linux/block/elevator.c

1049 lines
24 KiB
C
Raw Normal View History

/*
* Block device elevator/IO-scheduler.
*
* Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
*
* 30042000 Jens Axboe <axboe@kernel.dk> :
*
* Split the elevator a bit so that it is possible to choose a different
* one or even write a new "plug in". There are three pieces:
* - elevator_fn, inserts a new request in the queue list
* - elevator_merge_fn, decides whether a new buffer can be merged with
* an existing request
* - elevator_dequeue_fn, called when a request is taken off the active list
*
* 20082000 Dave Jones <davej@suse.de> :
* Removed tests for max-bomb-segments, which was breaking elvtune
* when run without -bN
*
* Jens:
* - Rework again to work with bio instead of buffer_heads
* - loose bi_dev comparisons, partition handling is right now
* - completely modularize elevator setup and teardown
*
*/
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/blktrace_api.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
#include <linux/pm_runtime.h>
#include <linux/blk-cgroup.h>
tracing/events: convert block trace points to TRACE_EVENT() TRACE_EVENT is a more generic way to define tracepoints. Doing so adds these new capabilities to this tracepoint: - zero-copy and per-cpu splice() tracing - binary tracing without printf overhead - structured logging records exposed under /debug/tracing/events - trace events embedded in function tracer output and other plugins - user-defined, per tracepoint filter expressions ... Cons: - no dev_t info for the output of plug, unplug_timer and unplug_io events. no dev_t info for getrq and sleeprq events if bio == NULL. no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL. This is mainly because we can't get the deivce from a request queue. But this may change in the future. - A packet command is converted to a string in TP_assign, not TP_print. While blktrace do the convertion just before output. Since pc requests should be rather rare, this is not a big issue. - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT has a unique format, which means we have some unused data in a trace entry. The overhead is minimized by using __dynamic_array() instead of __array(). I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing: dd dd + ioctl blktrace dd + TRACE_EVENT (splice) 1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s 2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s 3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s So the overhead of tracing is very small, and no regression when using those trace events vs blktrace. And the binary output of TRACE_EVENT is much smaller than blktrace: # ls -l -h -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out Following are some comparisons between TRACE_EVENT and blktrace: plug: kjournald-480 [000] 303.084981: block_plug: [kjournald] kjournald-480 [000] 303.084981: 8,0 P N [kjournald] unplug_io: kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1 kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1 remap: kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384 kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384 bio_backmerge: kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald] kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald] getrq: kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald] kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald] bash-2066 [001] 1072.953770: 8,0 G N [bash] bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash] rq_complete: konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0] konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0] ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0] ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0] rq_insert: kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald] kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald] Changelog from v2 -> v3: - use the newly introduced __dynamic_array(). Changelog from v1 -> v2: - use __string() instead of __array() to minimize the memory required to store hex dump of rq->cmd(). - support large pc requests. - add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT. - some cleanups. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-09 05:43:05 +00:00
#include <trace/events/block.h>
#include "blk.h"
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
/*
* Merge hash stuff.
*/
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
#define rq_hash_key(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq))
/*
* Query io scheduler to see if the current process issuing bio may be
* merged with rq.
*/
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
if (e->type->ops.elevator_allow_bio_merge_fn)
return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);
return 1;
}
/*
* can we safely merge with this request?
*/
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
{
if (!blk_rq_merge_ok(rq, bio))
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
return false;
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
if (!elv_iosched_allow_bio_merge(rq, bio))
return false;
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
return true;
}
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
EXPORT_SYMBOL(elv_bio_merge_ok);
static struct elevator_type *elevator_find(const char *name)
{
struct elevator_type *e;
list_for_each_entry(e, &elv_list, list) {
if (!strcmp(e->elevator_name, name))
return e;
}
return NULL;
}
static void elevator_put(struct elevator_type *e)
{
module_put(e->elevator_owner);
}
block: don't request module during elevator init Block layer allows selecting an elevator which is built as a module to be selected as system default via kernel param "elevator=". This is achieved by automatically invoking request_module() whenever a new block device is initialized and the elevator is not available. This led to an interesting deadlock problem involving async and module init. Block device probing running off an async job invokes request_module(). While the module is being loaded, it performs async_synchronize_full() which ends up waiting for the async job which is already waiting for request_module() to finish, leading to deadlock. Invoking request_module() from deep in block device init path is already nasty in itself. It seems best to avoid these situations from the beginning by moving on-demand module loading out of block init path. The previous patch made sure that the default elevator module is loaded early during boot if available. This patch removes on-demand loading of the default elevator from elevator init path. As the module would have been loaded during boot, userland-visible behavior difference should be minimal. For more details, please refer to the following thread. http://thread.gmane.org/gmane.linux.kernel/1420814 v2: The bool parameter was named @request_module which conflicted with request_module(). This built okay w/ CONFIG_MODULES because request_module() was defined as a macro. W/o CONFIG_MODULES, it causes build breakage. Rename the parameter to @try_loading. Reported by Fengguang. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alex Riesen <raa.lkml@gmail.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2013-01-23 00:48:03 +00:00
static struct elevator_type *elevator_get(const char *name, bool try_loading)
{
struct elevator_type *e;
spin_lock(&elv_list_lock);
e = elevator_find(name);
block: don't request module during elevator init Block layer allows selecting an elevator which is built as a module to be selected as system default via kernel param "elevator=". This is achieved by automatically invoking request_module() whenever a new block device is initialized and the elevator is not available. This led to an interesting deadlock problem involving async and module init. Block device probing running off an async job invokes request_module(). While the module is being loaded, it performs async_synchronize_full() which ends up waiting for the async job which is already waiting for request_module() to finish, leading to deadlock. Invoking request_module() from deep in block device init path is already nasty in itself. It seems best to avoid these situations from the beginning by moving on-demand module loading out of block init path. The previous patch made sure that the default elevator module is loaded early during boot if available. This patch removes on-demand loading of the default elevator from elevator init path. As the module would have been loaded during boot, userland-visible behavior difference should be minimal. For more details, please refer to the following thread. http://thread.gmane.org/gmane.linux.kernel/1420814 v2: The bool parameter was named @request_module which conflicted with request_module(). This built okay w/ CONFIG_MODULES because request_module() was defined as a macro. W/o CONFIG_MODULES, it causes build breakage. Rename the parameter to @try_loading. Reported by Fengguang. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alex Riesen <raa.lkml@gmail.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2013-01-23 00:48:03 +00:00
if (!e && try_loading) {
spin_unlock(&elv_list_lock);
request_module("%s-iosched", name);
spin_lock(&elv_list_lock);
e = elevator_find(name);
}
if (e && !try_module_get(e->elevator_owner))
e = NULL;
spin_unlock(&elv_list_lock);
return e;
}
static char chosen_elevator[ELV_NAME_MAX];
static int __init elevator_setup(char *str)
{
/*
* Be backwards-compatible with previous kernels, so users
* won't get the wrong elevator.
*/
strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
return 1;
}
__setup("elevator=", elevator_setup);
/* called during boot to load the elevator chosen by the elevator param */
void __init load_default_elevator_module(void)
{
struct elevator_type *e;
if (!chosen_elevator[0])
return;
spin_lock(&elv_list_lock);
e = elevator_find(chosen_elevator);
spin_unlock(&elv_list_lock);
if (!e)
request_module("%s-iosched", chosen_elevator);
}
static struct kobj_type elv_ktype;
struct elevator_queue *elevator_alloc(struct request_queue *q,
struct elevator_type *e)
{
struct elevator_queue *eq;
eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node);
if (unlikely(!eq))
return NULL;
eq->type = e;
kobject_init(&eq->kobj, &elv_ktype);
mutex_init(&eq->sysfs_lock);
hash_init(eq->hash);
return eq;
}
EXPORT_SYMBOL(elevator_alloc);
static void elevator_release(struct kobject *kobj)
{
struct elevator_queue *e;
e = container_of(kobj, struct elevator_queue, kobj);
elevator_put(e->type);
kfree(e);
}
int elevator_init(struct request_queue *q, char *name)
{
struct elevator_type *e = NULL;
int err;
elevator: Fix a race in elevator switching and md device initialization The soft lockup below happens at the boot time of the system using dm multipath and the udev rules to switch scheduler. [ 356.127001] BUG: soft lockup - CPU#3 stuck for 22s! [sh:483] [ 356.127001] RIP: 0010:[<ffffffff81072a7d>] [<ffffffff81072a7d>] lock_timer_base.isra.35+0x1d/0x50 ... [ 356.127001] Call Trace: [ 356.127001] [<ffffffff81073810>] try_to_del_timer_sync+0x20/0x70 [ 356.127001] [<ffffffff8118b08a>] ? kmem_cache_alloc_node_trace+0x20a/0x230 [ 356.127001] [<ffffffff810738b2>] del_timer_sync+0x52/0x60 [ 356.127001] [<ffffffff812ece22>] cfq_exit_queue+0x32/0xf0 [ 356.127001] [<ffffffff812c98df>] elevator_exit+0x2f/0x50 [ 356.127001] [<ffffffff812c9f21>] elevator_change+0xf1/0x1c0 [ 356.127001] [<ffffffff812caa50>] elv_iosched_store+0x20/0x50 [ 356.127001] [<ffffffff812d1d09>] queue_attr_store+0x59/0xb0 [ 356.127001] [<ffffffff812143f6>] sysfs_write_file+0xc6/0x140 [ 356.127001] [<ffffffff811a326d>] vfs_write+0xbd/0x1e0 [ 356.127001] [<ffffffff811a3ca9>] SyS_write+0x49/0xa0 [ 356.127001] [<ffffffff8164e899>] system_call_fastpath+0x16/0x1b This is caused by a race between md device initialization by multipathd and shell script to switch the scheduler using sysfs. - multipathd: SyS_ioctl -> do_vfs_ioctl -> dm_ctl_ioctl -> ctl_ioctl -> table_load -> dm_setup_md_queue -> blk_init_allocated_queue -> elevator_init q->elevator = elevator_alloc(q, e); // not yet initialized - sh -c 'echo deadline > /sys/$DEVPATH/queue/scheduler': elevator_switch (in the call trace above) struct elevator_queue *old = q->elevator; q->elevator = elevator_alloc(q, new_e); elevator_exit(old); // lockup! (*) - multipathd: (cont.) err = e->ops.elevator_init_fn(q); // init fails; q->elevator is modified (*) When del_timer_sync() is called, lock_timer_base() will loop infinitely while timer->base == NULL. In this case, as timer will never initialized, it results in lockup. This patch introduces acquisition of q->sysfs_lock around elevator_init() into blk_init_allocated_queue(), to provide mutual exclusion between initialization of the q->scheduler and switching of the scheduler. This should fix this bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=902012 Signed-off-by: Tomoki Sekiyama <tomoki.sekiyama@hds.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-15 22:42:16 +00:00
/*
* q->sysfs_lock must be held to provide mutual exclusion between
* elevator_switch() and here.
*/
lockdep_assert_held(&q->sysfs_lock);
if (unlikely(q->elevator))
return 0;
INIT_LIST_HEAD(&q->queue_head);
q->last_merge = NULL;
q->end_sector = 0;
q->boundary_rq = NULL;
if (name) {
block: don't request module during elevator init Block layer allows selecting an elevator which is built as a module to be selected as system default via kernel param "elevator=". This is achieved by automatically invoking request_module() whenever a new block device is initialized and the elevator is not available. This led to an interesting deadlock problem involving async and module init. Block device probing running off an async job invokes request_module(). While the module is being loaded, it performs async_synchronize_full() which ends up waiting for the async job which is already waiting for request_module() to finish, leading to deadlock. Invoking request_module() from deep in block device init path is already nasty in itself. It seems best to avoid these situations from the beginning by moving on-demand module loading out of block init path. The previous patch made sure that the default elevator module is loaded early during boot if available. This patch removes on-demand loading of the default elevator from elevator init path. As the module would have been loaded during boot, userland-visible behavior difference should be minimal. For more details, please refer to the following thread. http://thread.gmane.org/gmane.linux.kernel/1420814 v2: The bool parameter was named @request_module which conflicted with request_module(). This built okay w/ CONFIG_MODULES because request_module() was defined as a macro. W/o CONFIG_MODULES, it causes build breakage. Rename the parameter to @try_loading. Reported by Fengguang. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alex Riesen <raa.lkml@gmail.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2013-01-23 00:48:03 +00:00
e = elevator_get(name, true);
if (!e)
return -EINVAL;
}
block: don't request module during elevator init Block layer allows selecting an elevator which is built as a module to be selected as system default via kernel param "elevator=". This is achieved by automatically invoking request_module() whenever a new block device is initialized and the elevator is not available. This led to an interesting deadlock problem involving async and module init. Block device probing running off an async job invokes request_module(). While the module is being loaded, it performs async_synchronize_full() which ends up waiting for the async job which is already waiting for request_module() to finish, leading to deadlock. Invoking request_module() from deep in block device init path is already nasty in itself. It seems best to avoid these situations from the beginning by moving on-demand module loading out of block init path. The previous patch made sure that the default elevator module is loaded early during boot if available. This patch removes on-demand loading of the default elevator from elevator init path. As the module would have been loaded during boot, userland-visible behavior difference should be minimal. For more details, please refer to the following thread. http://thread.gmane.org/gmane.linux.kernel/1420814 v2: The bool parameter was named @request_module which conflicted with request_module(). This built okay w/ CONFIG_MODULES because request_module() was defined as a macro. W/o CONFIG_MODULES, it causes build breakage. Rename the parameter to @try_loading. Reported by Fengguang. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alex Riesen <raa.lkml@gmail.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2013-01-23 00:48:03 +00:00
/*
* Use the default elevator specified by config boot param or
* config option. Don't try to load modules as we could be running
* off async and request_module() isn't allowed from async.
*/
if (!e && *chosen_elevator) {
block: don't request module during elevator init Block layer allows selecting an elevator which is built as a module to be selected as system default via kernel param "elevator=". This is achieved by automatically invoking request_module() whenever a new block device is initialized and the elevator is not available. This led to an interesting deadlock problem involving async and module init. Block device probing running off an async job invokes request_module(). While the module is being loaded, it performs async_synchronize_full() which ends up waiting for the async job which is already waiting for request_module() to finish, leading to deadlock. Invoking request_module() from deep in block device init path is already nasty in itself. It seems best to avoid these situations from the beginning by moving on-demand module loading out of block init path. The previous patch made sure that the default elevator module is loaded early during boot if available. This patch removes on-demand loading of the default elevator from elevator init path. As the module would have been loaded during boot, userland-visible behavior difference should be minimal. For more details, please refer to the following thread. http://thread.gmane.org/gmane.linux.kernel/1420814 v2: The bool parameter was named @request_module which conflicted with request_module(). This built okay w/ CONFIG_MODULES because request_module() was defined as a macro. W/o CONFIG_MODULES, it causes build breakage. Rename the parameter to @try_loading. Reported by Fengguang. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alex Riesen <raa.lkml@gmail.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2013-01-23 00:48:03 +00:00
e = elevator_get(chosen_elevator, false);
if (!e)
printk(KERN_ERR "I/O scheduler %s not found\n",
chosen_elevator);
}
if (!e) {
block: don't request module during elevator init Block layer allows selecting an elevator which is built as a module to be selected as system default via kernel param "elevator=". This is achieved by automatically invoking request_module() whenever a new block device is initialized and the elevator is not available. This led to an interesting deadlock problem involving async and module init. Block device probing running off an async job invokes request_module(). While the module is being loaded, it performs async_synchronize_full() which ends up waiting for the async job which is already waiting for request_module() to finish, leading to deadlock. Invoking request_module() from deep in block device init path is already nasty in itself. It seems best to avoid these situations from the beginning by moving on-demand module loading out of block init path. The previous patch made sure that the default elevator module is loaded early during boot if available. This patch removes on-demand loading of the default elevator from elevator init path. As the module would have been loaded during boot, userland-visible behavior difference should be minimal. For more details, please refer to the following thread. http://thread.gmane.org/gmane.linux.kernel/1420814 v2: The bool parameter was named @request_module which conflicted with request_module(). This built okay w/ CONFIG_MODULES because request_module() was defined as a macro. W/o CONFIG_MODULES, it causes build breakage. Rename the parameter to @try_loading. Reported by Fengguang. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alex Riesen <raa.lkml@gmail.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2013-01-23 00:48:03 +00:00
e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
if (!e) {
printk(KERN_ERR
"Default I/O scheduler not found. " \
"Using noop.\n");
block: don't request module during elevator init Block layer allows selecting an elevator which is built as a module to be selected as system default via kernel param "elevator=". This is achieved by automatically invoking request_module() whenever a new block device is initialized and the elevator is not available. This led to an interesting deadlock problem involving async and module init. Block device probing running off an async job invokes request_module(). While the module is being loaded, it performs async_synchronize_full() which ends up waiting for the async job which is already waiting for request_module() to finish, leading to deadlock. Invoking request_module() from deep in block device init path is already nasty in itself. It seems best to avoid these situations from the beginning by moving on-demand module loading out of block init path. The previous patch made sure that the default elevator module is loaded early during boot if available. This patch removes on-demand loading of the default elevator from elevator init path. As the module would have been loaded during boot, userland-visible behavior difference should be minimal. For more details, please refer to the following thread. http://thread.gmane.org/gmane.linux.kernel/1420814 v2: The bool parameter was named @request_module which conflicted with request_module(). This built okay w/ CONFIG_MODULES because request_module() was defined as a macro. W/o CONFIG_MODULES, it causes build breakage. Rename the parameter to @try_loading. Reported by Fengguang. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alex Riesen <raa.lkml@gmail.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2013-01-23 00:48:03 +00:00
e = elevator_get("noop", false);
}
}
err = e->ops.elevator_init_fn(q, e);
if (err)
elevator_put(e);
return err;
}
EXPORT_SYMBOL(elevator_init);
void elevator_exit(struct elevator_queue *e)
{
mutex_lock(&e->sysfs_lock);
if (e->type->ops.elevator_exit_fn)
e->type->ops.elevator_exit_fn(e);
mutex_unlock(&e->sysfs_lock);
kobject_put(&e->kobj);
}
EXPORT_SYMBOL(elevator_exit);
static inline void __elv_rqhash_del(struct request *rq)
{
hash_del(&rq->hash);
block: fix regression with block enabled tagging Martin reported that his test system would not boot with current git, it oopsed with this: BUG: unable to handle kernel paging request at ffff88046c6c9e80 IP: [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 PGD 1ddf067 PUD 1de2067 PMD 47fc7d067 PTE 800000046c6c9060 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: sd_mod lpfc(+) scsi_transport_fc scsi_tgt oracleasm rpcsec_gss_krb5 ipv6 igb dca i2c_algo_bit i2c_core hwmon CPU: 3 PID: 87 Comm: kworker/u17:1 Not tainted 3.14.0+ #246 Hardware name: Supermicro X9DRX+-F/X9DRX+-F, BIOS 3.00 07/09/2013 Workqueue: events_unbound async_run_entry_fn task: ffff8802743c2150 ti: ffff880273d02000 task.ti: ffff880273d02000 RIP: 0010:[<ffffffff812971e0>] [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP: 0018:ffff880273d03a58 EFLAGS: 00010092 RAX: ffff88046c6c9e78 RBX: ffff880077208e78 RCX: 00000000fffc8da6 RDX: 00000000fffc186d RSI: 0000000000000009 RDI: 00000000fffc8d9d RBP: ffff880273d03a88 R08: 0000000000000001 R09: ffff8800021c2410 R10: 0000000000000005 R11: 0000000000015b30 R12: ffff88046c5bb8a0 R13: ffff88046c5c0890 R14: 000000000000001e R15: 000000000000001e FS: 0000000000000000(0000) GS:ffff880277b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88046c6c9e80 CR3: 00000000018f6000 CR4: 00000000000407e0 Stack: ffff880273d03a98 ffff880474b18800 0000000000000000 ffff880474157000 ffff88046c5c0890 ffff880077208e78 ffff880273d03ae8 ffffffff813b9e62 ffff880200000010 ffff880474b18968 ffff880474b18848 ffff88046c5c0cd8 Call Trace: [<ffffffff813b9e62>] scsi_request_fn+0xf2/0x510 [<ffffffff81293167>] __blk_run_queue+0x37/0x50 [<ffffffff8129ac43>] blk_execute_rq_nowait+0xb3/0x130 [<ffffffff8129ad24>] blk_execute_rq+0x64/0xf0 [<ffffffff8108d2b0>] ? bit_waitqueue+0xd0/0xd0 [<ffffffff813bba35>] scsi_execute+0xe5/0x180 [<ffffffff813bbe4a>] scsi_execute_req_flags+0x9a/0x110 [<ffffffffa01b1304>] sd_spinup_disk+0x94/0x460 [sd_mod] [<ffffffff81160000>] ? __unmap_hugepage_range+0x200/0x2f0 [<ffffffffa01b2b9a>] sd_revalidate_disk+0xaa/0x3f0 [sd_mod] [<ffffffffa01b2fb8>] sd_probe_async+0xd8/0x200 [sd_mod] [<ffffffff8107703f>] async_run_entry_fn+0x3f/0x140 [<ffffffff8106a1c5>] process_one_work+0x175/0x410 [<ffffffff8106b373>] worker_thread+0x123/0x400 [<ffffffff8106b250>] ? manage_workers+0x160/0x160 [<ffffffff8107104e>] kthread+0xce/0xf0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff815f0bac>] ret_from_fork+0x7c/0xb0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 Code: 48 0f ab 11 72 db 48 81 4b 40 00 00 10 00 89 83 08 01 00 00 48 89 df 49 8b 04 24 48 89 1c d0 e8 f7 a8 ff ff 49 8b 85 28 05 00 00 <48> 89 58 08 48 89 03 49 8d 85 28 05 00 00 48 89 43 08 49 89 9d RIP [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP <ffff880273d03a58> CR2: ffff88046c6c9e80 Martin bisected and found this to be the problem patch; commit 6d113398dcf4dfcd9787a4ead738b186f7b7ff0f Author: Jan Kara <jack@suse.cz> Date: Mon Feb 24 16:39:54 2014 +0100 block: Stop abusing rq->csd.list in blk-softirq and the problem was immediately apparent. The patch states that it is safe to reuse queuelist at completion time, since it is no longer used. However, that is not true if a device is using block enabled tagging. If that is the case, then the queuelist is reused to keep track of busy tags. If a device also ended up using softirq completions, we'd reuse ->queuelist for the IPI handling while block tagging was still using it. Boom. Fix this by adding a new ipi_list list head, and share the memory used with the request hash table. The hash table is never used after the request is moved to the dispatch list, which happens long before any potential completion of the request. Add a new request bit for this, so we don't have cases that check rq->hash while it could potentially have been reused for the IPI completion. Reported-by: Martin K. Petersen <martin.petersen@oracle.com> Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2014-04-10 02:27:01 +00:00
rq->cmd_flags &= ~REQ_HASHED;
}
static void elv_rqhash_del(struct request_queue *q, struct request *rq)
{
if (ELV_ON_HASH(rq))
__elv_rqhash_del(rq);
}
static void elv_rqhash_add(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
BUG_ON(ELV_ON_HASH(rq));
hash_add(e->hash, &rq->hash, rq_hash_key(rq));
block: fix regression with block enabled tagging Martin reported that his test system would not boot with current git, it oopsed with this: BUG: unable to handle kernel paging request at ffff88046c6c9e80 IP: [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 PGD 1ddf067 PUD 1de2067 PMD 47fc7d067 PTE 800000046c6c9060 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: sd_mod lpfc(+) scsi_transport_fc scsi_tgt oracleasm rpcsec_gss_krb5 ipv6 igb dca i2c_algo_bit i2c_core hwmon CPU: 3 PID: 87 Comm: kworker/u17:1 Not tainted 3.14.0+ #246 Hardware name: Supermicro X9DRX+-F/X9DRX+-F, BIOS 3.00 07/09/2013 Workqueue: events_unbound async_run_entry_fn task: ffff8802743c2150 ti: ffff880273d02000 task.ti: ffff880273d02000 RIP: 0010:[<ffffffff812971e0>] [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP: 0018:ffff880273d03a58 EFLAGS: 00010092 RAX: ffff88046c6c9e78 RBX: ffff880077208e78 RCX: 00000000fffc8da6 RDX: 00000000fffc186d RSI: 0000000000000009 RDI: 00000000fffc8d9d RBP: ffff880273d03a88 R08: 0000000000000001 R09: ffff8800021c2410 R10: 0000000000000005 R11: 0000000000015b30 R12: ffff88046c5bb8a0 R13: ffff88046c5c0890 R14: 000000000000001e R15: 000000000000001e FS: 0000000000000000(0000) GS:ffff880277b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88046c6c9e80 CR3: 00000000018f6000 CR4: 00000000000407e0 Stack: ffff880273d03a98 ffff880474b18800 0000000000000000 ffff880474157000 ffff88046c5c0890 ffff880077208e78 ffff880273d03ae8 ffffffff813b9e62 ffff880200000010 ffff880474b18968 ffff880474b18848 ffff88046c5c0cd8 Call Trace: [<ffffffff813b9e62>] scsi_request_fn+0xf2/0x510 [<ffffffff81293167>] __blk_run_queue+0x37/0x50 [<ffffffff8129ac43>] blk_execute_rq_nowait+0xb3/0x130 [<ffffffff8129ad24>] blk_execute_rq+0x64/0xf0 [<ffffffff8108d2b0>] ? bit_waitqueue+0xd0/0xd0 [<ffffffff813bba35>] scsi_execute+0xe5/0x180 [<ffffffff813bbe4a>] scsi_execute_req_flags+0x9a/0x110 [<ffffffffa01b1304>] sd_spinup_disk+0x94/0x460 [sd_mod] [<ffffffff81160000>] ? __unmap_hugepage_range+0x200/0x2f0 [<ffffffffa01b2b9a>] sd_revalidate_disk+0xaa/0x3f0 [sd_mod] [<ffffffffa01b2fb8>] sd_probe_async+0xd8/0x200 [sd_mod] [<ffffffff8107703f>] async_run_entry_fn+0x3f/0x140 [<ffffffff8106a1c5>] process_one_work+0x175/0x410 [<ffffffff8106b373>] worker_thread+0x123/0x400 [<ffffffff8106b250>] ? manage_workers+0x160/0x160 [<ffffffff8107104e>] kthread+0xce/0xf0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 [<ffffffff815f0bac>] ret_from_fork+0x7c/0xb0 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70 Code: 48 0f ab 11 72 db 48 81 4b 40 00 00 10 00 89 83 08 01 00 00 48 89 df 49 8b 04 24 48 89 1c d0 e8 f7 a8 ff ff 49 8b 85 28 05 00 00 <48> 89 58 08 48 89 03 49 8d 85 28 05 00 00 48 89 43 08 49 89 9d RIP [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150 RSP <ffff880273d03a58> CR2: ffff88046c6c9e80 Martin bisected and found this to be the problem patch; commit 6d113398dcf4dfcd9787a4ead738b186f7b7ff0f Author: Jan Kara <jack@suse.cz> Date: Mon Feb 24 16:39:54 2014 +0100 block: Stop abusing rq->csd.list in blk-softirq and the problem was immediately apparent. The patch states that it is safe to reuse queuelist at completion time, since it is no longer used. However, that is not true if a device is using block enabled tagging. If that is the case, then the queuelist is reused to keep track of busy tags. If a device also ended up using softirq completions, we'd reuse ->queuelist for the IPI handling while block tagging was still using it. Boom. Fix this by adding a new ipi_list list head, and share the memory used with the request hash table. The hash table is never used after the request is moved to the dispatch list, which happens long before any potential completion of the request. Add a new request bit for this, so we don't have cases that check rq->hash while it could potentially have been reused for the IPI completion. Reported-by: Martin K. Petersen <martin.petersen@oracle.com> Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2014-04-10 02:27:01 +00:00
rq->cmd_flags |= REQ_HASHED;
}
static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
{
__elv_rqhash_del(rq);
elv_rqhash_add(q, rq);
}
static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
{
struct elevator_queue *e = q->elevator;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
struct hlist_node *next;
struct request *rq;
Merge branch 'for-3.9/core' of git://git.kernel.dk/linux-block Pull block IO core bits from Jens Axboe: "Below are the core block IO bits for 3.9. It was delayed a few days since my workstation kept crashing every 2-8h after pulling it into current -git, but turns out it is a bug in the new pstate code (divide by zero, will report separately). In any case, it contains: - The big cfq/blkcg update from Tejun and and Vivek. - Additional block and writeback tracepoints from Tejun. - Improvement of the should sort (based on queues) logic in the plug flushing. - _io() variants of the wait_for_completion() interface, using io_schedule() instead of schedule() to contribute to io wait properly. - Various little fixes. You'll get two trivial merge conflicts, which should be easy enough to fix up" Fix up the trivial conflicts due to hlist traversal cleanups (commit b67bfe0d42ca: "hlist: drop the node parameter from iterators"). * 'for-3.9/core' of git://git.kernel.dk/linux-block: (39 commits) block: remove redundant check to bd_openers() block: use i_size_write() in bd_set_size() cfq: fix lock imbalance with failed allocations drivers/block/swim3.c: fix null pointer dereference block: don't select PERCPU_RWSEM block: account iowait time when waiting for completion of IO request sched: add wait_for_completion_io[_timeout] writeback: add more tracepoints block: add block_{touch|dirty}_buffer tracepoint buffer: make touch_buffer() an exported function block: add @req to bio_{front|back}_merge tracepoints block: add missing block_bio_complete() tracepoint block: Remove should_sort judgement when flush blk_plug block,elevator: use new hashtable implementation cfq-iosched: add hierarchical cfq_group statistics cfq-iosched: collect stats from dead cfqgs cfq-iosched: separate out cfqg_stats_reset() from cfq_pd_reset_stats() blkcg: make blkcg_print_blkgs() grab q locks instead of blkcg lock block: RCU free request_queue blkcg: implement blkg_[rw]stat_recursive_sum() and blkg_[rw]stat_merge() ...
2013-02-28 20:52:24 +00:00
hash_for_each_possible_safe(e->hash, rq, next, hash, offset) {
BUG_ON(!ELV_ON_HASH(rq));
if (unlikely(!rq_mergeable(rq))) {
__elv_rqhash_del(rq);
continue;
}
if (rq_hash_key(rq) == offset)
return rq;
}
return NULL;
}
/*
* RB-tree support functions for inserting/lookup/removal of requests
* in a sorted RB tree.
*/
void elv_rb_add(struct rb_root *root, struct request *rq)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct request *__rq;
while (*p) {
parent = *p;
__rq = rb_entry(parent, struct request, rb_node);
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
if (blk_rq_pos(rq) < blk_rq_pos(__rq))
p = &(*p)->rb_left;
else if (blk_rq_pos(rq) >= blk_rq_pos(__rq))
p = &(*p)->rb_right;
}
rb_link_node(&rq->rb_node, parent, p);
rb_insert_color(&rq->rb_node, root);
}
EXPORT_SYMBOL(elv_rb_add);
void elv_rb_del(struct rb_root *root, struct request *rq)
{
BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
rb_erase(&rq->rb_node, root);
RB_CLEAR_NODE(&rq->rb_node);
}
EXPORT_SYMBOL(elv_rb_del);
struct request *elv_rb_find(struct rb_root *root, sector_t sector)
{
struct rb_node *n = root->rb_node;
struct request *rq;
while (n) {
rq = rb_entry(n, struct request, rb_node);
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
if (sector < blk_rq_pos(rq))
n = n->rb_left;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
else if (sector > blk_rq_pos(rq))
n = n->rb_right;
else
return rq;
}
return NULL;
}
EXPORT_SYMBOL(elv_rb_find);
/*
* Insert rq into dispatch queue of q. Queue lock must be held on
* entry. rq is sort instead into the dispatch queue. To be used by
* specific elevators.
*/
void elv_dispatch_sort(struct request_queue *q, struct request *rq)
{
sector_t boundary;
struct list_head *entry;
int stop_flags;
if (q->last_merge == rq)
q->last_merge = NULL;
elv_rqhash_del(q, rq);
q->nr_sorted--;
boundary = q->end_sector;
stop_flags = REQ_SOFTBARRIER | REQ_STARTED;
list_for_each_prev(entry, &q->queue_head) {
struct request *pos = list_entry_rq(entry);
if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD))
break;
if (rq_data_dir(rq) != rq_data_dir(pos))
break;
if (pos->cmd_flags & stop_flags)
break;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
if (blk_rq_pos(rq) >= boundary) {
if (blk_rq_pos(pos) < boundary)
continue;
} else {
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
if (blk_rq_pos(pos) >= boundary)
break;
}
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
if (blk_rq_pos(rq) >= blk_rq_pos(pos))
break;
}
list_add(&rq->queuelist, entry);
}
EXPORT_SYMBOL(elv_dispatch_sort);
/*
* Insert rq into dispatch queue of q. Queue lock must be held on
* entry. rq is added to the back of the dispatch queue. To be used by
* specific elevators.
*/
void elv_dispatch_add_tail(struct request_queue *q, struct request *rq)
{
if (q->last_merge == rq)
q->last_merge = NULL;
elv_rqhash_del(q, rq);
q->nr_sorted--;
q->end_sector = rq_end_sector(rq);
q->boundary_rq = rq;
list_add_tail(&rq->queuelist, &q->queue_head);
}
EXPORT_SYMBOL(elv_dispatch_add_tail);
int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
{
struct elevator_queue *e = q->elevator;
struct request *__rq;
int ret;
/*
* Levels of merges:
* nomerges: No merges at all attempted
* noxmerges: Only simple one-hit cache try
* merges: All merge tries attempted
*/
if (blk_queue_nomerges(q) || !bio_mergeable(bio))
return ELEVATOR_NO_MERGE;
/*
* First try one-hit cache.
*/
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
ret = blk_try_merge(q->last_merge, bio);
if (ret != ELEVATOR_NO_MERGE) {
*req = q->last_merge;
return ret;
}
}
if (blk_queue_noxmerges(q))
return ELEVATOR_NO_MERGE;
/*
* See if our hash lookup can find a potential backmerge.
*/
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
if (__rq && elv_bio_merge_ok(__rq, bio)) {
*req = __rq;
return ELEVATOR_BACK_MERGE;
}
if (e->type->ops.elevator_merge_fn)
return e->type->ops.elevator_merge_fn(q, req, bio);
return ELEVATOR_NO_MERGE;
}
/*
* Attempt to do an insertion back merge. Only check for the case where
* we can append 'rq' to an existing request, so we can throw 'rq' away
* afterwards.
*
* Returns true if we merged, false otherwise
*/
static bool elv_attempt_insert_merge(struct request_queue *q,
struct request *rq)
{
struct request *__rq;
bool ret;
if (blk_queue_nomerges(q))
return false;
/*
* First try one-hit cache.
*/
if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq))
return true;
if (blk_queue_noxmerges(q))
return false;
ret = false;
/*
* See if our hash lookup can find a potential backmerge.
*/
while (1) {
__rq = elv_rqhash_find(q, blk_rq_pos(rq));
if (!__rq || !blk_attempt_req_merge(q, __rq, rq))
break;
/* The merged request could be merged with others, try again */
ret = true;
rq = __rq;
}
return ret;
}
void elv_merged_request(struct request_queue *q, struct request *rq, int type)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.elevator_merged_fn)
e->type->ops.elevator_merged_fn(q, rq, type);
if (type == ELEVATOR_BACK_MERGE)
elv_rqhash_reposition(q, rq);
q->last_merge = rq;
}
void elv_merge_requests(struct request_queue *q, struct request *rq,
struct request *next)
{
struct elevator_queue *e = q->elevator;
const int next_sorted = next->cmd_flags & REQ_SORTED;
if (next_sorted && e->type->ops.elevator_merge_req_fn)
e->type->ops.elevator_merge_req_fn(q, rq, next);
elv_rqhash_reposition(q, rq);
if (next_sorted) {
elv_rqhash_del(q, next);
q->nr_sorted--;
}
q->last_merge = rq;
}
void elv_bio_merged(struct request_queue *q, struct request *rq,
struct bio *bio)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.elevator_bio_merged_fn)
e->type->ops.elevator_bio_merged_fn(q, rq, bio);
}
#ifdef CONFIG_PM
static void blk_pm_requeue_request(struct request *rq)
{
if (rq->q->dev && !(rq->cmd_flags & REQ_PM))
rq->q->nr_pending--;
}
static void blk_pm_add_request(struct request_queue *q, struct request *rq)
{
if (q->dev && !(rq->cmd_flags & REQ_PM) && q->nr_pending++ == 0 &&
(q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING))
pm_request_resume(q->dev);
}
#else
static inline void blk_pm_requeue_request(struct request *rq) {}
static inline void blk_pm_add_request(struct request_queue *q,
struct request *rq)
{
}
#endif
void elv_requeue_request(struct request_queue *q, struct request *rq)
{
/*
* it already went through dequeue, we need to decrement the
* in_flight count again
*/
if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]--;
if (rq->cmd_flags & REQ_SORTED)
elv_deactivate_rq(q, rq);
}
rq->cmd_flags &= ~REQ_STARTED;
blk_pm_requeue_request(rq);
__elv_add_request(q, rq, ELEVATOR_INSERT_REQUEUE);
}
void elv_drain_elevator(struct request_queue *q)
{
static int printed;
lockdep_assert_held(q->queue_lock);
while (q->elevator->type->ops.elevator_dispatch_fn(q, 1))
;
if (q->nr_sorted && printed++ < 10) {
printk(KERN_ERR "%s: forced dispatching is broken "
"(nr_sorted=%u), please report this\n",
q->elevator->type->elevator_name, q->nr_sorted);
}
}
void __elv_add_request(struct request_queue *q, struct request *rq, int where)
{
trace_block_rq_insert(q, rq);
blk_pm_add_request(q, rq);
rq->q = q;
if (rq->cmd_flags & REQ_SOFTBARRIER) {
/* barriers are scheduling boundary, update end_sector */
if (rq->cmd_type == REQ_TYPE_FS) {
q->end_sector = rq_end_sector(rq);
q->boundary_rq = rq;
}
} else if (!(rq->cmd_flags & REQ_ELVPRIV) &&
(where == ELEVATOR_INSERT_SORT ||
where == ELEVATOR_INSERT_SORT_MERGE))
where = ELEVATOR_INSERT_BACK;
switch (where) {
block: drop barrier ordering by queue draining Filesystems will take all the responsibilities for ordering requests around commit writes and will only indicate how the commit writes themselves should be handled by block layers. This patch drops barrier ordering by queue draining from block layer. Ordering by draining implementation was somewhat invasive to request handling. List of notable changes follow. * Each queue has 1 bit color which is flipped on each barrier issue. This is used to track whether a given request is issued before the current barrier or not. REQ_ORDERED_COLOR flag and coloring implementation in __elv_add_request() are removed. * Requests which shouldn't be processed yet for draining were stalled by returning -EAGAIN from blk_do_ordered() according to the test result between blk_ordered_req_seq() and blk_blk_ordered_cur_seq(). This logic is removed. * Draining completion logic in elv_completed_request() removed. * All barrier sequence requests were queued to request queue and then trckled to lower layer according to progress and thus maintaining request orders during requeue was necessary. This is replaced by queueing the next request in the barrier sequence only after the current one is complete from blk_ordered_complete_seq(), which removes the need for multiple proxy requests in struct request_queue and the request sorting logic in the ELEVATOR_INSERT_REQUEUE path of elv_insert(). * As barriers no longer have ordering constraints, there's no need to dump the whole elevator onto the dispatch queue on each barrier. Insert barriers at the front instead. * If other barrier requests come to the front of the dispatch queue while one is already in progress, they are stored in q->pending_barriers and restored to dispatch queue one-by-one after each barrier completion from blk_ordered_complete_seq(). Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-09-03 09:56:16 +00:00
case ELEVATOR_INSERT_REQUEUE:
case ELEVATOR_INSERT_FRONT:
rq->cmd_flags |= REQ_SOFTBARRIER;
list_add(&rq->queuelist, &q->queue_head);
break;
case ELEVATOR_INSERT_BACK:
rq->cmd_flags |= REQ_SOFTBARRIER;
elv_drain_elevator(q);
list_add_tail(&rq->queuelist, &q->queue_head);
/*
* We kick the queue here for the following reasons.
* - The elevator might have returned NULL previously
* to delay requests and returned them now. As the
* queue wasn't empty before this request, ll_rw_blk
* won't run the queue on return, resulting in hang.
* - Usually, back inserted requests won't be merged
* with anything. There's no point in delaying queue
* processing.
*/
__blk_run_queue(q);
break;
case ELEVATOR_INSERT_SORT_MERGE:
/*
* If we succeed in merging this request with one in the
* queue already, we are done - rq has now been freed,
* so no need to do anything further.
*/
if (elv_attempt_insert_merge(q, rq))
break;
case ELEVATOR_INSERT_SORT:
BUG_ON(rq->cmd_type != REQ_TYPE_FS);
rq->cmd_flags |= REQ_SORTED;
q->nr_sorted++;
if (rq_mergeable(rq)) {
elv_rqhash_add(q, rq);
if (!q->last_merge)
q->last_merge = rq;
}
/*
* Some ioscheds (cfq) run q->request_fn directly, so
* rq cannot be accessed after calling
* elevator_add_req_fn.
*/
q->elevator->type->ops.elevator_add_req_fn(q, rq);
break;
block: reimplement FLUSH/FUA to support merge The current FLUSH/FUA support has evolved from the implementation which had to perform queue draining. As such, sequencing is done queue-wide one flush request after another. However, with the draining requirement gone, there's no reason to keep the queue-wide sequential approach. This patch reimplements FLUSH/FUA support such that each FLUSH/FUA request is sequenced individually. The actual FLUSH execution is double buffered and whenever a request wants to execute one for either PRE or POSTFLUSH, it queues on the pending queue. Once certain conditions are met, a flush request is issued and on its completion all pending requests proceed to the next sequence. This allows arbitrary merging of different type of flushes. How they are merged can be primarily controlled and tuned by adjusting the above said 'conditions' used to determine when to issue the next flush. This is inspired by Darrick's patches to merge multiple zero-data flushes which helps workloads with highly concurrent fsync requests. * As flush requests are never put on the IO scheduler, request fields used for flush share space with rq->rb_node. rq->completion_data is moved out of the union. This increases the request size by one pointer. As rq->elevator_private* are used only by the iosched too, it is possible to reduce the request size further. However, to do that, we need to modify request allocation path such that iosched data is not allocated for flush requests. * FLUSH/FUA processing happens on insertion now instead of dispatch. - Comments updated as per Vivek and Mike. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: "Darrick J. Wong" <djwong@us.ibm.com> Cc: Shaohua Li <shli@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-25 11:43:54 +00:00
case ELEVATOR_INSERT_FLUSH:
rq->cmd_flags |= REQ_SOFTBARRIER;
blk_insert_flush(rq);
break;
default:
printk(KERN_ERR "%s: bad insertion point %d\n",
__func__, where);
BUG();
}
}
EXPORT_SYMBOL(__elv_add_request);
void elv_add_request(struct request_queue *q, struct request *rq, int where)
{
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
__elv_add_request(q, rq, where);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(elv_add_request);
struct request *elv_latter_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.elevator_latter_req_fn)
return e->type->ops.elevator_latter_req_fn(q, rq);
return NULL;
}
struct request *elv_former_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.elevator_former_req_fn)
return e->type->ops.elevator_former_req_fn(q, rq);
return NULL;
}
block: implement bio_associate_current() IO scheduling and cgroup are tied to the issuing task via io_context and cgroup of %current. Unfortunately, there are cases where IOs need to be routed via a different task which makes scheduling and cgroup limit enforcement applied completely incorrectly. For example, all bios delayed by blk-throttle end up being issued by a delayed work item and get assigned the io_context of the worker task which happens to serve the work item and dumped to the default block cgroup. This is double confusing as bios which aren't delayed end up in the correct cgroup and makes using blk-throttle and cfq propio together impossible. Any code which punts IO issuing to another task is affected which is getting more and more common (e.g. btrfs). As both io_context and cgroup are firmly tied to task including userland visible APIs to manipulate them, it makes a lot of sense to match up tasks to bios. This patch implements bio_associate_current() which associates the specified bio with %current. The bio will record the associated ioc and blkcg at that point and block layer will use the recorded ones regardless of which task actually ends up issuing the bio. bio release puts the associated ioc and blkcg. It grabs and remembers ioc and blkcg instead of the task itself because task may already be dead by the time the bio is issued making ioc and blkcg inaccessible and those are all block layer cares about. elevator_set_req_fn() is updated such that the bio elvdata is being allocated for is available to the elevator. This doesn't update block cgroup policies yet. Further patches will implement the support. -v2: #ifdef CONFIG_BLK_CGROUP added around bio->bi_ioc dereference in rq_ioc() to fix build breakage. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Kent Overstreet <koverstreet@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-03-05 21:15:27 +00:00
int elv_set_request(struct request_queue *q, struct request *rq,
struct bio *bio, gfp_t gfp_mask)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.elevator_set_req_fn)
block: implement bio_associate_current() IO scheduling and cgroup are tied to the issuing task via io_context and cgroup of %current. Unfortunately, there are cases where IOs need to be routed via a different task which makes scheduling and cgroup limit enforcement applied completely incorrectly. For example, all bios delayed by blk-throttle end up being issued by a delayed work item and get assigned the io_context of the worker task which happens to serve the work item and dumped to the default block cgroup. This is double confusing as bios which aren't delayed end up in the correct cgroup and makes using blk-throttle and cfq propio together impossible. Any code which punts IO issuing to another task is affected which is getting more and more common (e.g. btrfs). As both io_context and cgroup are firmly tied to task including userland visible APIs to manipulate them, it makes a lot of sense to match up tasks to bios. This patch implements bio_associate_current() which associates the specified bio with %current. The bio will record the associated ioc and blkcg at that point and block layer will use the recorded ones regardless of which task actually ends up issuing the bio. bio release puts the associated ioc and blkcg. It grabs and remembers ioc and blkcg instead of the task itself because task may already be dead by the time the bio is issued making ioc and blkcg inaccessible and those are all block layer cares about. elevator_set_req_fn() is updated such that the bio elvdata is being allocated for is available to the elevator. This doesn't update block cgroup policies yet. Further patches will implement the support. -v2: #ifdef CONFIG_BLK_CGROUP added around bio->bi_ioc dereference in rq_ioc() to fix build breakage. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Kent Overstreet <koverstreet@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-03-05 21:15:27 +00:00
