LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-kernel@vger.kernel.org, linux-block@vger.kernel.org,
	Christoph Hellwig <hch@lst.de>,
	Dan Schatzberg <schatzberg.dan@gmail.com>,
	Ming Lei <ming.lei@redhat.com>
Subject: [PATCH V3 5/7] loop: improve loop_process_work
Date: Fri,  6 Aug 2021 10:34:21 +0800	[thread overview]
Message-ID: <20210806023423.131060-6-ming.lei@redhat.com> (raw)
In-Reply-To: <20210806023423.131060-1-ming.lei@redhat.com>

Avoid to acquire the spinlock for handling every loop command, and hold
lock once for taking all commands.

Acked-by: Dan Schatzberg <schatzberg.dan@gmail.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 drivers/block/loop.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 6d9cfd47b7a2..c9a28483433b 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -2238,21 +2238,26 @@ static void loop_process_work(struct loop_worker *worker,
 {
 	int orig_flags = current->flags;
 	struct loop_cmd *cmd;
+	LIST_HEAD(list);
 
 	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
+
 	spin_lock(&lo->lo_work_lock);
-	while (!list_empty(cmd_list)) {
-		cmd = container_of(
-			cmd_list->next, struct loop_cmd, list_entry);
-		list_del(cmd_list->next);
-		spin_unlock(&lo->lo_work_lock);
+ again:
+	list_splice_init(cmd_list, &list);
+	spin_unlock(&lo->lo_work_lock);
 
-		loop_handle_cmd(cmd);
-		cond_resched();
+	while (!list_empty(&list)) {
+		cmd = list_first_entry(&list, struct loop_cmd, list_entry);
+		list_del_init(&cmd->list_entry);
 
-		spin_lock(&lo->lo_work_lock);
+		loop_handle_cmd(cmd);
 	}
 
+	spin_lock(&lo->lo_work_lock);
+	if (!list_empty(cmd_list))
+		goto again;
+
 	/*
 	 * We only add to the idle list if there are no pending cmds
 	 * *and* the worker will not run again which ensures that it
-- 
2.31.1


  parent reply	other threads:[~2021-08-06  2:35 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-06  2:34 [PATCH V3 0/7] loop: cleanup charging io to mem/blkcg Ming Lei
2021-08-06  2:34 ` [PATCH V3 1/7] mm: memcontrol: add helper of memcg_get_e_css Ming Lei
2021-08-06  2:34 ` [PATCH V3 2/7] loop: clean up blkcg association Ming Lei
2021-08-06  5:50   ` kernel test robot
2021-08-06  2:34 ` [PATCH V3 3/7] loop: conver timer for monitoring idle worker into dwork Ming Lei
2021-08-06  2:34 ` [PATCH V3 4/7] loop: add __loop_free_idle_workers() for covering freeing workers in clearing FD Ming Lei
2021-08-06  2:34 ` Ming Lei [this message]
2021-08-06  2:34 ` [PATCH V3 6/7] loop: use xarray to store workers Ming Lei
2021-08-06  2:34 ` [PATCH V3 7/7] loop: don't add worker into idle list Ming Lei

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=20210806023423.131060-6-ming.lei@redhat.com \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=schatzberg.dan@gmail.com \
    --subject='Re: [PATCH V3 5/7] loop: improve loop_process_work' \
    /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

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).