From: Guoqing Jiang <guoqing.jiang@linux.dev>
To: Jinpu Wang <jinpu.wang@ionos.com>, Haris Iqbal <haris.iqbal@ionos.com>
Cc: jgg@ziepe.ca, leon@kernel.org, linux-rdma@vger.kernel.org
Subject: Re: [PATCH RFC 10/12] RDMA/rtrs-srv: Remove paths_num
Date: Tue, 15 Nov 2022 18:30:56 +0800 [thread overview]
Message-ID: <feee4146-129e-3cac-85ea-397b9b9e02c8@linux.dev> (raw)
In-Reply-To: <CAMGffEmPd4XjjgATYTNHt0HPCp=B9KNFChzmkh9YLp_S=hzDEw@mail.gmail.com>
On 11/15/22 6:01 PM, Jinpu Wang wrote:
> On Tue, Nov 15, 2022 at 10:49 AM Haris Iqbal <haris.iqbal@ionos.com> wrote:
>> On Sun, Nov 13, 2022 at 2:08 AM Guoqing Jiang <guoqing.jiang@linux.dev> wrote:
>>> The paths_num is only increased by rtrs_rdma_connect -> __alloc_path
>>> which is only one time thing, so is the decreasing of it given only
>>> rtrs_srv_close_work -> del_path_from_srv, which means paths_num should
>>> always be 1.
>> It would actually go up to the number of paths a session will have in
>> a multipath setup. It is the exact counter part of paths_num in the
>> structure rtrs_clt_sess. But whereas on the client side, the number is
>> used to access the path list for making decisions in multipathing IO
>> like round-robin, etc. On the server side, I don't see the use of it.
>> Maybe just for sanity checks.
>>
>> @Jinpu Any thoughts?
> Yes, the idea is RTRS can have many paths, not only one, and you can
> add/remove path at run time,
> so not a one time thing.
Got it, thanks for your review.
Guoqing
next prev parent reply other threads:[~2022-11-15 10:31 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-13 1:08 [PATCH RFC 00/12] Misc changes for rtrs Guoqing Jiang
2022-11-13 1:08 ` [PATCH RFC 01/12] RDMA/rtrs-srv: Remove ib_dev_count from rtrs_srv_ib_ctx Guoqing Jiang
2022-11-14 7:39 ` Jinpu Wang
2022-11-14 8:00 ` Guoqing Jiang
2022-11-14 8:24 ` Jinpu Wang
2022-11-14 8:45 ` Guoqing Jiang
2022-11-14 13:36 ` Haris Iqbal
2022-11-15 10:22 ` Guoqing Jiang
2022-11-13 1:08 ` [PATCH RFC 02/12] RDMA/rtrs-srv: Refactor rtrs_srv_rdma_cm_handler Guoqing Jiang
2022-11-14 14:39 ` Haris Iqbal
2022-11-15 10:24 ` Guoqing Jiang
2022-11-13 1:08 ` [PATCH RFC 03/12] RDMA/rtrs-srv: Only close srv_path if it is just allocated Guoqing Jiang
2022-11-14 16:18 ` Haris Iqbal
2022-11-15 10:24 ` Guoqing Jiang
2022-11-15 10:31 ` Jinpu Wang
2022-11-13 1:08 ` [PATCH RFC 04/12] RDMA/rtrs-srv: refactor the handling of failure case in map_cont_bufs Guoqing Jiang
2022-11-14 16:21 ` Haris Iqbal
2022-11-13 1:08 ` [PATCH RFC 05/12] RDMA/rtrs-srv: Correct the checking of ib_map_mr_sg Guoqing Jiang
2022-11-15 11:46 ` Jinpu Wang
2022-11-16 1:13 ` Guoqing Jiang
2022-11-16 5:44 ` Jinpu Wang
2022-11-13 1:08 ` [PATCH RFC 06/12] RDMA/rtrs-clt: " Guoqing Jiang
2022-11-15 11:49 ` Jinpu Wang
2022-11-13 1:08 ` [PATCH RFC 07/12] RDMA/rtrs-srv: Remove outdated comments from create_con Guoqing Jiang
2022-11-14 16:22 ` Haris Iqbal
2022-11-13 1:08 ` [PATCH RFC 08/12] RDMA/rtrs: Kill recon_cnt from several structs Guoqing Jiang
2022-11-15 9:39 ` Haris Iqbal
2022-11-15 9:53 ` Jinpu Wang
2022-11-15 9:58 ` Jinpu Wang
2022-11-15 10:33 ` Guoqing Jiang
2022-11-13 1:08 ` [PATCH RFC 09/12] RDMA/rtrs: Clean up rtrs_rdma_dev_pd_ops Guoqing Jiang
2022-11-15 9:18 ` Haris Iqbal
2022-11-13 1:08 ` [PATCH RFC 10/12] RDMA/rtrs-srv: Remove paths_num Guoqing Jiang
2022-11-15 9:48 ` Haris Iqbal
2022-11-15 10:01 ` Jinpu Wang
2022-11-15 10:30 ` Guoqing Jiang [this message]
2022-11-13 1:08 ` [PATCH RFC 11/12] RDMA/rtrs-srv: fix several issues in rtrs_srv_destroy_path_files Guoqing Jiang
2022-11-14 16:22 ` Haris Iqbal
2022-11-13 1:08 ` [PATCH RFC 12/12] RDMA/rtrs-srv: Remove kobject_del from rtrs_srv_destroy_once_sysfs_root_folders Guoqing Jiang
2022-11-14 16:23 ` Haris Iqbal
2022-11-14 8:32 ` [PATCH RFC 00/12] Misc changes for rtrs Leon Romanovsky
2022-11-14 8:46 ` Guoqing Jiang
2022-11-17 9:52 ` Leon Romanovsky
2022-11-17 10:06 ` Guoqing Jiang
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=feee4146-129e-3cac-85ea-397b9b9e02c8@linux.dev \
--to=guoqing.jiang@linux.dev \
--cc=haris.iqbal@ionos.com \
--cc=jgg@ziepe.ca \
--cc=jinpu.wang@ionos.com \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
/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.