Received-SPF: pass (google.com: domain of linux-kernel+bounces-180734-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: Yang Yang <yang.yang@vivo.com>
To: Alasdair Kergon <agk@redhat.com>,
	Mike Snitzer <snitzer@kernel.org>,
	Mikulas Patocka <mpatocka@redhat.com>,
	dm-devel@lists.linux.dev,
	linux-kernel@vger.kernel.org
Cc: Yang Yang <yang.yang@vivo.com>
Subject: [PATCH v4 5/5] dm linear: enable flush optimization function
Date: Thu, 16 May 2024 16:03:18 +0800
Message-Id: <20240516080318.120231-6-yang.yang@vivo.com>
In-Reply-To: <20240516080318.120231-1-yang.yang@vivo.com>
References: <20240516080318.120231-1-yang.yang@vivo.com>
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
Precedence: bulk
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0:
	=?us-ascii?Q?ff1Ok/aSWDmc/oKgX6Z3mRiweLDSvA6plgEAAb29iB5iom9oNQjUR1BK7cx5?=
 =?us-ascii?Q?iFL67oKIEq8/6Xp4UJuWTVPRbHu+OPzS1cB7uWPh+pya4n6jdikqEadYZ3oW?=
 =?us-ascii?Q?9EZo6eCGOG7zjeLwW/qZKQpUcVrtkbV84Dc5YnYyok0sEVcM1nmvDBFLpB3E?=
 =?us-ascii?Q?1tbP2bGVMHeJwFgnHqXZUGQrnZtyHHJ1gqxgKo/JEPjN0ecCtW4LrQgOBNXD?=
 =?us-ascii?Q?JtCmVX8x6oqwCxcwZMYu9pGfybeFuKf0cmG7Fp+y/J7S0FP50lePsRKHbuQe?=
 =?us-ascii?Q?qzW1G2N64HFHESDUXR/LucZQBIKZEZSqq7lADYc8oerEg82c0YccY4WRihwP?=
 =?us-ascii?Q?2D3iSCU+10UjlATGNPh8foOIRe7zk1UqxInhJJSlQ6Rp/8muOMyufWrke/Ei?=
 =?us-ascii?Q?utaHfw4rhlYqsAwYCSqQr10PrGvYhHFrH8Tn67c/CyrkZNC36qBXwr1Byoa8?=
 =?us-ascii?Q?6IcZcxZUJJuO3pItd7YYbMHwZHMiWvS5Kvz9kZg8ifCzUzFwPLD2GqSjn9z+?=
 =?us-ascii?Q?dGW/DOUd8LqSC6EyKY1MSGDnrPIv3nVVBCHAwfa2wERWkIE/sWbw9VgLDOD9?=
 =?us-ascii?Q?AbzcaVPR8DPC8XMHL163HKNMIsklKsYAf1oeFwmi5kW/obfu6hjLel/w+CQc?=
 =?us-ascii?Q?6M2QMXntdWeRUoi5sH1cM40tgda7ehpT0/EfoP+/PLLg4OvceQ9b+7YFJ4e8?=
 =?us-ascii?Q?JQQ6IRUDFdfp9zxiA3+Jk2dUCHEBtd8N7cjdXomiGP7VQA8Qh6fD1eXIgr/g?=
 =?us-ascii?Q?aPspiqmw4RkTVpaqDyva/BcOZi+WN7+YC3UlmtsuSuNez4KfSgNtTFVfHNZ9?=
 =?us-ascii?Q?UfSbwH8hbjExb48TIXpZ64pZZOoUKKE/+Og+mP5t+M0m75tLeVMrDe43A1RK?=
 =?us-ascii?Q?y2NLWnufnnr+pqnqcJ3SKr9EsAn2XKeF0epB4AAhAhUbhX6ZaHbo5V+wvlaC?=
 =?us-ascii?Q?nYgI0plRAOrutWeA247RY4mcbg/AFTMjHbOhAJTiwm4Gt4GPh/xfTvJzXCXJ?=
 =?us-ascii?Q?DN7uokutezN+TAWOp0RufjRX0I3Zs8Z6y4of8SKUjXydZ9UVm5KS9P8Bf6cr?=
 =?us-ascii?Q?1Slh/3UdwiBjbt1UVXBmAD2rh5bnuno8oRCzYPjPPcugUDJC920hM1C/Xrbi?=
 =?us-ascii?Q?alf0i4Y/U/LCOtonTGvVBMHe+skOTYiiNqe/EKy8CFjgj0DWlCEYGFIU36kG?=
 =?us-ascii?Q?iowGKrHmi9YWW41FyF1q0/H4J59XIUeZUBciGtqp7bYOGSPWxnVCu+8a1DWH?=
 =?us-ascii?Q?4ZQWeLP1BIcQbfAYaOPgQTdkPuvhZd/O6vZ6OVpCSZhfupnkKoYSOrGsSSr/?=
 =?us-ascii?Q?VIgZNqPuRblDmXP1r36rlhyh8izijhkpcnKpfhDQ+VV6CTE7q4f9hXnYd+V5?=
 =?us-ascii?Q?BXqKlRHpYdkEnHpIOnSEME7QvvP6ESnGyIZEQQzq+sv+2iUq0zgxusFPItTR?=
 =?us-ascii?Q?rMcXWoF+eognL7VryO3X27YbUQOB6+rkWEwC8qbov+m6d0UG0Kd0k1gYZsSn?=
 =?us-ascii?Q?0wf6nShC8FjFPnbRyHYAhk8FoH0vd6l1oKmHhRrojbrK+TSSgK9mo11+TKU3?=
 =?us-ascii?Q?YS65vjpppQz+vmORWQwRcl6DAZDMJh/NzCbfLoPd?=
X-OriginatorOrg: vivo.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 0195cbde-feed-43a7-6de7-08dc757ec856
X-MS-Exchange-CrossTenant-AuthSource: TYSPR06MB6411.apcprd06.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 16 May 2024 08:04:16.8848
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 923e42dc-48d5-4cbe-b582-1a797a6412ed
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: 17Flpdv/WdRoZqeKbMIT1x4mzmd7/yA7QNnJXSezCuNfpimZO6BBt9Q20Qt9u/OMqqMDdYroyb4dcS4X2MuzJQ==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SEYPR06MB6830

__send_empty_flush() sends empty flush bios to every target in the
dm_table. However, if the num_targets exceeds the number of block
devices in the dm_table's device list, it could lead to multiple
invocations of __send_duplicate_bios() for the same block device.
Typically, a single thread sending numerous empty flush bios to one
block device is redundant, as these bios are likely to be merged by the
flush state machine. In scenarios where num_targets significantly
outweighs the number of block devices, such behavior may result in a
noteworthy decrease in performance.

This issue can be reproduced using this command line:
  for i in {0..1023}; do
    echo $((8000*$i)) 8000 linear /dev/sda2 $((16384*$i))
  done | dmsetup create example

With this fix, a random write with fsync workload executed with the
following fio command:

  fio --group_reporting --name=benchmark --filename=/dev/mapper/example \
      --ioengine=sync --invalidate=1 --numjobs=16 --rw=randwrite \
      --blocksize=4k --size=2G --time_based --runtime=30 --fdatasync=1

results in an increase from 857 KB/s to 30.8 MB/s of the write
throughput (3580% increase).

Signed-off-by: Yang Yang <yang.yang@vivo.com>
---
 drivers/md/dm-linear.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 2d3e186ca87e..3e1a33b4d289 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -62,6 +62,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ti->num_discard_bios = 1;
 	ti->num_secure_erase_bios = 1;
 	ti->num_write_zeroes_bios = 1;
+	ti->flush_pass_around = 1;
 	ti->private = lc;
 	return 0;
 
-- 
2.34.1