From: "Lluís Vilanova" <vilanova@ac.upc.edu>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: "Emilio G. Cota" <cota@braap.org>,
QEMU Developers <qemu-devel@nongnu.org>,
Stefan Hajnoczi <stefanha@redhat.com>,
Markus Armbruster <armbru@redhat.com>
Subject: Re: [Qemu-devel] [PATCH v6 01/22] instrument: Add documentation
Date: Fri, 29 Sep 2017 16:16:41 +0300 [thread overview]
Message-ID: <87shf5zlty.fsf@frigg.lan> (raw)
In-Reply-To: <87o9pywt8k.fsf@frigg.lan> (=?utf-8?Q?=22Llu=C3=ADs?= Vilanova"'s message of "Mon, 25 Sep 2017 21:03:39 +0300")
Lluís Vilanova writes:
[...]
> This was working on a much older version of instrumentation for QEMU, but I can
> implement something that does the first use-case point above and some filtering
> example (second use-case point) to see what's the performance difference.
Ok, so here's some numbers for the discussion (booting Emilio's ARM full system
image that immediately shuts down):
* Without instrumentation
real 0m10,099s
user 0m9,876s
sys 0m0,128s
* Count number of memory access writes, by instrumenting only when they are
executed
real 0m15,896s
user 0m15,752s
sys 0m0,108s
* Counting same, but the filtering is done at translation time (i.e., not
generate an execute-time callback if it's not a write)
real 0m11,084s
user 0m10,880s
sys 0m0,112s
As Peter said, the filtering can be added into the API to take advantage of
this "speedup", without exposing translation vs execution time callbacks.
* Counting number of executed instructions, by instrumenting the beginning of
each one of them
real 0m24,583s
user 0m24,352s
sys 0m0,184s
* Counting same, but per-TB numbers are collected at translation-time, and we
only generate a per-TB execution time callback to add the corresponding number
of instructions for that TB
real 0m11,151s
user 0m10,952s
sys 0m0,092s
This really needs to expose translation vs execution time callbacks to take
advantage of this "speedup".
Cheers,
Lluis
next prev parent reply other threads:[~2017-09-29 13:17 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-13 9:53 [Qemu-devel] [PATCH v6 00/22] instrument: Add basic event instrumentation Lluís Vilanova
2017-09-13 9:57 ` [Qemu-devel] [PATCH v6 01/22] instrument: Add documentation Lluís Vilanova
2017-09-14 14:41 ` Peter Maydell
2017-09-15 13:39 ` Lluís Vilanova
2017-09-18 14:41 ` Peter Maydell
2017-09-18 17:09 ` Lluís Vilanova
2017-09-18 17:42 ` Peter Maydell
2017-09-19 13:50 ` Emilio G. Cota
2017-09-25 18:03 ` Lluís Vilanova
2017-09-25 19:42 ` Emilio G. Cota
2017-09-26 16:49 ` Lluís Vilanova
2017-09-29 13:16 ` Lluís Vilanova [this message]
2017-09-29 17:59 ` Emilio G. Cota
2017-09-29 21:46 ` Lluís Vilanova
2017-09-30 18:09 ` Emilio G. Cota
2017-10-04 23:28 ` Lluís Vilanova
2017-10-05 0:50 ` Emilio G. Cota
2017-10-06 15:07 ` Lluís Vilanova
2017-10-06 17:59 ` Emilio G. Cota
2017-10-15 16:30 ` Lluís Vilanova
2017-10-15 16:47 ` Peter Maydell
2017-10-21 14:05 ` Lluís Vilanova
2017-10-21 16:56 ` Peter Maydell
2017-10-21 17:12 ` Alex Bennée
2017-09-19 13:09 ` Peter Maydell
2017-09-18 14:33 ` Stefan Hajnoczi
2017-09-18 14:40 ` Stefan Hajnoczi
2017-09-13 10:01 ` [Qemu-devel] [PATCH v6 02/22] instrument: Add configure-time flag Lluís Vilanova
2017-09-13 10:05 ` [Qemu-devel] [PATCH v6 03/22] instrument: Add generic library loader Lluís Vilanova
2017-09-18 14:34 ` Stefan Hajnoczi
2017-09-13 10:09 ` [Qemu-devel] [PATCH v6 04/22] instrument: [linux-user] Add command line " Lluís Vilanova
2017-09-13 10:13 ` [Qemu-devel] [PATCH v6 05/22] instrument: [bsd-user] " Lluís Vilanova
2017-09-13 10:17 ` [Qemu-devel] [PATCH v6 06/22] instrument: [softmmu] " Lluís Vilanova
2017-09-13 10:21 ` [Qemu-devel] [PATCH v6 07/22] instrument: [qapi] Add " Lluís Vilanova
2017-09-13 10:25 ` [Qemu-devel] [PATCH v6 08/22] instrument: [hmp] " Lluís Vilanova
2017-09-13 10:30 ` [Qemu-devel] [PATCH v6 09/22] instrument: Add basic control interface Lluís Vilanova
2017-09-13 10:34 ` [Qemu-devel] [PATCH v6 10/22] instrument: Add support for tracing events Lluís Vilanova
2017-09-13 10:38 ` [Qemu-devel] [PATCH v6 11/22] instrument: Track vCPUs Lluís Vilanova
2017-09-13 10:42 ` [Qemu-devel] [PATCH v6 12/22] instrument: Add event 'guest_cpu_enter' Lluís Vilanova
2017-09-13 10:46 ` [Qemu-devel] [PATCH v6 13/22] instrument: Support synchronous modification of vCPU state Lluís Vilanova
2017-09-13 10:50 ` [Qemu-devel] [PATCH v6 14/22] exec: Add function to synchronously flush TB on a stopped vCPU Lluís Vilanova
2017-09-13 10:54 ` [Qemu-devel] [PATCH v6 15/22] instrument: Add event 'guest_cpu_exit' Lluís Vilanova
2017-09-13 10:58 ` [Qemu-devel] [PATCH v6 16/22] instrument: Add event 'guest_cpu_reset' Lluís Vilanova
2017-09-13 11:02 ` [Qemu-devel] [PATCH v6 17/22] trace: Introduce a proper structure to describe memory accesses Lluís Vilanova
2017-09-13 11:06 ` [Qemu-devel] [PATCH v6 18/22] instrument: Add event 'guest_mem_before_trans' Lluís Vilanova
2017-09-13 11:10 ` [Qemu-devel] [PATCH v6 19/22] instrument: Add event 'guest_mem_before_exec' Lluís Vilanova
2017-09-13 11:14 ` [Qemu-devel] [PATCH v6 20/22] instrument: Add event 'guest_user_syscall' Lluís Vilanova
2017-09-13 11:18 ` [Qemu-devel] [PATCH v6 21/22] instrument: Add event 'guest_user_syscall_ret' Lluís Vilanova
2017-09-13 11:22 ` [Qemu-devel] [PATCH v6 22/22] instrument: Add API to manipulate guest memory Lluís Vilanova
2017-09-13 11:42 ` [Qemu-devel] [PATCH v6 00/22] instrument: Add basic event instrumentation no-reply
2017-09-22 22:48 ` Emilio G. Cota
2017-09-25 18:07 ` Lluís Vilanova
2017-09-25 18:55 ` Emilio G. Cota
2017-09-26 8:17 ` Lluís Vilanova
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=87shf5zlty.fsf@frigg.lan \
--to=vilanova@ac.upc.edu \
--cc=armbru@redhat.com \
--cc=cota@braap.org \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
/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.