return e->type->ops.elevator_set_req_fn(q, rq, bio, gfp_mask);
return 0;
}
void elv_put_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.elevator_put_req_fn)
e->type->ops.elevator_put_req_fn(rq);
}
int elv_may_queue(struct request_queue *q, int op, int op_flags)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.elevator_may_queue_fn)
return e->type->ops.elevator_may_queue_fn(q, op, op_flags);
return ELV_MQUEUE_MAY;
}
void elv_completed_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
/*
* request is released from the driver, io must be done
*/
if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]--;
if ((rq->cmd_flags & REQ_SORTED) &&
e->type->ops.elevator_completed_req_fn)
e->type->ops.elevator_completed_req_fn(q, rq);
}
}
#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
static ssize_t
elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
struct elv_fs_entry *entry = to_elv(attr);
struct elevator_queue *e;
ssize_t error;
if (!entry->show)
return -EIO;
e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
error = e->type ? entry->show(e, page) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
static ssize_t
elv_attr_store(struct kobject *kobj, struct attribute *attr,
const char *page, size_t length)
{
struct elv_fs_entry *entry = to_elv(attr);
struct elevator_queue *e;
ssize_t error;
if (!entry->store)
return -EIO;
e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
error = e->type ? entry->store(e, page, length) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
static const struct sysfs_ops elv_sysfs_ops = {
.show = elv_attr_show,
.store = elv_attr_store,
};
static struct kobj_type elv_ktype = {
.sysfs_ops = &elv_sysfs_ops,
.release = elevator_release,
};
int elv_register_queue(struct request_queue *q)
{
struct elevator_queue *e = q->elevator;
int error;
error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
if (!error) {
struct elv_fs_entry *attr = e->type->elevator_attrs;
if (attr) {
while (attr->attr.name) {
if (sysfs_create_file(&e->kobj, &attr->attr))
break;
attr++;
}
}
kobject_uevent(&e->kobj, KOBJ_ADD);
elevator: fix oops on early call to elevator_change() 2.6.36 introduces an API for drivers to switch the IO scheduler instead of manually calling the elevator exit and init functions. This API was added since q->elevator must be cleared in between those two calls. And since we already have this functionality directly from use by the sysfs interface to switch schedulers online, it was prudent to reuse it internally too. But this API needs the queue to be in a fully initialized state before it is called, or it will attempt to unregister elevator kobjects before they have been added. This results in an oops like this: BUG: unable to handle kernel NULL pointer dereference at 0000000000000051 IP: [<ffffffff8116f15e>] sysfs_create_dir+0x2e/0xc0 PGD 47ddfc067 PUD 47c6a1067 PMD 0 Oops: 0000 [#1] PREEMPT SMP last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:04:00.1/irq CPU 2 Modules linked in: t(+) loop hid_apple usbhid ahci ehci_hcd uhci_hcd libahci usbcore nls_base igb Pid: 7319, comm: modprobe Not tainted 2.6.36-rc6+ #132 QSSC-S4R/QSSC-S4R RIP: 0010:[<ffffffff8116f15e>] [<ffffffff8116f15e>] sysfs_create_dir+0x2e/0xc0 RSP: 0018:ffff88027da25d08 EFLAGS: 00010246 RAX: ffff88047c68c528 RBX: 00000000fffffffe RCX: 0000000000000000 RDX: 000000000000002f RSI: 000000000000002f RDI: ffff88047e196c88 RBP: ffff88027da25d38 R08: 0000000000000000 R09: d84156c5635688c0 R10: d84156c5635688c0 R11: 0000000000000000 R12: ffff88047e196c88 R13: 0000000000000000 R14: 0000000000000000 R15: ffff88047c68c528 FS: 00007fcb0b26f6e0(0000) GS:ffff880287400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000051 CR3: 000000047e76e000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process modprobe (pid: 7319, threadinfo ffff88027da24000, task ffff88027d377090) Stack: ffff88027da25d58 ffff88047c68c528 00000000fffffffe ffff88047e196c88 <0> ffff88047c68c528 ffff88047e05bd90 ffff88027da25d78 ffffffff8123fb77 <0> ffff88047e05bd90 0000000000000000 ffff88047e196c88 ffff88047c68c528 Call Trace: [<ffffffff8123fb77>] kobject_add_internal+0xe7/0x1f0 [<ffffffff8123fd98>] kobject_add_varg+0x38/0x60 [<ffffffff8123feb9>] kobject_add+0x69/0x90 [<ffffffff8116efe0>] ? sysfs_remove_dir+0x20/0xa0 [<ffffffff8103d48d>] ? sub_preempt_count+0x9d/0xe0 [<ffffffff8143de20>] ? _raw_spin_unlock+0x30/0x50 [<ffffffff8116efe0>] ? sysfs_remove_dir+0x20/0xa0 [<ffffffff8116eff4>] ? sysfs_remove_dir+0x34/0xa0 [<ffffffff81224204>] elv_register_queue+0x34/0xa0 [<ffffffff81224aad>] elevator_change+0xfd/0x250 [<ffffffffa007e000>] ? t_init+0x0/0x361 [t] [<ffffffffa007e000>] ? t_init+0x0/0x361 [t] [<ffffffffa007e0a8>] t_init+0xa8/0x361 [t] [<ffffffff810001de>] do_one_initcall+0x3e/0x170 [<ffffffff8108c3fd>] sys_init_module+0xbd/0x220 [<ffffffff81002f2b>] system_call_fastpath+0x16/0x1b Code: e5 41 56 41 55 41 54 49 89 fc 53 48 83 ec 10 48 85 ff 74 52 48 8b 47 18 49 c7 c5 00 46 61 81 48 85 c0 74 04 4c 8b 68 30 45 31 f6 <41> 80 7d 51 00 74 0e 49 8b 44 24 28 4c 89 e7 ff 50 20 49 89 c6 RIP [<ffffffff8116f15e>] sysfs_create_dir+0x2e/0xc0 RSP <ffff88027da25d08> CR2: 0000000000000051 ---[ end trace a6541d3bf07945df ]--- Fix this by adding a registered bit to the elevator queue, which is set when the sysfs kobjects have been registered. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-10-07 07:35:16 +00:00
e->registered = 1;
if (e->type->ops.elevator_registered_fn)
e->type->ops.elevator_registered_fn(q);
}
return error;
}
EXPORT_SYMBOL(elv_register_queue);
void elv_unregister_queue(struct request_queue *q)
{
if (q) {
struct elevator_queue *e = q->elevator;
kobject_uevent(&e->kobj, KOBJ_REMOVE);
kobject_del(&e->kobj);
e->registered = 0;
}
}
EXPORT_SYMBOL(elv_unregister_queue);
int elv_register(struct elevator_type *e)
{
char *def = "";
/* create icq_cache if requested */
if (e->icq_size) {
if (WARN_ON(e->icq_size < sizeof(struct io_cq)) ||
WARN_ON(e->icq_align < __alignof__(struct io_cq)))
return -EINVAL;
snprintf(e->icq_cache_name, sizeof(e->icq_cache_name),
"%s_io_cq", e->elevator_name);
e->icq_cache = kmem_cache_create(e->icq_cache_name, e->icq_size,
e->icq_align, 0, NULL);
if (!e->icq_cache)
return -ENOMEM;
}
/* register, don't allow duplicate names */
spin_lock(&elv_list_lock);
if (elevator_find(e->elevator_name)) {
spin_unlock(&elv_list_lock);
if (e->icq_cache)
kmem_cache_destroy(e->icq_cache);
return -EBUSY;
}
list_add_tail(&e->list, &elv_list);
spin_unlock(&elv_list_lock);
/* print pretty message */
if (!strcmp(e->elevator_name, chosen_elevator) ||
(!*chosen_elevator &&
!strcmp(e->elevator_name, CONFIG_DEFAULT_IOSCHED)))
def = " (default)";
printk(KERN_INFO "io scheduler %s registered%s\n", e->elevator_name,
def);
return 0;
}
EXPORT_SYMBOL_GPL(elv_register);
void elv_unregister(struct elevator_type *e)
{
/* unregister */
spin_lock(&elv_list_lock);
list_del_init(&e->list);
spin_unlock(&elv_list_lock);
/*
* Destroy icq_cache if it exists. icq's are RCU managed. Make
* sure all RCU operations are complete before proceeding.
