From: John David Anglin <[email protected]>
To: Helge Deller <[email protected]>, Jens Axboe <[email protected]>,
[email protected], [email protected],
James Bottomley <[email protected]>
Subject: Re: io_uring failure on parisc with VIPT caches
Date: Wed, 15 Feb 2023 11:18:10 -0500 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On 2023-02-15 10:52 a.m., Helge Deller wrote:
>>>> Are they from the kernel side, if the lower bits mean we end up
>>>> with the same coloring? Because I think this is a bit of a big
>>>> hammer, in terms of overhead for flushing. As an example, on arm64
>>>> that is perfectly fine with the existing code, it's about a 20-25%
>>>> performance hit.
>>>
>>> The io_uring-test testcase still works on rp3440 with the kernel
>>> flushes removed.
>>
>> That's what I suspected, the important bit here is just aligning it for
>> identical coloring. Can you confirm if the below works for you? Had to
>> fiddle it a bit to get it to work without coloring.
>
> Yes, the patch works for me on 32- and 64-bit, even with PA8900 CPUs...
>
> Is there maybe somewhere a more detailled testcase which I could try too?
We need to look at liburing and mariadb testsuites. Mariadb testsuite failed last night
on rp3440. So, I don't think we have a full solution for machines with PA8800 and PA8900
CPUs.
As I have said in the past, I don't think we have a consistent alias boundary for these
machines because of their L2 cache design.
--
John David Anglin [email protected]
prev parent reply other threads:[~2023-02-15 16:18 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-12 9:47 io_uring failure on parisc (32-bit userspace and 64-bit kernel) Helge Deller
2023-02-12 13:16 ` Jens Axboe
2023-02-12 13:28 ` Helge Deller
2023-02-12 13:35 ` Jens Axboe
2023-02-12 14:00 ` Jens Axboe
2023-02-12 14:03 ` Helge Deller
2023-02-12 19:35 ` Helge Deller
2023-02-12 19:42 ` Jens Axboe
2023-02-12 20:01 ` Helge Deller
2023-02-12 21:48 ` Jens Axboe
2023-02-12 22:20 ` Helge Deller
2023-02-12 22:31 ` Helge Deller
2023-02-13 16:15 ` Jens Axboe
2023-02-13 20:59 ` Helge Deller
2023-02-13 21:05 ` Jens Axboe
2023-02-13 22:05 ` Helge Deller
2023-02-13 22:50 ` John David Anglin
2023-02-14 23:09 ` io_uring failure on parisc with VIPT caches Helge Deller
2023-02-14 23:29 ` Jens Axboe
2023-02-15 2:12 ` John David Anglin
2023-02-15 15:16 ` Jens Axboe
2023-02-15 15:52 ` Helge Deller
2023-02-15 15:56 ` Jens Axboe
2023-02-15 16:02 ` Helge Deller
2023-02-15 16:04 ` Jens Axboe
2023-02-15 21:40 ` Helge Deller
2023-02-15 23:04 ` Jens Axboe
2023-02-15 16:38 ` John David Anglin
2023-02-15 17:01 ` Jens Axboe
2023-02-15 19:00 ` Jens Axboe
2023-02-15 19:16 ` Jens Axboe
2023-02-15 20:27 ` John David Anglin
2023-02-15 20:37 ` Jens Axboe
2023-02-15 21:06 ` John David Anglin
2023-02-15 21:38 ` Jens Axboe
2023-02-15 21:39 ` John David Anglin
2023-02-15 22:10 ` John David Anglin
2023-02-15 23:02 ` Jens Axboe
2023-02-15 23:43 ` John David Anglin
2023-02-16 2:40 ` John David Anglin
2023-02-16 2:50 ` Jens Axboe
2023-02-16 8:24 ` Helge Deller
2023-02-16 15:22 ` Jens Axboe
2023-02-16 20:35 ` John David Anglin
2023-02-15 23:03 ` Jens Axboe
2023-02-15 19:20 ` John David Anglin
2023-02-15 19:24 ` Jens Axboe
2023-02-15 16:18 ` John David Anglin [this message]
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 \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox