From: Bart Van Assche <bart.vanassche@sandisk.com>
To: Douglas Gilbert <dgilbert@interlog.com>, linux-scsi@vger.kernel.org
Cc: martin.petersen@oracle.com, tomas.winkler@intel.com, emilne@redhat.com
Subject: Re: [PATCH 07/12] scsi_debug: use likely hints on fast path
Date: Tue, 26 Apr 2016 15:14:24 -0700 [thread overview]
Message-ID: <571FE840.1010304@sandisk.com> (raw)
In-Reply-To: <1461600999-28893-8-git-send-email-dgilbert@interlog.com>
On 04/25/2016 09:16 AM, Douglas Gilbert wrote:
> - if ((SDEBUG_OPT_MEDIUM_ERR & sdebug_opts) &&
> - (lba <= (OPT_MEDIUM_ERR_ADDR + OPT_MEDIUM_ERR_NUM - 1)) &&
> - ((lba + num) > OPT_MEDIUM_ERR_ADDR)) {
> + if (unlikely((SDEBUG_OPT_MEDIUM_ERR & sdebug_opts) &&
> + (lba <= (OPT_MEDIUM_ERR_ADDR + OPT_MEDIUM_ERR_NUM - 1)) &&
> + ((lba + num) > OPT_MEDIUM_ERR_ADDR))) {
> [ ... ]
> - if ((qa_indx < 0) || (qa_indx >= SCSI_DEBUG_CANQUEUE)) {
> + if (unlikely((qa_indx < 0) || (qa_indx >= SCSI_DEBUG_CANQUEUE))) {
> [ ... ]
> - if ((qdepth > 0) && (num_in_q >= qdepth)) {
> + if (unlikely((qdepth > 0) && (num_in_q >= qdepth))) {
> [ ... ]
> - } else if ((sdebug_every_nth != 0) &&
> - (SDEBUG_OPT_RARE_TSF & sdebug_opts) &&
> - (scsi_result == 0)) {
> + } else if (unlikely((sdebug_every_nth != 0) &&
> + (SDEBUG_OPT_RARE_TSF & sdebug_opts) &&
> + (scsi_result == 0))) {
Since you are modifying this code, please remove the superfluous
parentheses.
> - struct sdebug_host_info * sdbg_host;
> - struct sdebug_dev_info * open_devip = NULL;
> - struct sdebug_dev_info * devip =
> - (struct sdebug_dev_info *)sdev->hostdata;
> + struct sdebug_host_info *sdbg_host;
> + struct sdebug_dev_info *open_devip = NULL;
> + struct sdebug_dev_info *devip;
>
> - if (devip)
> - return devip;
Has this change been described in the patch description?
> @@ -4632,9 +4617,11 @@ static int __init scsi_debug_init(void)
> switch (sdebug_dif) {
>
> case SD_DIF_TYPE0_PROTECTION:
> + break;
> case SD_DIF_TYPE1_PROTECTION:
> case SD_DIF_TYPE2_PROTECTION:
> case SD_DIF_TYPE3_PROTECTION:
> + have_dif_prot = true;
> break;
Same comment for this code: has this change been explained in the patch
description?
Bart.
next prev parent reply other threads:[~2016-04-26 22:14 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-04-25 16:16 [PATCH 00/12] scsi_debug: multiple queue support and cleanup Douglas Gilbert
2016-04-25 16:16 ` [PATCH 01/12] scsi_debug: cleanup naming and bit crunching Douglas Gilbert
2016-04-26 6:14 ` Hannes Reinecke
2016-04-26 18:13 ` Bart Van Assche
2016-04-26 18:27 ` James Bottomley
2016-04-27 5:25 ` Douglas Gilbert
2016-04-25 16:16 ` [PATCH 02/12] scsi_debug: ignore host lock option Douglas Gilbert
2016-04-26 6:15 ` Hannes Reinecke
2016-04-25 16:16 ` [PATCH 03/12] scsi_debug: replace jiffy timers with hr timers Douglas Gilbert
2016-04-26 6:17 ` Hannes Reinecke
2016-04-26 18:38 ` Bart Van Assche
2016-04-25 16:16 ` [PATCH 04/12] scsi_debug: make jiffy delay name clearer Douglas Gilbert
2016-04-26 6:17 ` Hannes Reinecke
2016-04-25 16:16 ` [PATCH 05/12] scsi_debug: replace tasklet with work queue Douglas Gilbert
2016-04-26 6:20 ` Hannes Reinecke
2016-04-25 16:16 ` [PATCH 06/12] scsi_debug: re-order file scope declarations Douglas Gilbert
2016-04-26 6:21 ` Hannes Reinecke
2016-04-26 20:55 ` Bart Van Assche
2016-04-25 16:16 ` [PATCH 07/12] scsi_debug: use likely hints on fast path Douglas Gilbert
2016-04-26 6:22 ` Hannes Reinecke
2016-04-26 22:14 ` Bart Van Assche [this message]
2016-04-27 5:25 ` Douglas Gilbert
2016-04-27 5:33 ` Bart Van Assche
2016-04-27 14:29 ` Bart Van Assche
2016-04-25 16:16 ` [PATCH 08/12] scsi_debug: rework resp_report_luns Douglas Gilbert
2016-04-26 6:26 ` Hannes Reinecke
2016-04-27 4:08 ` Douglas Gilbert
2016-04-27 5:58 ` Hannes Reinecke
2016-04-26 7:33 ` Winkler, Tomas
2016-04-27 23:09 ` Bart Van Assche
2016-04-25 16:16 ` [PATCH 09/12] scsi_debug: add multiple queue support Douglas Gilbert
2016-04-26 6:29 ` Hannes Reinecke
2016-04-26 22:19 ` Bart Van Assche
2016-04-25 16:16 ` [PATCH 10/12] scsi_debug: vpd and mode page work Douglas Gilbert
2016-04-26 6:29 ` Hannes Reinecke
2016-04-25 16:16 ` [PATCH 11/12] scsi_debug: uuid for lu name Douglas Gilbert
2016-04-26 6:30 ` Hannes Reinecke
2016-04-25 16:16 ` [PATCH 12/12] scsi_debug: use locally assigned naa Douglas Gilbert
2016-04-26 6:31 ` Hannes Reinecke
2016-04-29 23:53 ` [PATCH 00/12] scsi_debug: multiple queue support and cleanup Martin K. Petersen
2016-04-30 2:06 ` Douglas Gilbert
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=571FE840.1010304@sandisk.com \
--to=bart.vanassche@sandisk.com \
--cc=dgilbert@interlog.com \
--cc=emilne@redhat.com \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=tomas.winkler@intel.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;
as well as URLs for NNTP newsgroup(s).