*/
if (e->icq_cache) {
rcu_barrier();
kmem_cache_destroy(e->icq_cache);
e->icq_cache = NULL;
}
}
EXPORT_SYMBOL_GPL(elv_unregister);
/*
* switch to new_e io scheduler. be careful not to introduce deadlocks -
* we don't free the old io scheduler, before we have allocated what we
* need for the new one. this way we have a chance of going back to the old
* one, if the new one fails init for some reason.
*/
static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
{
struct elevator_queue *old = q->elevator;
bool registered = old->registered;
blkcg: unify blkg's for blkcg policies Currently, blkg is per cgroup-queue-policy combination. This is unnatural and leads to various convolutions in partially used duplicate fields in blkg, config / stat access, and general management of blkgs. This patch make blkg's per cgroup-queue and let them serve all policies. blkgs are now created and destroyed by blkcg core proper. This will allow further consolidation of common management logic into blkcg core and API with better defined semantics and layering. As a transitional step to untangle blkg management, elvswitch and policy [de]registration, all blkgs except the root blkg are being shot down during elvswitch and bypass. This patch adds blkg_root_update() to update root blkg in place on policy change. This is hacky and racy but should be good enough as interim step until we get locking simplified and switch over to proper in-place update for all blkgs. -v2: Root blkgs need to be updated on elvswitch too and blkg_alloc() comment wasn't updated according to the function change. Fixed. Both pointed out by Vivek. -v3: v2 updated blkg_destroy_all() to invoke update_root_blkg_pd() for all policies. This freed root pd during elvswitch before the last queue finished exiting and led to oops. Directly invoke update_root_blkg_pd() only on BLKIO_POLICY_PROP from cfq_exit_queue(). This also is closer to what will be done with proper in-place blkg update. Reported by Vivek. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-03-05 21:15:20 +00:00
int err;
/*
* Turn on BYPASS and drain all requests w/ elevator private data.
* Block layer doesn't call into a quiesced elevator - all requests
* are directly put on the dispatch list without elevator data
* using INSERT_BACK. All requests have SOFTBARRIER set and no
* merge happens either.
*/
blk_queue_bypass_start(q);
/* unregister and clear all auxiliary data of the old elevator */
if (registered)
elv_unregister_queue(q);
spin_lock_irq(q->queue_lock);
ioc_clear_queue(q);
spin_unlock_irq(q->queue_lock);
/* allocate, init and register new elevator */
err = new_e->ops.elevator_init_fn(q, new_e);
if (err)
goto fail_init;
if (registered) {
err = elv_register_queue(q);
if (err)
goto fail_register;
}
/* done, kill the old one and finish */
elevator_exit(old);
blk_queue_bypass_end(q);
blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
return 0;
fail_register:
elevator_exit(q->elevator);
fail_init:
/* switch failed, restore and re-register old elevator */
q->elevator = old;
elv_register_queue(q);
blk_queue_bypass_end(q);
return err;
}
/*
* Switch this queue to the given IO scheduler.
*/
static int __elevator_change(struct request_queue *q, const char *name)
{
char elevator_name[ELV_NAME_MAX];
struct elevator_type *e;
if (!q->elevator)
return -ENXIO;
strlcpy(elevator_name, name, sizeof(elevator_name));
block: don't request module during elevator init Block layer allows selecting an elevator which is built as a module to be selected as system default via kernel param "elevator=". This is achieved by automatically invoking request_module() whenever a new block device is initialized and the elevator is not available. This led to an interesting deadlock problem involving async and module init. Block device probing running off an async job invokes request_module(). While the module is being loaded, it performs async_synchronize_full() which ends up waiting for the async job which is already waiting for request_module() to finish, leading to deadlock. Invoking request_module() from deep in block device init path is already nasty in itself. It seems best to avoid these situations from the beginning by moving on-demand module loading out of block init path. The previous patch made sure that the default elevator module is loaded early during boot if available. This patch removes on-demand loading of the default elevator from elevator init path. As the module would have been loaded during boot, userland-visible behavior difference should be minimal. For more details, please refer to the following thread. http://thread.gmane.org/gmane.linux.kernel/1420814 v2: The bool parameter was named @request_module which conflicted with request_module(). This built okay w/ CONFIG_MODULES because request_module() was defined as a macro. W/o CONFIG_MODULES, it causes build breakage. Rename the parameter to @try_loading. Reported by Fengguang. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Alex Riesen <raa.lkml@gmail.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2013-01-23 00:48:03 +00:00
e = elevator_get(strstrip(elevator_name), true);
if (!e) {
printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
return -EINVAL;
}
if (!strcmp(elevator_name, q->elevator->type->elevator_name)) {
elevator_put(e);
return 0;
}
return elevator_switch(q, e);
}
int elevator_change(struct request_queue *q, const char *name)
{
int ret;
/* Protect q->elevator from elevator_init() */
mutex_lock(&q->sysfs_lock);
ret = __elevator_change(q, name);
mutex_unlock(&q->sysfs_lock);
return ret;
}
EXPORT_SYMBOL(elevator_change);
ssize_t elv_iosched_store(struct request_queue *q, const char *name,
size_t count)
{
int ret;
if (!q->elevator)
return count;
ret = __elevator_change(q, name);
if (!ret)
return count;
printk(KERN_ERR "elevator: switch to %s failed\n", name);
return ret;
}
ssize_t elv_iosched_show(struct request_queue *q, char *name)
{
struct elevator_queue *e = q->elevator;
struct elevator_type *elv;
struct elevator_type *__e;
int len = 0;
if (!q->elevator || !blk_queue_stackable(q))
return sprintf(name, "none\n");
elv = e->type;
spin_lock(&elv_list_lock);
list_for_each_entry(__e, &elv_list, list) {
if (!strcmp(elv->elevator_name, __e->elevator_name))
len += sprintf(name+len, "[%s] ", elv->elevator_name);
else
len += sprintf(name+len, "%s ", __e->elevator_name);
}
spin_unlock(&elv_list_lock);
len += sprintf(len+name, "\n");
return len;
}
struct request *elv_rb_former_request(struct request_queue *q,
struct request *rq)
{
struct rb_node *rbprev = rb_prev(&rq->rb_node);
if (rbprev)
return rb_entry_rq(rbprev);
return NULL;
}
EXPORT_SYMBOL(elv_rb_former_request);
struct request *elv_rb_latter_request(struct request_queue *q,
struct request *rq)
{
struct rb_node *rbnext = rb_next(&rq->rb_node);
if (rbnext)
return rb_entry_rq(rbnext);
return NULL;
}
EXPORT_SYMBOL(elv_rb_latter_request);