- 22 10月, 2010 1 次提交
-
-
由 Vivek Goyal 提交于
- Andi encountedred following warning with gcc 4.5 linux/block/cfq-iosched.c: In function ‘cfq_dispatch_requests’: linux/block/cfq-iosched.c:2156:3: warning: array subscript is above array bounds - Warning happens due to following code. slice = group_slice * count / max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio], cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg)); gcc is complaining about cfqg->busy_queues_avg[] being indexed by CFQ prio classes (RT, BE and IDLE) while the array size is only 2. - At run time, we never access cfqg->busy_queues_avg[IDLE] and return from function before this code hits. - To fix warning increase the array size though it will remain unused. This patch also puts some comments to clarify some of the confusions. - I have taken Jens's patch and modified it a bit. - Compile tested with gcc 4.4 and boot tested. I don't have gcc 4.5 running, Andi can you please test it with gcc 4.5 to make sure it worked. Reported-by: NAndi Kleen <ak@linux.intel.com> Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Acked-by: NJeff Moyer <jmoyer@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 21 10月, 2010 1 次提交
-
-
由 Geert Uytterhoeven 提交于
Convert bvec_k{un,}map_irq() from macros to static inline functions if !CONFIG_HIGHMEM, so we can easier detect mistakes like the one fixed in 93055c31 ("ps3disk: passing wrong variable = to bvec_kunmap_irq()") Signed-off-by: NGeert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 19 10月, 2010 1 次提交
-
-
由 Yasuaki Ishimatsu 提交于
/proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. When reloading partition tables, quiesce IO to ensure that no request references to the partition struct exists. When it is safe to free the partition table, the IO for that device is restarted again. Signed-off-by: NYasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 15 10月, 2010 2 次提交
-
-
由 Martin K. Petersen 提交于
Previously we tracked whether the integrity metadata had been remapped using a request flag. This was fine for low-level retries. However, if an I/O was redriven by upper layers we would end up remapping again, causing the retry to fail. Deprecate the REQ_INTEGRITY flag and introduce BIO_MAPPED_INTEGRITY which enables filesystems to notify lower layers that the bio in question has already been remapped. Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Martin K. Petersen 提交于
Commit 3839e4b2 introduced a kobject_put but failed to remove the kmem_cache_free beneath it, leading to a double free. Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 14 10月, 2010 1 次提交
-
-
由 Martin K. Petersen 提交于
Physical block size was declared unsigned int to accomodate the maximum size reported by READ CAPACITY(16). Make sure we use the right type in the related functions. Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com> Acked-by: NMike Snitzer <snitzer@redhat.com> Cc: stable@kernel.org Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 02 10月, 2010 3 次提交
-
-
由 Vivek Goyal 提交于
o User can specify max iops value of 32bit (UINT_MAX), through cgroup interface. If a user has specified say 4294967294 (UNIT_MAX - 2), then on 32bit platform, following multiplication can overflow. io_allowed = (tg->iops[rw] * jiffy_elapsed_rnd) o Explicitly cast the multiplication to 64bit and then perform division and then check whether result is still great then UNINT_MAX. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
- Limit max iops value to UINT_MAX and return error to user if value is more than that instead of accepting bigger values and truncating implicitly. Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o Do not convert jiffies to mili seconds as it is not required. Just work with jiffies and HZ. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 01 10月, 2010 7 次提交
-
-
由 Vivek Goyal 提交于
o Randy Dunlap reported following linux-next failure. This patch fixes it. on i386: blk-throttle.c:(.text+0x1abb8): undefined reference to `__udivdi3' blk-throttle.c:(.text+0x1b1dc): undefined reference to `__udivdi3' o bytes_per_second interface is 64bit and I was continuing to do 64 bit division even on 32bit platform without help of special macros/functions hence the failure. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Reported-by: NRandy Dunlap <randy.dunlap@oracle.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o Currently any cgroup throttle limit changes are processed asynchronousy and the change does not take affect till a new bio is dispatched from same group. o It might happen that a user sets a redicuously low limit on throttling. Say 1 bytes per second on reads. In such cases simple operations like mount a disk can wait for a very long time. o Once bio is throttled, there is no easy way to come out of that wait even if user increases the read limit later. o This patch fixes it. Now if a user changes the cgroup limits, we recalculate the bio dispatch time according to new limits. o Can't take queueu lock under blkcg_lock, hence after the change I wake up the dispatch thread again which recalculates the time. So there are some variables being synchronized across two threads without lock and I had to make use of barriers. Hoping I have used barriers correctly. Any review of memory barrier code especially will help. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o Currently all the dynamically allocated groups, except root grp is added to td->tg_list. This was not a problem so far but in next patch I will travel through td->tg_list to process any updates of limits on the group. If root group is not in tg_list, then root group's updates are not processed. o It is better to root group also to tg_list instead of doing special processing for it during limit updates. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o Now a cgroup list of blkg elements can contain blkg from multiple policies. Before sending an unlink event, make sure blkg belongs to they policy. If policy does not own the blkg, do not send update for this blkg. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
Currently throttling related files were visible even if user had disabled throttling using config options. It was switching off background throttling of bio but not the cgroup files. This patch fixes it. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Malahal Naineni 提交于
The bounce_pfn of the request queue in 64 bit systems is set to the current max_low_pfn. Adding more memory later makes this incorrect. Memory allocated beyond this boot time max_low_pfn appear to require bounce buffers (bounce buffers are actually not allocated but used in calculating segments that may result in "over max segments limit" errors). Signed-off-by: NMalahal Naineni <malahal@us.ibm.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Jens Axboe 提交于
Revert "block: set the bounce_pfn to the actual DMA limit rather than to max memory" This reverts commit c49825fa. Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 25 9月, 2010 2 次提交
-
-
由 Mark Lord 提交于
Ensure that 'sysctl_hung_task_timeout_secs' is defined even when CONFIG_DETECT_HUNG_TASK is not set. This way we can safely reference it without need for ifdefs in the code elsewhere. eg. in block/blk-exec.c Signed-off-by: NMark Lord <mlord@pobox.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Malahal Naineni 提交于
The bounce_pfn of the request queue in 64 bit systems is set to the current max_low_pfn. Adding more memory later makes this incorrect. Memory allocated beyond this boot time max_low_pfn appear to require bounce buffers (bounce buffers are actually not allocated but used in calculating segments that may result in "over max segments limit" errors). Signed-off-by: NMalahal Naineni <malahal@us.ibm.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 24 9月, 2010 1 次提交
-
-
由 Mark Lord 提交于
During long I/O operations, the hang_check timer may fire, trigger stack dumps that unnecessarily alarm the user. Eg. hdparm --security-erase NULL /dev/sdb ## can take *hours* to complete So, if hang_check is armed, we should wake up periodically to prevent it from triggering. This patch uses a wake-up interval equal to half the hang_check timer period, which keeps overhead low enough. Signed-off-by: NMark Lord <mlord@pobox.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 20 9月, 2010 1 次提交
-
-
由 Corrado Zoccolo 提交于
Fsync performance for small files achieved by cfq on high-end disks is lower than what deadline can achieve, due to idling introduced between the sync write happening in process context and the journal commit. Moreover, when competing with a sequential reader, a process writing small files and fsync-ing them is starved. This patch fixes the two problems by: - marking journal commits as WRITE_SYNC, so that they get the REQ_NOIDLE flag set, - force all queues that have REQ_NOIDLE requests to be put in the noidle tree. Having the queue associated to the fsync-ing process and the one associated to journal commits in the noidle tree allows: - switching between them without idling, - fairness vs. competing idling queues, since they will be serviced only after the noidle tree expires its slice. Acked-by: NVivek Goyal <vgoyal@redhat.com> Reviewed-by: NJeff Moyer <jmoyer@redhat.com> Tested-by: NJeff Moyer <jmoyer@redhat.com> Signed-off-by: NCorrado Zoccolo <czoccolo@gmail.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 17 9月, 2010 2 次提交
-
-
由 Jens Axboe 提交于
When CONFIG_BLOCK is not enabled: init/do_mounts.c:71: error: implicit declaration of function 'dev_to_part' init/do_mounts.c:71: warning: initialization makes pointer from integer without a cast init/do_mounts.c:73: error: dereferencing pointer to incomplete type init/do_mounts.c:76: error: dereferencing pointer to incomplete type init/do_mounts.c:76: error: dereferencing pointer to incomplete type init/do_mounts.c:102: error: implicit declaration of function 'part_pack_uuid' init/do_mounts.c:104: error: 'block_class' undeclared (first use in this function) Reported-by: NRandy Dunlap <randy.dunlap@oracle.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Signed-off-by: Jan Kara 提交于
When a new disk is being discovered, add_disk() first ties the bdev to gendisk (via register_disk()->blkdev_get()) and only after that calls bdi_register_bdev(). Because register_disk() also creates disk's kobject, it can happen that userspace manages to open and modify the device's data (or inode) before its BDI is properly initialized leading to a warning in __mark_inode_dirty(). Fix the problem by registering BDI early enough. This patch addresses https://bugzilla.kernel.org/show_bug.cgi?id=16312 Cc: stable@kernel.org Reported-by: NLarry Finger <Larry.Finger@lwfinger.net> Signed-off-by: NJan Kara <jack@suse.cz> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 16 9月, 2010 9 次提交
-
-
由 Vivek Goyal 提交于
