From: Christoph Hellwig <hch@infradead.org>
To: Andy Grover <agrover@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>,
target-devel@vger.kernel.org, linux-scsi@vger.kernel.org
Subject: Re: [PATCH 20/20] target: change alloc_task call to take *cdb, not *cmd
Date: Mon, 11 Jul 2011 11:28:15 -0400 [thread overview]
Message-ID: <20110711152815.GA20603@infradead.org> (raw)
In-Reply-To: <4E1A2AAF.6080705@redhat.com>
On Sun, Jul 10, 2011 at 03:41:51PM -0700, Andy Grover wrote:
> We can assume each se_cmd only needs 1 se_task???
>
> I couldn't see where the max sectors per se_cmd was limited, therefore
> we needed to support cmds being broken up into
> se_sub_dev.max_sectors-size chunks, and therefore being >1 se_task per
> se_cmd, for all backstores not just pscsi?
The most important backend, iblock already handles arbitrarily sized
payloads by using multiple bios internally, which is much lower overhead
than using the multiple task complexity, and the ramdisk code has no
inherent limitation either. The file code has a limitation on the
number of iovecs accepted by the kernel, and only the pscsi backend
really needs multiple "tasks".
Given that the performance of iblock is the important one streamline
the path for this backend as much as possible sounds like a good idea.
next prev parent reply other threads:[~2011-07-11 15:28 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-07 22:33 [0/20] Patches from June 28 v2 Andy Grover
2011-07-07 22:33 ` [PATCH 01/20] target: Remove ifdeffed code in t_g_process_write Andy Grover
2011-07-07 22:33 ` [PATCH 02/20] target: Pass 2nd param of transport_split_cdb by value Andy Grover
2011-07-07 22:33 ` [PATCH 03/20] target: Make all control CDBs scatter-gather Andy Grover
2011-07-08 19:57 ` Christoph Hellwig
2011-07-09 0:02 ` Andy Grover
2011-07-09 0:35 ` Andy Grover
2011-07-07 22:33 ` [PATCH 04/20] target: Enforce 1 page max for control cdb buffer sizes Andy Grover
2011-07-08 19:58 ` Christoph Hellwig
2011-07-07 22:33 ` [PATCH 05/20] target: Remove direct ramdisk code Andy Grover
2011-07-08 19:59 ` Christoph Hellwig
2011-07-07 22:33 ` [PATCH 06/20] target: Eliminate usage of struct se_mem Andy Grover
2011-07-08 20:13 ` Christoph Hellwig
2011-07-09 0:38 ` Andy Grover
2011-07-07 22:33 ` [PATCH 07/20] target: Rename task_sg_num to task_sg_nents Andy Grover
2011-07-07 22:33 ` [PATCH 08/20] target: Remove custom debug macros for pr_debug. Use pr_err() Andy Grover
2011-07-07 22:33 ` [PATCH 09/20] target: Remove custom debug macros in non-iscsi fabrics Andy Grover
2011-07-07 22:33 ` [PATCH 10/20] target/iscsi: Remove iscsi_target_debug.h and usage of TRACE() & printk() Andy Grover
2011-07-07 22:33 ` [PATCH 11/20] target/iscsi: Remove SE_CMD macro Andy Grover
2011-07-07 22:33 ` [PATCH 12/20] target: Set WSNZ=1 in block limits VPD. Abort if WRITE_SAME sectors = 0 Andy Grover
2011-07-07 22:33 ` [PATCH 13/20] target: Remove transport do_se_mem_map callback Andy Grover
2011-07-07 22:33 ` [PATCH 14/20] target: When using kunmap_first_data_page, use goto-style err handling Andy Grover
2011-07-07 22:33 ` [PATCH 15/20] target: Further simplify transport_free_pages Andy Grover
2011-07-07 22:33 ` [PATCH 16/20] target: Redo task allocation return value handling Andy Grover
2011-07-07 22:33 ` [PATCH 17/20] target/core: Remove extra parentheses Andy Grover
2011-07-07 22:33 ` [PATCH 18/20] target: Extraneous paren removal in tcm_vhost and tcm_qla2xxx Andy Grover
2011-07-07 22:33 ` [PATCH 19/20] target/iscsi: Remove unneeded parens in conditional statements Andy Grover
2011-07-07 22:33 ` [PATCH 20/20] target/iscsi: Simplify two small bits Andy Grover
2011-07-09 1:18 ` [0/20] target: Patches for June 28 v3 Andy Grover
2011-07-17 19:32 ` Nicholas A. Bellinger
2011-07-09 1:18 ` [PATCH 01/20] target: Remove ifdeffed code in t_g_process_write Andy Grover
2011-07-09 1:18 ` [PATCH 02/20] target: Pass 2nd param of transport_split_cdb by value Andy Grover
2011-07-09 1:18 ` [PATCH 03/20] target: Make all control CDBs scatter-gather Andy Grover
2011-07-17 19:40 ` Nicholas A. Bellinger
2011-07-09 1:18 ` [PATCH 04/20] target: Enforce 1 page max for control cdb buffer sizes Andy Grover
2011-07-09 1:18 ` [PATCH 05/20] target: Remove direct ramdisk code Andy Grover
2011-07-09 1:18 ` [PATCH 06/20] target: Eliminate usage of struct se_mem Andy Grover
2011-07-17 19:57 ` Nicholas A. Bellinger
2011-07-18 17:16 ` Andy Grover
2011-07-18 18:44 ` Nicholas A. Bellinger
2011-07-19 4:56 ` Christoph Hellwig
2011-07-19 5:40 ` Nicholas A. Bellinger
2011-07-09 1:18 ` [PATCH 07/20] target: Rename task_sg_num to task_sg_nents Andy Grover
2011-07-09 1:18 ` [PATCH 08/20] target: Remove custom debug macros for pr_debug. Use pr_err() Andy Grover
2011-07-09 1:18 ` [PATCH 09/20] target: Remove custom debug macros in non-iscsi fabrics Andy Grover
2011-07-17 20:02 ` Nicholas A. Bellinger
2011-07-09 1:18 ` [PATCH 10/20] target/iscsi: Remove iscsi_target_debug.h and usage of TRACE() & printk() Andy Grover
2011-07-09 1:18 ` [PATCH 11/20] target/iscsi: Remove SE_CMD macro Andy Grover
2011-07-09 1:18 ` [PATCH 12/20] target: Set WSNZ=1 in block limits VPD. Abort if WRITE_SAME sectors = 0 Andy Grover
2011-07-09 1:18 ` [PATCH 13/20] target: Remove transport do_se_mem_map callback Andy Grover
2011-07-09 1:18 ` [PATCH 14/20] target: Further simplify transport_free_pages Andy Grover
2011-07-09 1:18 ` [PATCH 15/20] target: Redo task allocation return value handling Andy Grover
2011-07-09 1:18 ` [PATCH 16/20] target/core: Remove extra parentheses Andy Grover
2011-07-09 1:18 ` [PATCH 17/20] target: Extraneous paren removal in tcm_vhost and tcm_qla2xxx Andy Grover
2011-07-09 1:18 ` [PATCH 18/20] target/iscsi: Remove unneeded parens in conditional statements Andy Grover
2011-07-09 1:18 ` [PATCH 19/20] target/iscsi: Simplify two small bits Andy Grover
2011-07-09 1:18 ` [PATCH 20/20] target: change alloc_task call to take *cdb, not *cmd Andy Grover
2011-07-09 10:11 ` Christoph Hellwig
2011-07-10 22:41 ` Andy Grover
2011-07-11 15:28 ` Christoph Hellwig [this message]
2011-07-17 20:04 ` Nicholas A. Bellinger
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=20110711152815.GA20603@infradead.org \
--to=hch@infradead.org \
--cc=agrover@redhat.com \
--cc=linux-scsi@vger.kernel.org \
--cc=target-devel@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox