a (reference) in projects: spdk - OpenGrok search results

Project(s)

Full Search
Definition
Symbol
File Path
History
Type

Searched refs:a (Results 1 – 25 of 131) sorted by relevance

12 3 4 5 6

/spdk/doc/
H A D	two.min.js	31 …a=document.body.getBoundingClientRect(),c=this.width=a.width,a=this.height=a.height;this.renderer.… 32 …a){return a},isArguments:function(a){return"[object Arguments]"===h.call(a)},isFunction:function(a… argument 33 …a))},isNaN:function(a){return d.isNumber(a)&&a!==+a},isBoolean:function(a){return!0===a\|\|!1===a\|\|"… argument 34 …a},toArray:function(a){return a?d.isArray(a)?x.call(a):q(a)?d.map(a,d.identity):d.values(a):[]},ra… argument 35 …a.bind===f)return f.apply(a,x.call(arguments,1));var e=x.call(arguments,2);return function(){a.app… argument 36 …a),f=[],e=0;e<c.length;e++)f.push(a[c[e]]);return f},each:function(a,c,f){f=f\|\|this;for(var e=!q(a… argument 37 …a){var c=++d._indexAmount+"";return a?a+c:c}},e=Math.sin,a=Math.cos,g=Math.atan2,n=Math.sqrt,f=Mat… argument 38 …a.attachEvent("on"+c,f);return w},unbind:function(a,c,f,e){w.hasEventListeners?a.removeEventListen… argument 39 …a,function(a,c){"fullscreen"!==c&&"autostart"!==c&&(this[c]=a)},this);if(d.isElement(a.domElement)… argument 40 ….bind(l,"resize",a),a()):d.isElement(a.domElement)\|\|(this.renderer.setSize(a.width,a.height,this.r… [all …]
H A D	sma.md	3 Storage Management Agent (SMA) is a service providing a gRPC interface for 4 orchestrating SPDK applications. It's a standalone application that allows 10 deployments on IPUs (Infrastructure Processing Unit), which usually require a 15 The interface is defined in a protobuf files located in `proto` 21 main types of objects: volumes and devices. A volume is a representation of 22 some storage media. It is equivalent to a SPDK bdev and/or an NVMe namespace 24 usually a virtual/physical PCIe function that is exposed to a host. It is 26 to a host. 28 The following sections provide a high-level description of each method. For 33 This method creates a device. If a device with given parameters already exists, [all …]
H A D	bdev_pg.md	10 A block device is a storage device that supports reading and writing data in 15 The block device layer consists of a single generic library in `lib/bdev`, 16 plus a number of optional modules (as separate libraries) that implement 20 API. For a guide to implementing a bdev module, see @ref bdev_module. 22 The bdev layer provides a number of useful features in addition to providing a 32 Users of the bdev API interact with a number of basic objects. 34 struct spdk_bdev, which this guide will refer to as a bdev, represents a 35 generic block device. struct spdk_bdev_desc, heretofore called a descriptor, 36 represents a handle to a given block device. Descriptors are used to establish 37 and track permissions to use the underlying block device, much like a file [all …]
H A D	nvme_spec.md	5 The NVMe specification describes a hardware interface for interacting with 7 remote storage as well as a hardware register layout for local PCIe devices. 8 What follows here is an overview of how an I/O is submitted to a local PCIe 12 queue pairs in host memory. The term "host" is used a lot, so to clarify that's 14 queues - a submission queue and a completion queue. These queues are more 21 An I/O is submitted to an NVMe device by constructing a 64 byte command, placing 24 submission queue tail doorbell register. It's actually valid to copy a whole set 28 There is a very detailed description of the command submission and completion 33 necessary, a location in host memory containing a descriptor for host memory 34 associated with the command. This host memory is the data to be written on a [all …]
H A D	blob.md	18 intended to serve as a design document or an API reference and in some cases source code snippets a… 23 Blobstore is a persistent, power-fail safe block allocator designed to be used as the local storage… 24 backing a higher level storage service, typically in lieu of a traditional filesystem. These higher… 26 distributed storage systems (ex. Ceph, Cassandra). It is not designed to be a general purpose files… 29 groups of blocks on a block device called 'blobs'. Blobs are typically large, measured in at least … 30 kilobytes, and are always a multiple of the underlying block size. 40 The Blobstore defines a hierarchy of storage abstractions as follows. 44 * Page: A page is defined to be a fixed number of logical blocks defined at Blobstore creation … 45 …blocks that compose a page are always contiguous. Pages are also numbered from the beginning of th… 49 * Cluster: A cluster is a fixed number of pages defined at Blobstore creation time. The pages t… [all …]
