public inbox for [email protected]
 help / color / mirror / Atom feed
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]


      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