Revision c4f675cd40d955d539180506c09515c90169b15b authored by Sergei Trofimovich on 20 May 2011, 20:20:30 UTC, committed by Chris Mason on 23 May 2011, 17:24:14 UTC
Observed as a large delay when --mixed filesystem is filled up.
Test example:
1. create tiny --mixed FS:
   $ dd if=/dev/zero of=2G.img seek=$((2048 * 1024 * 1024 - 1)) count=1 bs=1
   $ mkfs.btrfs --mixed 2G.img
   $ mount -oloop 2G.img /mnt/ut/
2. Try to fill it up:
   $ dd if=/dev/urandom of=10M.file bs=10240 count=1024
   $ seq 1 256 | while read file_no; do echo $file_no; time cp 10M.file ${file_no}.copy; done

Up to '200.copy' it goes fast, but when disk fills-up each -ENOSPC
message takes 3 seconds to pop-up _every_ ENOSPC (and in usermode linux
it's even more: 30-60 seconds!). (Maybe, time depends on kernel's timer resolution).

No IO, no CPU load, just rescheduling. Some debugging revealed busy spinning
in shrink_delalloc.

Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
Reviewed-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
1 parent 0f3b708
Raw File
ev67-strlen.S
/*
 * arch/alpha/lib/ev67-strlen.S
 * 21264 version by Rick Gorton <rick.gorton@alpha-processor.com>
 *
 * Finds length of a 0-terminated string.  Optimized for the
 * Alpha architecture:
 *
 *	- memory accessed as aligned quadwords only
 *	- uses bcmpge to compare 8 bytes in parallel
 *
 * Much of the information about 21264 scheduling/coding comes from:
 *	Compiler Writer's Guide for the Alpha 21264
 *	abbreviated as 'CWG' in other comments here
 *	ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
 * Scheduling notation:
 *	E	- either cluster
 *	U	- upper subcluster; U0 - subcluster U0; U1 - subcluster U1
 *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
 */

	.set noreorder
	.set noat

	.globl	strlen
	.ent	strlen
	.align 4
strlen:
	ldq_u	$1, 0($16)	# L : load first quadword ($16  may be misaligned)
	lda	$2, -1($31)	# E :
	insqh	$2, $16, $2	# U :
	andnot	$16, 7, $0	# E :

	or	$2, $1, $1	# E :
	cmpbge	$31, $1, $2	# E : $2  <- bitmask: bit i == 1 <==> i-th byte == 0
	nop			# E :
	bne	$2, $found	# U :

$loop:	ldq	$1, 8($0)	# L :
	addq	$0, 8, $0	# E : addr += 8
	cmpbge	$31, $1, $2	# E :
	beq	$2, $loop	# U :

$found:
	cttz	$2, $3		# U0 :
	addq	$0, $3, $0	# E :
	subq	$0, $16, $0	# E :
	ret	$31, ($26)	# L0 :

	.end	strlen
back to top