H A D	bdev_module.md	1 # Writing a Custom Block Device Module {#bdev_module} 6 device modules to integrate with SPDK's bdev layer. For a guide on how to use 11 A block device module is SPDK's equivalent of a device driver in a traditional 12 operating system. The module provides a set of function pointers that are 13 called to service block device I/O requests. SPDK provides a number of block 17 how to write a module. 22 currently possible to place the code for a bdev module elsewhere, but updates 23 to the build system could be made to enable this in the future. To create a 24 module, add a new directory with a single C file and a Makefile. A great 28 include/spdk/bdev_module.h. In that header a macro is defined that registers [all …]
H A D	ssd_internals.md	6 up with better software designs. It should not be thought of as a strictly 10 [NAND Flash](https://en.wikipedia.org/wiki/Flash_memory) memory. At a 11 very high level, this media has a few important properties: 15 * Flipping a bit is a highly asymmetric process. Flipping it one way is 22 bit-granularity once. In order to write to the erase block a second time, the 24 0). This is the asymmetry part from above. Erasing a block causes a measurable 25 amount of wear and each block may only be erased a limited number of times. 28 drive is composed of a set of fixed size logical blocks which are usually 30 device firmware and they do not statically map to a location on the backing 31 media. Instead, upon each write to a logical block, a new location on the NAND [all …]
H A D	concurrency.md	15 the heap, protecting it with a lock, and then having all threads of execution 21 version. You add a lock around the data. 22 * You can write your program as a synchronous, imperative list of statements 29 the complexity of the program. Even then, beyond a certain number of contended 33 SPDK takes a different approach altogether. Instead of placing shared data in a 34 global location that all threads access after acquiring a lock, SPDK will often 35 assign that data to a single thread. When other threads want to access the data, 36 they pass a message to the owning thread to perform the operation on their 41 in SPDK consists of a function pointer and a pointer to some context. Messages 42 are passed between threads using a [all …]
H A D	nvmf_tgt_pg.md	8 guide will not cover how to use the SPDK NVMe-oF target application. For a 24 The library exposes a number of primitives - basic objects that the user 31 throughout this guide as a target. 35 access control. This will be referred to throughout this guide as a 40 the SPDK bdev layer. This will be referred to throughout this guide as a 45 throughout this guide as a qpair. 47 `struct spdk_nvmf_transport`: An abstraction for a network fabric, as defined 49 different network fabrics, so the code mirrors that and implements a plugin 51 to throughout this guide as a transport. 53 `struct spdk_nvmf_poll_group`: An abstraction for a collection of network [all …]
H A D	memory.md	21 done at a much more granular level than a full page. 37 memory to be describable by what is called a PRP list. To be described by a 41 * The first device page can be a partial page starting at any 4-byte aligned 44 * If there is more than one device page, the first device page must end on a 46 * The last device page begins on a physical 4KiB page boundary, but is not 47 required to end on a physical 4KiB page boundary. 55 User space drivers run in the context of a regular process and so have access 60 within a process. This file contains the virtual address to physical address 64 into whether a PCI device is directly transferring data to a set of physical 66 movement. When an operating system flags a page such that the virtual to [all …]
H A D	userspace.md	6 important to understand what that means at a technical level. First and 7 foremost, a _driver_ is software that directly controls a particular device 8 attached to a computer. Second, operating systems segregate the system's 18 In order for SPDK to take control of a device, it must first instruct the 21 [writing to a file in sysfs](https://lwn.net/Articles/143397/). 27 system that the device has a driver bound to it so it won't automatically try 33 which is a critical piece of hardware for ensuring memory safety in user space 42 implementations of most of the layers in a typical operating system storage 44 This includes a [block device abstraction layer](@ref bdev) primarily, but 59 are a number of reasons for doing this: 1) practically speaking, routing an [all …]
H A D	vhost_processing.md	22 > and guests should have a straightforward, efficient, standard and extensible 26 Virtio devices use virtqueues to transport data efficiently. Virtqueue is a set 29 where the QEMU itself exposes a virtual PCI device and the guest OS communicates 30 with it using a specific Virtio PCI driver. With only Virtio involved, it's 33 Vhost is a protocol for devices accessible via inter-process communication. 35 directly to Virtio devices. This allows a Vhost device, exposed by an SPDK 36 application, to be accessed directly by a guest OS inside a QEMU process with 41 The initial vhost implementation is a part of the Linux kernel and uses ioctl 43 SPDK to expose a vhost device is Vhost-user protocol. 50 > plane needed to establish virtqueue sharing with a user space process on the [all …]
H A D	blobfs.md	16 Clone the RocksDB repository from the SPDK GitHub fork into a separate directory. 31 Or you can also add `DEBUG_LEVEL=0` for a release build (need to turn on `USE_RTTI`). 68 SPDK has a set of scripts which will run `db_bench` against a variety of workloads and capture perf… 73 BlobFS provides a FUSE plug-in to mount an SPDK BlobFS as a kernel filesystem for inspection or deb… 84 …rily been tested with RocksDB so far, so any use cases different from how RocksDB uses a filesystem 85 …may run into issues. BlobFS will be tested in a broader range of use cases after this initial rel… 86 * Only a synchronous API is currently supported. An asynchronous API has been developed but not th… 87 yet so is not part of the public interface yet. This will be added in a future release. 88 * File renames are not atomic. This will be fixed in a future release. 89 * BlobFS currently supports only a flat namespace for files with no directory support. Filenames a… [all …]
H A D	about.md	3 The Storage Performance Development Kit (SPDK) provides a set of tools and 5 applications. It achieves high performance through the use of a number of key 14 The bedrock of SPDK is a user space, polled-mode, asynchronous, lockless 16 parallel access directly to an SSD from a user space application. The driver is 17 written as a C library with a single public header. See @ref nvme for more 20 SPDK further provides a full block stack as a user space library that performs 21 many of the same operations as a block stack in an operating system. This 34 implementations. These targets can be used as examples of how to implement a
H A D	overview.md	5 SPDK is composed of a set of C libraries residing in `lib` with public interface 6 header files in `include/spdk`, plus a set of applications built out of those 22 `include/spdk/stdinc.h`. However, SPDK requires a number of operations that 25 abstracted in a library called `env` whose public header is at 26 `include/spdk/env.h`. By default, SPDK implements the `env` interface using a 33 components. For a full overview, see @ref app_overview. 35 SPDK applications can typically be started with a small number of configuration 41 The `lib` directory contains the real heart of SPDK. Each component is a C library with 57 The `examples` top-level directory contains a set of examples intended to be used 58 for reference. These are different than the applications, which are doing a "real" [all …]
H A D	ftl.md	20 Since the L2P would occupy a significant amount of DRAM (4B/LBA for drives smaller than 16TiB, 27 A band describes a collection of zones, each belonging to a different parallel unit. All writes to 28 a band follow the same pattern - a batch of logical blocks is written to one zone, another batch 53 The address map (`P2L`) is saved as a part of the band's metadata, at the end of each band: 63 Bands are written sequentially (in a way that was described earlier). Before a band can be written 64 to, all of its zones need to be erased. During that time, the band is considered to be in a `PREP` 73 Nvcache is a bdev that is used for buffering user writes and storing various metadata. 99 Since a write to the same LBA invalidates its previous physical location, some of the blocks on a 101 written block for a ZNS drive, this data will stay there until the whole zone is reset. This might … 103 can be executed anymore. Therefore a mechanism is needed to move valid data and invalidate whole [all …]
H A D	libraries.md	3 The SPDK repository is, first and foremost, a collection of high-performance 7 (`lib` and `module`) inside of the SPDK repository in a deliberate way to prevent 25 libraries easier to implement. For example, `spdk_log` contains macro definitions that provide a 26 consistent logging paradigm and `spdk_json` is a general purpose JSON parsing library. 27 - Protocol Libraries: These libraries contain the building blocks for a specific service. For examp… 29 - Storage Service Libraries: These libraries provide a specific abstraction that can be mapped to s… 31 …provides a general block device abstraction layer, `spdk_lvol` provides a logical volume abstracti… 32 `spdk_blobfs` provides a filesystem abstraction, and `spdk_ftl` provides a flash translation layer 34 - System Libraries: These libraries provide system level services such as a JSON based RPC service 36 …is the `spdk_env_dpdk` library which provides a shim for the underlying Data Plane Development Kit… [all …]
H A D	usdt.md	11 bpftrace.sh is a helper script that facilitates running bpftrace scripts 12 against a running SPDK application. Here is a typical usage: 20 marker instead of a full path name, and bpftrace.sh will dynamically 25 written with a __PID__ marker, and bpftrace.sh will dynamically replace 56 nvmf_create_subsystem nqn.2016-06.io.spdk:cnode1 -a -s SPDK00000000000001 -m 10 57 nvmf_subsystem_add_listener nqn.2016-06.io.spdk:cnode1 -t tcp -a 127.0.0.1 -s 4420 63 This creates the nvmf tcp transport, a new nvmf subsystem that listens on a tcp 64 port, and a null bdev which is added as a namespace to the new nvmf subsystem. 113 it again with the send_msg.bt script. This script keeps a count of 121 From the third terminal, create another null bdev and add it as a [all …]
/spdk/test/unit/lib/bdev/gpt/gpt.c/
H A D	gpt_ut.c	17 unsigned char a[SPDK_GPT_BUFFER_SIZE]; in test_check_mbr() local 31 memset(a, 'a', sizeof(a)); in test_check_mbr() 32 gpt->buf = &a[0]; in test_check_mbr() 65 unsigned char a[SPDK_GPT_BUFFER_SIZE]; in test_read_header() local 75 memset(a, 'a', sizeof(a)); in test_read_header() 76 gpt->buf = &a[0]; in test_read_header() 77 gpt->buf_size = sizeof(a); in test_read_header() 133 unsigned char a[SPDK_GPT_BUFFER_SIZE]; in test_read_partitions() local 143 memset(a, 'a', sizeof(a)); in test_read_partitions() 144 gpt->buf = &a[0]; in test_read_partitions() [all …]
/spdk/
H A D	README.md	8 NOTE: The SPDK mailing list has moved to a new location. Please visit 13 The Storage Performance Development Kit ([SPDK](http://www.spdk.io)) provides a set of tools 16 drivers into userspace and operating in a polled mode instead of relying on 44 <a id="documentation"></a> 48 well as a [Porting Guide](http://www.spdk.io/doc/porting.html) for porting SPDK to different framew… 51 <a id="source"></a> 60 <a id="prerequisites"></a> 72 <a id="libraries"></a> 92 <a id="tests"></a> 103 <a id="vagrant"></a> [all …]
/spdk/test/app/fuzz/nvme_fuzz/
H A D	README.md	3 This application is intended to fuzz test the NVMe-oF target or a physical NVMe drive by 5 drives are configured through a .ini style config file (See the -C option on the application). 6 Multiple controllers and namespaces can be exposed to the fuzzer at a time. In order to 7 handle multiple namespaces, the fuzzer will round robin assign a thread to each namespace and 8 submit commands to that thread at a set queue depth. (currently 128 for I/O, 16 for Admin). The 13 3. The user specified a json file containing operations to run and the fuzzer has received valid co… 20 2. Are outstanding at the time of a controller timeout. 23 script for targeted debugging on a subsequent run. See `Debugging` below. 24 By default no output is generated when a specific command is returned with a failed status. 27 At the end of each test run, a summary is printed for each namespace in the following format: [all …]
/spdk/test/common/config/pkgdep/patches/qat/
H A D	0001-missing-prototypes.patch
/spdk/proto/
H A D	sma.proto	58 // Parameters describing a volume 89 // Device handle that can uniquely identify a device within an instance of 126 // current limit value unchanged. If one of the limits isn't supported by a 147 // GUID/UUID of a volume to configure QoS on. If this parameter is omitted, 151 // (volume_id cannot be empty). This information can be obtained by sending a 163 // Type of a device to query for QoS capabilities 191 // Creates a new device. A device is an entity that can be used to expose 195 // Deletes a device. It is only allowed to delete a device with volumes still 201 // Attaches a volume to a specified device making it available through that 202 // device (e.g. for NVMeoF this results in adding a namespace to an NVMeoF [all …]
/spdk/test/app/fuzz/iscsi_fuzz/
H A D	README.md	`4 randomized PDU commands through a simulated iSCSI initiator. 8 1. iSCSI initiator send a login request PDU to iSCSI Target. Once a session is connected, 10 3. iSCSI initiator send a logout request PDU to iSCSI Target in the end. 21 2. Are outstanding at the time of a connection error occurs. 24 script for targeted debugging on a subsequent run. 26 At the end of each test run, a summary is printed in the following format:`
/spdk/.github/ISSUE_TEMPLATE/
H A D	bug_report.md	`3 about: Create a report to help us improve. Please use the issue tracker only for reporting suspecte… 12 <!--- Provide a general summary of the issue in the Title above --> 24 <!--- Not obligatory, but suggest a fix/reason for the potential issue, --> 28 <!--- Provide a link to a live example, or an unambiguous set of steps to --> 37 <!--- Providing context helps us come up with a solution that is most useful in the real world -->`

12 3 4 5 6