From: Long Li <leo.lilong@huawei.com>
To: <leo.lilong@huaweicloud.com>, <josef@toxicpanda.com>, <axboe@kernel.dk>
Cc: <linux-block@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<yi.zhang@huawei.com>, <yangerkun@huawei.com>,
<lonuxli.64@gmail.com>
Subject: Re: [PATCH 0/4] nbd: replace socks pointer array with xarray to eliminate queue freeze
Date: Mon, 20 Apr 2026 10:46:21 +0800 [thread overview]
Message-ID: <aeWTfZ5G5lXT9lZo@localhost.localdomain> (raw)
In-Reply-To: <20260327091223.4147956-1-leo.lilong@huaweicloud.com>
On Fri, Mar 27, 2026 at 05:12:19PM +0800, leo.lilong@huaweicloud.com wrote:
> From: Long Li <leo.lilong@huawei.com>
>
> Hi,
>
> Commit b98e762e3d ("nbd: freeze the queue while we're adding
> connections") introduced blk_mq_freeze_queue() in the add-socket path
> to prevent use-after-free when krealloc() relocates the config->socks
> array while I/O is in flight. However, freezing the queue on every
> connection setup introduces significant latency when establishing a
> large number of connections.
>
> This series eliminates the queue freeze by replacing the
> krealloc-based struct nbd_sock **socks array with a struct xarray.
> The xarray provides RCU-safe pointer publishing: each nbd_sock is
> fully initialized before being stored via xa_store(), and concurrent
> readers access individual entries through xa_load() without ever
> holding a reference to the array itself. This removes the possibility
> of UAF on array reallocation, making the queue freeze unnecessary.
>
> The following test was performed with 256 connections on a local
> nbd-server:
>
> nbd-server -M 256 -C /etc/nbd-server/config
> time nbd-client 127.0.0.1 10809 /dev/nbd0 -N myexport -C 256
>
> Before: real 4.510s user 0.004s sys 0.038s
> After: real 0.263s user 0.009s sys 0.032s
>
> Connection setup time is reduced by ~94%.
>
> Long Li (4):
> nbd: simplify find_fallback() by removing redundant logic
> nbd: replace socks pointer array with xarray
> nbd: remove redundant num_connections boundary checks
> nbd: remove queue freeze in nbd_add_socket
>
> drivers/block/nbd.c | 201 +++++++++++++++++++++++---------------------
> 1 file changed, 106 insertions(+), 95 deletions(-)
>
> --
> 2.39.2
>
Friendly ping ...
prev parent reply other threads:[~2026-04-20 2:52 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-27 9:12 [PATCH 0/4] nbd: replace socks pointer array with xarray to eliminate queue freeze leo.lilong
2026-03-27 9:12 ` [PATCH 1/4] nbd: simplify find_fallback() by removing redundant logic leo.lilong
2026-03-27 9:12 ` [PATCH 2/4] nbd: replace socks pointer array with xarray leo.lilong
2026-03-27 9:12 ` [PATCH 3/4] nbd: remove redundant num_connections boundary checks leo.lilong
2026-03-27 9:12 ` [PATCH 4/4] nbd: remove queue freeze in nbd_add_socket leo.lilong
2026-04-20 2:46 ` Long Li [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 \
--in-reply-to=aeWTfZ5G5lXT9lZo@localhost.localdomain \
--to=leo.lilong@huawei.com \
--cc=axboe@kernel.dk \
--cc=josef@toxicpanda.com \
--cc=leo.lilong@huaweicloud.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lonuxli.64@gmail.com \
--cc=yangerkun@huawei.com \
--cc=yi.zhang@huawei.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox