All of lore.kernel.org
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
	Bart Van Assche <bvanassche@acm.org>
Subject: [PATCH] block: Optimize bio_init()
Date: Sat, 11 Sep 2021 14:47:34 -0700	[thread overview]
Message-ID: <20210911214734.4692-1-bvanassche@acm.org> (raw)

The following test:

sudo taskset -c 0 t/io_uring -b512 -d128 -c32 -s32 -p1 -F1 -B1 /dev/nullb0

reports 1366 K IOPS on my test setup without this patch and 1380 K IOPS
with this patch applied. In other words, this patch realizes a 1%
performance improvement. I think this is because this patch makes the
compiler generate better code. See also commit da521626ac62 ("bio:
optimize initialization of a bio").

The assembler code generated by gcc without this patch is as follows:

   0x0000000000000000 <+0>:     call   0x5 <bio_init+5>
   0x0000000000000005 <+5>:     xor    %eax,%eax
   0x0000000000000007 <+7>:     xor    %ecx,%ecx
   0x0000000000000009 <+9>:     movl   $0x1,0x1c(%rdi)
   0x0000000000000010 <+16>:    movq   $0x0,(%rdi)
   0x0000000000000017 <+23>:    movq   $0x0,0x8(%rdi)
   0x000000000000001f <+31>:    movq   $0x0,0x10(%rdi)
   0x0000000000000027 <+39>:    mov    %ax,0x18(%rdi)
   0x000000000000002b <+43>:    movb   $0x0,0x1a(%rdi)
   0x000000000000002f <+47>:    movq   $0x0,0x20(%rdi)
   0x0000000000000037 <+55>:    movq   $0x0,0x28(%rdi)
   0x000000000000003f <+63>:    movl   $0x0,0x30(%rdi)
   0x0000000000000046 <+70>:    movq   $0x0,0x38(%rdi)
   0x000000000000004e <+78>:    movq   $0x0,0x40(%rdi)
   0x0000000000000056 <+86>:    movq   $0x0,0x48(%rdi)
   0x000000000000005e <+94>:    movq   $0x0,0x50(%rdi)
   0x0000000000000066 <+102>:   movq   $0x0,0x58(%rdi)
   0x000000000000006e <+110>:   movq   $0x0,0x60(%rdi)
   0x0000000000000076 <+118>:   mov    %cx,0x68(%rdi)
   0x000000000000007a <+122>:   movl   $0x1,0x6c(%rdi)
   0x0000000000000081 <+129>:   mov    %dx,0x6a(%rdi)
   0x0000000000000085 <+133>:   mov    %rsi,0x70(%rdi)
   0x0000000000000089 <+137>:   movq   $0x0,0x78(%rdi)
   0x0000000000000091 <+145>:   ret

With this patch bio_init() is compiled into the following assembly code:

   0x0000000000000000 <+0>:     call   0x5 <bio_init+5>
   0x0000000000000005 <+5>:     mov    %rdi,%r8
   0x0000000000000008 <+8>:     mov    $0x10,%ecx
   0x000000000000000d <+13>:    xor    %eax,%eax
   0x000000000000000f <+15>:    rep stos %rax,%es:(%rdi)
   0x0000000000000012 <+18>:    movl   $0x1,0x1c(%r8)
   0x000000000000001a <+26>:    mov    %dx,0x6a(%r8)
   0x000000000000001f <+31>:    movl   $0x1,0x6c(%r8)
   0x0000000000000027 <+39>:    mov    %rsi,0x70(%r8)
   0x000000000000002b <+43>:    ret

Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
---
 block/bio.c | 45 ++++++++-------------------------------------
 1 file changed, 8 insertions(+), 37 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 5df3dd282e40..775cd4274523 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -244,47 +244,18 @@ static void bio_free(struct bio *bio)
 }
 
 /*
- * Users of this function have their own bio allocation. Subsequently,
- * they must remember to pair any call to bio_init() with bio_uninit()
- * when IO has completed, or when the bio is released.
+ * Users of this function must pair any call to bio_init() with a call to
+ * bio_uninit() after IO has completed or when the bio is released.
  */
 void bio_init(struct bio *bio, struct bio_vec *table,
 	      unsigned short max_vecs)
 {
-	bio->bi_next = NULL;
-	bio->bi_bdev = NULL;
-	bio->bi_opf = 0;
-	bio->bi_flags = 0;
-	bio->bi_ioprio = 0;
-	bio->bi_write_hint = 0;
-	bio->bi_status = 0;
-	bio->bi_iter.bi_sector = 0;
-	bio->bi_iter.bi_size = 0;
-	bio->bi_iter.bi_idx = 0;
-	bio->bi_iter.bi_bvec_done = 0;
-	bio->bi_end_io = NULL;
-	bio->bi_private = NULL;
-#ifdef CONFIG_BLK_CGROUP
-	bio->bi_blkg = NULL;
-	bio->bi_issue.value = 0;
-#ifdef CONFIG_BLK_CGROUP_IOCOST
-	bio->bi_iocost_cost = 0;
-#endif
-#endif
-#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-	bio->bi_crypt_context = NULL;
-#endif
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-	bio->bi_integrity = NULL;
-#endif
-	bio->bi_vcnt = 0;
-
-	atomic_set(&bio->__bi_remaining, 1);
-	atomic_set(&bio->__bi_cnt, 1);
-
-	bio->bi_max_vecs = max_vecs;
-	bio->bi_io_vec = table;
-	bio->bi_pool = NULL;
+	*bio = (struct bio) {
+		.__bi_remaining	= ATOMIC_INIT(1),
+		.__bi_cnt	= ATOMIC_INIT(1),
+		.bi_max_vecs	= max_vecs,
+		.bi_io_vec	= table,
+	};
 }
 EXPORT_SYMBOL(bio_init);
 

             reply	other threads:[~2021-09-11 21:47 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-11 21:47 Bart Van Assche [this message]
2021-09-11 22:01 ` [PATCH] block: Optimize bio_init() Jens Axboe
2021-09-11 22:09   ` Jens Axboe
2021-09-11 22:16     ` Jens Axboe
2021-09-12  3:19       ` Bart Van Assche
2021-09-12 13:03         ` Jens Axboe
2021-09-12 22:01           ` Bart Van Assche
2021-09-12 22:13             ` Jens Axboe
2021-09-13  3:52               ` Bart Van Assche

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=20210911214734.4692-1-bvanassche@acm.org \
    --to=bvanassche@acm.org \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=linux-block@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.