03 Jun, 2011
1 commit
-
Hi, Jens,
If you recall, I posted an RFC patch for this back in July of last year:
http://lkml.org/lkml/2010/7/13/279The basic problem is that a process can issue a never-ending stream of
async direct I/Os to the same sector on a device, thus starving out
other I/O in the system (due to the way the alias handling works in both
cfq and deadline). The solution I proposed back then was to start
dispatching from the fifo after a certain number of aliases had been
dispatched. Vivek asked why we had to treat aliases differently at all,
and I never had a good answer. So, I put together a simple patch which
allows aliases to be added to the rb tree (it adds them to the right,
though that doesn't matter as the order isn't guaranteed anyway). I
think this is the preferred solution, as it doesn't break up time slices
in CFQ or batches in deadline. I've tested it, and it does solve the
starvation issue. Let me know what you think.Cheers,
JeffSigned-off-by: Jeff Moyer
Signed-off-by: Jens Axboe
21 May, 2011
2 commits
-
We don't need them anymore, so kill:
- REQ_ON_PLUG checks in various places
- !rq_mergeable() check in plug mergingSigned-off-by: Jens Axboe
-
Since for-2.6.40/core was forked off the 2.6.39 devel tree, we've
had churn in the core area that makes it difficult to handle
patches for eg cfq or blk-throttle. Instead of requiring that they
be based in older versions with bugs that have been fixed later
in the rc cycle, merge in 2.6.39 final.Also fixes up conflicts in the below files.
Conflicts:
drivers/block/paride/pcd.c
drivers/cdrom/viocd.c
drivers/ide/ide-cd.cSigned-off-by: Jens Axboe
06 May, 2011
1 commit
-
After the anticipatory scheduler was dropped, there was no need to
special-case the request_module string. As such, drop the redundant
sprintf and stack variable.Signed-off-by: Kees Cook
Signed-off-by: Jens Axboe
22 Apr, 2011
1 commit
-
The sort insert is the one that goes to the IO scheduler. With
the SORT_MERGE addition, we could bypass IO scheduler setup
but still ask the IO scheduler to insert the request. This would
cause an oops on switching IO schedulers through the sysfs
interface, unless the disk just happened to be idle while it
occured.Signed-off-by: Jens Axboe
18 Apr, 2011
1 commit
-
Instead of overloading __blk_run_queue to force an offload to kblockd
add a new blk_run_queue_async helper to do it explicitly. I've kept
the blk_queue_stopped check for now, but I suspect it's not needed
as the check we do when the workqueue items runs should be enough.Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe
06 Apr, 2011
1 commit
-
Merge it with __elv_add_request(), it's pretty pointless to
have a function with only two callers. The main interface
is elv_add_request()/__elv_add_request().Signed-off-by: Jens Axboe
21 Mar, 2011
1 commit
-
One of the disadvantages of on-stack plugging is that we potentially
lose out on merging since all pending IO isn't always visible to
everybody. When we flush the on-stack plugs, right now we don't do
any checks to see if potential merge candidates could be utilized.Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE.
It works just ELEVATOR_INSERT_SORT, but first checks whether we can
merge with an existing request before doing the insertion (if we fail
merging).This fixes a regression with multiple processes issuing IO that
can be merged.Thanks to Shaohua Li for testing and fixing
an accounting bug.Signed-off-by: Jens Axboe
10 Mar, 2011
3 commits
-
Conflicts:
block/blk-core.c
block/blk-flush.c
drivers/md/raid1.c
drivers/md/raid10.c
drivers/md/raid5.c
fs/nilfs2/btnode.c
fs/nilfs2/mdt.cSigned-off-by: Jens Axboe
-
Code has been converted over to the new explicit on-stack plugging,
and delay users have been converted to use the new API for that.
So lets kill off the old plugging along with aops->sync_page().Signed-off-by: Jens Axboe
-
This patch adds support for creating a queuing context outside
of the queue itself. This enables us to batch up pieces of IO
before grabbing the block device queue lock and submitting them to
the IO scheduler.The context is created on the stack of the process and assigned in
the task structure, so that we can auto-unplug it if we hit a schedule
event.The current queue plugging happens implicitly if IO is submitted to
an empty device, yet callers have to remember to unplug that IO when
they are going to wait for it. This is an ugly API and has caused bugs
in the past. Additionally, it requires hacks in the vm (->sync_page()
callback) to handle that logic. By switching to an explicit plugging
scheme we make the API a lot nicer and can get rid of the ->sync_page()
hack in the vm.Signed-off-by: Jens Axboe
05 Mar, 2011
1 commit
-
This merge creates two set of conflicts. One is simple context
conflicts caused by removal of throtl_scheduled_delayed_work() in
for-linus and removal of throtl_shutdown_timer_wq() in
for-2.6.39/core.The other is caused by commit 255bb490c8 (block: blk-flush shouldn't
call directly into q->request_fn() __blk_run_queue()) in for-linus
crashing with FLUSH reimplementation in for-2.6.39/core. The conflict
isn't trivial but the resolution is straight-forward.* __blk_run_queue() calls in flush_end_io() and flush_data_end_io()
should be called with @force_kblockd set to %true.* elv_insert() in blk_kick_flush() should use
%ELEVATOR_INSERT_REQUEUE.Both changes are to avoid invoking ->request_fn() directly from
request completion path and closely match the changes in the commit
255bb490c8.Signed-off-by: Tejun Heo
02 Mar, 2011
1 commit
-
__blk_run_queue() automatically either calls q->request_fn() directly
or schedules kblockd depending on whether the function is recursed.
blk-flush implementation needs to be able to explicitly choose
kblockd. Add @force_kblockd.All the current users are converted to specify %false for the
parameter and this patch doesn't introduce any behavior change.stable: This is prerequisite for fixing ide oops caused by the new
blk-flush implementation.Signed-off-by: Tejun Heo
Cc: Jan Beulich
Cc: James Bottomley
Cc: stable@kernel.org
Signed-off-by: Jens Axboe
11 Feb, 2011
1 commit
-
Flush requests are never put on the IO scheduler. Convert request
structure's elevator_private* into an array and have the flush fields
share a union with it.Reclaim the space lost in 'struct request' by moving 'completion_data'
back in the union with 'rb_node'.Signed-off-by: Mike Snitzer
Acked-by: Vivek Goyal
Acked-by: Tejun Heo
Signed-off-by: Jens Axboe
25 Jan, 2011
1 commit
-
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
Cc: "Darrick J. Wong"
Cc: Shaohua Li
Cc: Christoph Hellwig
Cc: Vivek Goyal
Cc: Mike Snitzer
Signed-off-by: Jens Axboe
10 Nov, 2010
1 commit
-
REQ_HARDBARRIER is dead now, so remove the leftovers. What's left
at this point is:- various checks inside the block layer.
- sanity checks in bio based drivers.
- now unused bio_empty_barrier helper.
- Xen blockfront use of BLKIF_OP_WRITE_BARRIER - it's dead for a while,
but Xen really needs to sort out it's barrier situaton.
- setting of ordered tags in uas - dead code copied from old scsi
drivers.
- scsi different retry for barriers - it's dead and should have been
removed when flushes were converted to FS requests.
- blktrace handling of barriers - removed. Someone who knows blktrace
better should add support for REQ_FLUSH and REQ_FUA, though.Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe
19 Oct, 2010
1 commit
-
Conflicts:
block/blk-core.c
drivers/block/loop.c
mm/swapfile.cSigned-off-by: Jens Axboe
07 Oct, 2010
1 commit
-
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: [] 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 igbPid: 7319, comm: modprobe Not tainted 2.6.36-rc6+ #132 QSSC-S4R/QSSC-S4R
RIP: 0010:[] [] 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
ffff88047c68c528 ffff88047e05bd90 ffff88027da25d78 ffffffff8123fb77
ffff88047e05bd90 0000000000000000 ffff88047e196c88 ffff88047c68c528
Call Trace:
[] kobject_add_internal+0xe7/0x1f0
[] kobject_add_varg+0x38/0x60
[] kobject_add+0x69/0x90
[] ? sysfs_remove_dir+0x20/0xa0
[] ? sub_preempt_count+0x9d/0xe0
[] ? _raw_spin_unlock+0x30/0x50
[] ? sysfs_remove_dir+0x20/0xa0
[] ? sysfs_remove_dir+0x34/0xa0
[] elv_register_queue+0x34/0xa0
[] elevator_change+0xfd/0x250
[] ? t_init+0x0/0x361 [t]
[] ? t_init+0x0/0x361 [t]
[] t_init+0xa8/0x361 [t]
[] do_one_initcall+0x3e/0x170
[] sys_init_module+0xbd/0x220
[] 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 80 7d 51 00 74 0e 49 8b 44 24 28 4c 89 e7 ff 50 20 49 89 c6
RIP [] sysfs_create_dir+0x2e/0xc0
RSP
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
10 Sep, 2010
1 commit
-
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
Cc: Christoph Hellwig
Signed-off-by: Jens Axboe
23 Aug, 2010
1 commit
-
Currently drivers must do an elevator_exit() + elevator_init()
to switch IO schedulers. There are a few problems with this:- Since commit 1abec4fdbb142e3ccb6ce99832fae42129134a96,
elevator_init() requires a zeroed out q->elevator
pointer. The two existing in-kernel users don't do that.- It will only work at initialization time, since using the
above two-staged construct does not properly quisce the queue.So add elevator_change() which takes care of this, and convert
the elv_iosched_store() sysfs interface to use this helper as well.Reported-by: Peter Oberparleiter
Reported-by: Kevin Vigor
Signed-off-by: Jens Axboe
12 Aug, 2010
1 commit
-
Secure discard is the same as discard except that all copies of the
discarded sectors (perhaps created by garbage collection) must also be
erased.Signed-off-by: Adrian Hunter
Acked-by: Jens Axboe
Cc: Kyungmin Park
Cc: Madhusudhan Chikkature
Cc: Christoph Hellwig
Cc: Ben Gardiner
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
08 Aug, 2010
2 commits
-
Remove the current bio flags and reuse the request flags for the bio, too.
This allows to more easily trace the type of I/O from the filesystem
down to the block driver. There were two flags in the bio that were
missing in the requests: BIO_RW_UNPLUG and BIO_RW_AHEAD. Also I've
renamed two request flags that had a superflous RW in them.Note that the flags are in bio.h despite having the REQ_ name - as
blkdev.h includes bio.h that is the only way to go for now.Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe -
Remove all the trivial wrappers for the cmd_type and cmd_flags fields in
struct requests. This allows much easier grepping for different request
types instead of unwinding through macros.Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe
04 Jun, 2010
1 commit
-
blk_init_allocated_queue_node may fail and the caller _could_ retry.
Accommodate the unlikely event that blk_init_allocated_queue_node is
called on an already initialized (possibly partially) request_queue.Signed-off-by: Mike Snitzer
Signed-off-by: Jens Axboe
24 May, 2010
1 commit
-
Bio-based DM doesn't use an elevator (queue is !blk_queue_stackable()).
Longer-term DM will not allocate an elevator for bio-based DM. But even
then there will be small potential for an elevator to be allocated for
a request-based DM table only to have a bio-based table be loaded in the
end.Displaying "none" for bio-based DM will help avoid user confusion.
Signed-off-by: Mike Snitzer
Signed-off-by: Jens Axboe
11 May, 2010
1 commit
-
blk_init_queue() allocates the request_queue structure and then
initializes it as needed (request_fn, elevator, etc).Split initialization out to blk_init_allocated_queue_node.
Introduce blk_init_allocated_queue wrapper function to model existing
blk_init_queue and blk_init_queue_node interfaces.Export elv_register_queue to allow a newly added elevator to be
registered with sysfs. Export elv_unregister_queue for symmetry.These changes allow DM to initialize a device's request_queue with more
precision. In particular, DM no longer unconditionally initializes a
full request_queue (elevator et al). It only does so for a
request-based DM device.Signed-off-by: Mike Snitzer
Signed-off-by: Jens Axboe
09 Apr, 2010
1 commit
-
This includes both the number of bios merged into requests belonging to this
cgroup as well as the number of requests merged together.
In the past, we've observed different merging behavior across upstream kernels,
some by design some actual bugs. This stat helps a lot in debugging such
problems when applications report decreased throughput with a new kernel
version.This needed adding an extra elevator function to capture bios being merged as I
did not want to pollute elevator code with blkiocg knowledge and hence needed
the accounting invocation to come from CFQ.Signed-off-by: Divyesh Shah
Signed-off-by: Jens Axboe
02 Apr, 2010
1 commit
-
elevator_get() not check the name length, if the name length > sizeof(elv),
elv will miss the '\0'. And elv buffer will be replace "-iosched" as something
like aaaaaaaaa, then call request_module() can load an not trust module.Signed-off-by: Zhitong Wang
Signed-off-by: Jens Axboe
08 Mar, 2010
1 commit
-
Constify struct sysfs_ops.
This is part of the ops structure constification
effort started by Arjan van de Ven et al.Benefits of this constification:
* prevents modification of data that is shared
(referenced) by many other structure instances
at runtime* detects/prevents accidental (but not intentional)
modification attempts on archs that enforce
read-only kernel data at runtime* potentially better optimized code as the compiler
can assume that the const data cannot be changed* the compiler/linker move const data into .rodata
and therefore exclude them from false sharingSigned-off-by: Emese Revfy
Acked-by: David Teigland
Acked-by: Matt Domsch
Acked-by: Maciej Sosnowski
Acked-by: Hans J. Koch
Acked-by: Pekka Enberg
Acked-by: Jens Axboe
Acked-by: Stephen Hemminger
Signed-off-by: Greg Kroah-Hartman
29 Jan, 2010
1 commit
-
Updated 'nomerges' tunable to accept a value of '2' - indicating that _no_
merges at all are to be attempted (not even the simple one-hit cache).The following table illustrates the additional benefit - 5 minute runs of
a random I/O load were applied to a dozen devices on a 16-way x86_64 system.nomerges Throughput %System Improvement (tput / %sys)
-------- ------------ ----------- -------------------------
0 12.45 MB/sec 0.669365609
1 12.50 MB/sec 0.641519199 0.40% / 2.71%
2 12.52 MB/sec 0.639849750 0.56% / 2.96%Signed-off-by: Alan D. Brunelle
Signed-off-by: Jens Axboe
13 Oct, 2009
1 commit
09 Oct, 2009
1 commit
-
elv_iosched_store() ignore the return value of strstrip(). It makes small
inconsistent behavior.This patch fixes it.
====================================
# cd /sys/block/{blockdev}/queuecase1:
# echo "anticipatory" > scheduler
# cat scheduler
noop [anticipatory] deadline cfqcase2:
# echo "anticipatory " > scheduler
# cat scheduler
noop [anticipatory] deadline cfqcase3:
# echo " anticipatory" > scheduler
bash: echo: write error: Invalid argument
====================================
# cd /sys/block/{blockdev}/queuecase1:
# echo "anticipatory" > scheduler
# cat scheduler
noop [anticipatory] deadline cfqcase2:
# echo "anticipatory " > scheduler
# cat scheduler
noop [anticipatory] deadline cfqcase3:
# echo " anticipatory" > scheduler
noop [anticipatory] deadline cfqCc: Li Zefan
Cc: Jens Axboe
Signed-off-by: KOSAKI Motohiro
Signed-off-by: Jens Axboe
03 Oct, 2009
1 commit
-
AS is mostly a subset of CFQ, so there's little point in still
providing this separate IO scheduler. Hopefully at some point we
can get down to one single IO scheduler again, at least this brings
us closer by having only one intelligent IO scheduler.Signed-off-by: Jens Axboe
11 Sep, 2009
2 commits
-
Get rid of any functions that test for these bits and make callers
use bio_rw_flagged() directly. Then it is at least directly apparent
what variable and flag they check.Signed-off-by: Jens Axboe
-
Update scsi_io_completion() such that it only fails requests till the
next error boundary and retry the leftover. This enables block layer
to merge requests with different failfast settings and still behave
correctly on errors. Allow merge of requests of different failfast
settings.As SCSI is currently the only subsystem which follows failfast status,
there's no need to worry about other block drivers for now.Signed-off-by: Tejun Heo
Cc: Niel Lambrechts
Cc: James Bottomley
Signed-off-by: Jens Axboe
17 Jul, 2009
1 commit
-
Commit ab0fd1debe730ec9998678a0c53caefbd121ed10 tries to prevent merge
of requests with different failfast settings. In elv_rq_merge_ok(),
it compares new bio's failfast flags against the merge target
request's. However, the flag testing accessors for bio and blk don't
return boolean but the tested bit value directly and FAILFAST on bio
and blk don't match, so directly comparing them with == results in
false negative unnecessary preventing merge of readahead requests.This patch convert the results to boolean by negating them before
comparison.Signed-off-by: Tejun Heo
Cc: Jens Axboe
Cc: Boaz Harrosh
Cc: FUJITA Tomonori
Cc: James Bottomley
Cc: Jeff Garzik
04 Jul, 2009
1 commit
-
Block layer used to merge requests and bios with different failfast
settings. This caused regular IOs to fail prematurely when they were
merged into failfast requests for readahead.Niel Lambrechts could trigger the problem semi-reliably on ext4 when
resuming from STR. ext4 uses readahead when reading inodes and
combined with the deterministic extra SATA PHY exception cycle during
resume on the specific configuration, non-readahead inode read would
fail causing ext4 errors. Please read the following thread for
details.http://lkml.org/lkml/2009/5/23/21
This patch makes block layer reject merging if the failfast settings
don't match. This is correct but likely to lower IO performance by
preventing regular IOs from mingling into surrounding readahead
requests. Changes to allow such mixed merges and handle errors
correctly will be added later.Signed-off-by: Tejun Heo
Reported-by: Niel Lambrechts
Cc: Theodore Tso
Signed-off-by: Jens Axboe
12 Jun, 2009
1 commit
-
* 'for-2.6.31' of git://git.kernel.dk/linux-2.6-block: (153 commits)
block: add request clone interface (v2)
floppy: fix hibernation
ramdisk: remove long-deprecated "ramdisk=" boot-time parameter
fs/bio.c: add missing __user annotation
block: prevent possible io_context->refcount overflow
Add serial number support for virtio_blk, V4a
block: Add missing bounce_pfn stacking and fix comments
Revert "block: Fix bounce limit setting in DM"
cciss: decode unit attention in SCSI error handling code
cciss: Remove no longer needed sendcmd reject processing code
cciss: change SCSI error handling routines to work with interrupts enabled.
cciss: separate error processing and command retrying code in sendcmd_withirq_core()
cciss: factor out fix target status processing code from sendcmd functions
cciss: simplify interface of sendcmd() and sendcmd_withirq()
cciss: factor out core of sendcmd_withirq() for use by SCSI error handling code
cciss: Use schedule_timeout_uninterruptible in SCSI error handling code
block: needs to set the residual length of a bidi request
Revert "block: implement blkdev_readpages"
block: Fix bounce limit setting in DM
Removed reference to non-existing file Documentation/PCI/PCI-DMA-mapping.txt
...Manually fix conflicts with tracing updates in:
block/blk-sysfs.c
drivers/ide/ide-atapi.c
drivers/ide/ide-cd.c
drivers/ide/ide-floppy.c
drivers/ide/ide-tape.c
include/trace/events/block.h
kernel/trace/blktrace.c
10 Jun, 2009
1 commit
-
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/sSo 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.outFollowing 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] 1remap:
kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 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
LKML-Reference:
Signed-off-by: Steven Rostedt
02 Jun, 2009
1 commit
-
I found one more mis-conversion to the 'request is always dequeued
when completing' model in elv_abort_queue() during code inspection.
Although I haven't hit any problem caused by this mis-conversion yet
and just done compile/boot test, please apply if you have no problem.Request must be dequeued when it completes.
However, elv_abort_queue() completes requests without dequeueing.
This will cause oops in the __blk_end_request_all().
This patch fixes the oops.Signed-off-by: Kiyoshi Ueda
Signed-off-by: Jun'ichi Nomura
Signed-off-by: Jens Axboe
