From: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
To: kvm-ppc@vger.kernel.org
Subject: FYI - current trace results
Date: Tue, 15 Jul 2008 11:53:28 +0000 [thread overview]
Message-ID: <487C8FB8.8050906@linux.vnet.ibm.com> (raw)
As part of the preparation to extend our code with paravirtual features
to speed up the guest execution I used the new kvmtrace code and took a
trace of a ubuntu_8.04 guest booting on a ubuntu_8.04 host.
The full log is ~800M but I wanted to post the instruction emulation
summary for all interested parties.
Based on that I want to compare the behavior later on when we use the PV
features.
I think about tracing segments like "early boot", "init scripts" and
some basic workloads separate, but for now the full boot is all I have.
@Hollis - I'll try contact you on IRC later today to discuss about PV
potential of SPRG0-SPRG3 (and maybe other SPR's)
mnemonic + count
---------------+-----------
mtspr | 1154660
mfspr | 1083036
wrteei | 347988
tlbwe | 296970
mfmsr | 253217
rfi | 210161
wrtee | 184312
mtmsr | 87671
tlbsx | 18837
lbz | 8497
lbzx | 4710
stb | 2144
mfdcr | 1696
stbx | 1550
mtdcr | 1282
sthbrx | 389
stwbrx | 224
iccci | 204
lwbrx | 84
lhbrx | 25
lwz | 1
stw | 1
sum = 3657659
mnemonic-spr + count
---------------+-----------
mfspr-SPRG3 | 208616
mtspr-SPRG4 | 164330
mtspr-SPRG0 | 164330
mtspr-SPRG1 | 164330
mfspr-SPRG0 | 164330
mfspr-SPRG1 | 164330
mfspr-SRR1 | 123952
mtspr-SRR0 | 123814
mtspr-SRR1 | 123814
mtspr-MMUCR | 111975
mfspr-MMUCR | 111973
mfspr-SRR0 | 105592
mtspr-SPRG5 | 102354
mtspr-SPRG7 | 102354
mfspr-PID | 102199
mfspr-DEAR | 67266
mtspr-DEC | 61666
mfspr-ESR | 34774
mtspr-TSR | 30833
mtspr-SPRG3 | 2696
mtspr-PID | 2144
mfspr-PVR | 4
mtspr-IVOR8 | 1
mtspr-IVOR9 | 1
mtspr-IVOR2 | 1
mtspr-IVOR3 | 1
mtspr-IVOR0 | 1
mtspr-IVOR1 | 1
mtspr-IVOR6 | 1
mtspr-IVOR7 | 1
mtspr-IVOR4 | 1
mtspr-IVOR5 | 1
mtspr-IVOR14 | 1
mtspr-IVOR15 | 1
mtspr-IVOR10 | 1
mtspr-IVOR11 | 1
mtspr-IVOR12 | 1
mtspr-IVOR13 | 1
mtspr-TCR | 1
mtspr-IVPR | 1
mtspr-TBWL | 1
mtspr-TBWU | 1
sum = 2237696
mnemonic-dcr + count
---------------+-----------
mtdcr-00C2 | 849
mfdcr-00C2 | 848
mfdcr-00C6 | 842
mtdcr-00C0 | 425
mtdcr-00C5 | 4
mtdcr-00C4 | 3
mfdcr-00C4 | 3
mfdcr-00C5 | 3
mtdcr-00C3 | 1
sum = 2978
mnemonic-tlb + count
---------------+-----------
tlbwe-PAGEID | 133491
tlbwe-ATTRIB | 86348
tlbwe-XLAT | 77131
sum = 296970
--
Grüsse / regards,
Christian Ehrhardt
IBM Linux Technology Center, Open Virtualization
reply other threads:[~2008-07-15 11:53 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=487C8FB8.8050906@linux.vnet.ibm.com \
--to=ehrhardt@linux.vnet.ibm.com \
--cc=kvm-ppc@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.