysctl kern.timecounter.hardware=3DTSC-low
kern.timecounter.hardware: kvmclock -> TSC-low
(freebsd </root>) 0 # time dc3dd wipe=3D/dev/vtbd1=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20

dc3dd 7.2.646 started at 2021-06-04 14:59:07 +0200
compiled options:
command line: dc3dd wipe=3D/dev/vtbd1
device size: 209715200 sectors (probed),   107,374,182,400 bytes
sector size: 512 bytes (probed)
  2588770304 bytes ( 2.4 G ) copied (  2% ),  150 s, 16 M/s=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20

input results for pattern `00':
   5056192 sectors in

output results for device `/dev/vtbd1':
   5056192 sectors out

dc3dd aborted at 2021-06-04 15:01:37 +0200

dc3dd wipe=3D/dev/vtbd1  0.99s user 1.53s system 1% cpu 2:29.96 total


This volume should be good for 5000 IOPs and 250MB/s.

--=20
You are receiving this mail because:
You are the assignee for the bug.=



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-216759-27103-VUvSuxvFqi>