o Documentation update Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o core logic of implementing IOPS throttling. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o cgroup changes for IOPS throttling rules. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o Actual implementation of throttling policy in block layer. Currently it implements READ and WRITE bytes per second throttling logic. IOPS throttling comes in later patches. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o cgroup chagnes for throttle policy. o Introduces READ and WRITE bytes per second throttling rules. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o This patch prepares the base for introducing new IO control policies. Currently all the code is written knowing there is only one policy and that is proportional bandwidth. Creating infrastructure for newer policies to come in. o Also there were many functions which were generated using macro. It was very confusing. Got rid of those. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Vivek Goyal 提交于
o Kill extra "dev weight" header which is printed when somebody reads blkio.weight_device file. This really seems to be out of convention. No other blkio files are printing any header at the start of file. I think it is ok to just print values and how to interpret values should be part of documentation. Signed-off-by: NVivek Goyal <vgoyal@redhat.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Jens Axboe 提交于
It is also called outside the scope of init functions. Stephen reports: WARNING: init/mounts.o(.text+0x21a): Section mismatch in reference from the function name_to_dev_t() to the function .init.text:match_dev_by_uuid() The function name_to_dev_t() references the function __init match_dev_by_uuid(). This is often because name_to_dev_t lacks a __init annotation or the annotation of match_dev_by_uuid is wrong. Reported-by: NStephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Namhyung Kim 提交于
2nd argument of blk_rq_aligned() has changed to 'unsigned long' by the previous commit 'block: fix an address space warning in blk-map.c'. That commit neglected to update a user of that function. Signed-off-by: NNamhyung Kim <namhyung@gmail.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 15 9月, 2010 4 次提交
-
-
由 Will Drewry 提交于
This is the third patch in a series which adds support for storing partition metadata, optionally, off of the hd_struct. One major use for that data is being able to resolve partition by other identities than just the index on a block device. Device enumeration varies by platform and there's a benefit to being able to use something like EFI GPT's GUIDs to determine the correct block device and partition to mount as the root. This change adds that support to root= by adding support for the following syntax: root=PARTUUID=hex-uuid Signed-off-by: NWill Drewry <wad@chromium.org> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Will Drewry 提交于
This change extends the partition_meta_info structure to support EFI GPT-specific metadata and ensures that data is copied in on partition scanning. Signed-off-by: NWill Drewry <wad@chromium.org> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Will Drewry 提交于
I'm reposting this patch series as v4 since there have been no additional comments, and I cleaned up one extra bit of unneeded code (in 3/3). The patches are against Linus's tree: 2bfc96a1 (2.6.36-rc3). Would this patchset be suitable for inclusion in an mm branch? This changes adds a partition_meta_info struct which itself contains a union of structures that provide partition table specific metadata. This change leaves the union empty. The subsequent patch includes an implementation for CONFIG_EFI_PARTITION-based metadata. Signed-off-by: NWill Drewry <wad@chromium.org> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
由 Namhyung Kim 提交于
Change type of 2nd parameter of blk_rq_aligned() into unsigned long and remove unnecessary casting. Now we can call it with 'uaddr' instead of 'ubuf' in __blk_rq_map_user() so that it can remove following warnings from sparse: block/blk-map.c:57:31: warning: incorrect type in argument 2 (different address spaces) block/blk-map.c:57:31: expected void *addr block/blk-map.c:57:31: got void [noderef] <asn:1>*ubuf However blk_rq_map_kern() needs one more local variable to handle it. Signed-off-by: NNamhyung Kim <namhyung@gmail.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 14 9月, 2010 1 次提交
-
-
由 San Mehat 提交于
Signed-off-by: NSan Mehat <san@android.com> Signed-off-by: NLinus Walleij <linus.walleij@stericsson.com> Signed-off-by: NJens Axboe <jaxboe@fusionio.com>
-
- 11 9月, 2010 3 次提交
-
-
由 Christof Schmitt 提交于
When sending DIX integrity segments with an I/O request, the restriction for the maximum number of segments is still the same for the zfcp hardware. Report the new sg_prot_tablesize for the SCSI host, so that the number of integrity segments plus the number of data segments is not larger than the hardware limit. This results in using half of the hardware segments for integrity data and the other half for regular data. Reviewed-by: NSwen Schillig <swen@vnet.ibm.com> Signed-off-by: NChristof Schmitt <christof.schmitt@de.ibm.com> Signed-off-by: NJens Axboe <axboe@carl.home.kernel.dk>
-
由 Martin K. Petersen 提交于
Some controllers have a hardware limit on the number of protection information scatter-gather list segments they can handle. Introduce a max_integrity_segments limit in the block layer and provide a new scsi_host_template setting that allows HBA drivers to provide a value suitable for the hardware. Add support for honoring the integrity segment limit when merging both bios and requests. Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com> Signed-off-by: NJens Axboe <axboe@carl.home.kernel.dk>
-
由 Martin K. Petersen 提交于
We have several users of min_not_zero, each of them using their own definition. Move the define to kernel.h. Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com> Signed-off-by: NJens Axboe <axboe@carl.home.kernel.dk>
-
- 23 8月, 2010 1 次提交
-
-
由 Linus Torvalds 提交于
-