From: Dominik Csapak <d.csapak@proxmox.com>
To: Friedrich Weber <f.weber@proxmox.com>,
Proxmox VE development discussion <pve-devel@lists.proxmox.com>,
Thomas Lamprecht <t.lamprecht@proxmox.com>
Subject: Re: [pve-devel] [RFC PATCH pve-cluster] fix #5728: pmxcfs: allow bigger writes than 4k for fuse
Date: Mon, 23 Sep 2024 14:03:22 +0200 [thread overview]
Message-ID: <c91c3fc3-6491-4f67-b68c-80b9ea7a99ab@proxmox.com> (raw)
In-Reply-To: <5b613718-953b-4450-9979-24b123d00b09@proxmox.com>
On 9/23/24 14:00, Friedrich Weber wrote:
> On 23/09/2024 11:17, Dominik Csapak wrote:
>> [...]
>> so i did some benchmarks (mostly disk writes) and wrote the short script
>> below
>> (maybe we can reuse that?)
>>
>> ----8<----
>> use strict;
>> use warnings;
>>
>> use PVE::Tools;
>>
>> my $size = shift;
>>
>> sub get_bytes_written {
>> my $fh = IO::File->new("/proc/diskstats", "r");
>> die if !$fh;
>> my $bytes = undef;
>> while (defined(my $line = <$fh>)) {
>> if ($line =~ m/sdb/) {
>> my @fields = split(/\s+/, $line);
>> $bytes = $fields[10] * 512;
>> }
>> }
>> return $bytes;
>> }
>>
>> sub test_write {
>> my ($k) = @_;
>> system("rm /etc/pve/testfile");
>> my $data = "a"x($k*1024);
>> system("sync; echo -n 3> /proc/sys/vm/drop_caches");
>
> I'm not sure this actually drops the caches: Without the space between
> `3` and `>` I think this redirects fd 3 to that file (so doesn't
> actually write the `3`)? I didn't run the script though, so not sure if
> it makes any difference for the results.
ah yeah, i noticed, but forgot to answer here. i fixed it here locally and
rerun the tests but had the same results (+- a bit of variation)
_______________________________________________
pve-devel mailing list
pve-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
next prev parent reply other threads:[~2024-09-23 12:03 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-19 9:52 Dominik Csapak
2024-09-19 12:01 ` Thomas Lamprecht
2024-09-19 12:45 ` Dominik Csapak
2024-09-19 14:57 ` Thomas Lamprecht
2024-09-20 4:04 ` Esi Y via pve-devel
2024-09-20 5:29 ` Esi Y via pve-devel
[not found] ` <CABtLnHoQFAUN0KcahbMF6hoX=WTfL8bHL0St77gQMSaojVGhBA@mail.gmail.com>
2024-09-20 7:32 ` Dominik Csapak
2024-09-20 6:16 ` Dominik Csapak
2024-09-22 9:25 ` Dietmar Maurer
2024-09-23 9:17 ` Dominik Csapak
2024-09-23 11:48 ` Filip Schauer
2024-09-23 14:08 ` Filip Schauer
2024-09-23 12:00 ` Friedrich Weber
2024-09-23 12:03 ` Dominik Csapak [this message]
2024-09-19 12:23 ` Esi Y via pve-devel
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=c91c3fc3-6491-4f67-b68c-80b9ea7a99ab@proxmox.com \
--to=d.csapak@proxmox.com \
--cc=f.weber@proxmox.com \
--cc=pve-devel@lists.proxmox.com \
--cc=t.lamprecht@proxmox.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.
Service provided by Proxmox Server Solutions GmbH | Privacy | Legal