1 What: /sys/class/scsi_host/hostX/isc 1 What: /sys/class/scsi_host/hostX/isci_id
2 Date: June 2011 2 Date: June 2011
3 Contact: Dave Jiang <dave.jiang@intel.co 3 Contact: Dave Jiang <dave.jiang@intel.com>
4 Description: 4 Description:
5 This file contains the enumera 5 This file contains the enumerated host ID for the Intel
6 SCU controller. The Intel(R) C 6 SCU controller. The Intel(R) C600 Series Chipset SATA/SAS
7 Storage Control Unit embeds up 7 Storage Control Unit embeds up to two 4-port controllers in
8 a single PCI device. The cont 8 a single PCI device. The controllers are enumerated in order
9 which usually means the lowest 9 which usually means the lowest number scsi_host corresponds
10 with the first controller, but 10 with the first controller, but this association is not
11 guaranteed. The 'isci_id' att 11 guaranteed. The 'isci_id' attribute unambiguously identifies
12 the controller index: '0' for 12 the controller index: '0' for the first controller,
13 '1' for the second. 13 '1' for the second.
14 14
15 What: /sys/class/scsi_host/hostX/acc 15 What: /sys/class/scsi_host/hostX/acciopath_status
16 Date: November 2013 16 Date: November 2013
17 Contact: Stephen M. Cameron <scameron@be 17 Contact: Stephen M. Cameron <scameron@beardog.cce.hp.com>
18 Description: This file contains the current 18 Description: This file contains the current status of the "SSD Smart Path"
19 feature of HP Smart Array RAID 19 feature of HP Smart Array RAID controllers using the hpsa
20 driver. SSD Smart Path, when 20 driver. SSD Smart Path, when enabled permits the driver to
21 send i/o requests directly to 21 send i/o requests directly to physical devices that are part
22 of a logical drive, bypassing 22 of a logical drive, bypassing the controllers firmware RAID
23 stack for a performance advant 23 stack for a performance advantage when possible. A value of
24 '1' indicates the feature is e 24 '1' indicates the feature is enabled, and the controller may
25 use the direct i/o path to phy 25 use the direct i/o path to physical devices. A value of zero
26 means the feature is disabled 26 means the feature is disabled and the controller may not use
27 the direct i/o path to physica 27 the direct i/o path to physical devices. This setting is
28 controller wide, affecting all 28 controller wide, affecting all configured logical drives on the
29 controller. This file is read 29 controller. This file is readable and writable.
30 30
31 What: /sys/class/scsi_host/hostX/lin 31 What: /sys/class/scsi_host/hostX/link_power_management_policy
32 Date: Oct, 2007 32 Date: Oct, 2007
33 KernelVersion: v2.6.24 33 KernelVersion: v2.6.24
34 Contact: linux-ide@vger.kernel.org 34 Contact: linux-ide@vger.kernel.org
35 Description: 35 Description:
36 (RW) This parameter allows the 36 (RW) This parameter allows the user to read and set the link
37 (interface) power management. 37 (interface) power management.
38 38
39 There are four possible option 39 There are four possible options:
40 40
41 min_power: Tell the controller 41 min_power: Tell the controller to try to make the link use the
42 least possible power when poss 42 least possible power when possible. This may sacrifice some
43 performance due to increased l 43 performance due to increased latency when coming out of lower
44 power states. 44 power states.
45 45
46 max_performance: Generally, th 46 max_performance: Generally, this means no power management.
47 Tell the controller to have pe 47 Tell the controller to have performance be a priority over power
48 management. 48 management.
49 49
50 medium_power: Tell the control 50 medium_power: Tell the controller to enter a lower power state
51 when possible, but do not ente 51 when possible, but do not enter the lowest power state, thus
52 improving latency over min_pow 52 improving latency over min_power setting.
53 53
54 med_power_with_dipm: Identical 54 med_power_with_dipm: Identical to the existing medium_power
55 setting except that it enables 55 setting except that it enables dipm (device initiated power
56 management) on top, which make 56 management) on top, which makes it match the Windows IRST (Intel
57 Rapid Storage Technology) driv 57 Rapid Storage Technology) driver settings. This setting is also
58 close to min_power, except tha 58 close to min_power, except that:
59 59
60 a) It does not use host-initia 60 a) It does not use host-initiated slumber mode, but it does
61 allow device-initiated slum 61 allow device-initiated slumber
62 b) It does not enable low powe 62 b) It does not enable low power device sleep mode (DevSlp).
63 63
64 What: /sys/class/scsi_host/hostX/em_ 64 What: /sys/class/scsi_host/hostX/em_message
65 What: /sys/class/scsi_host/hostX/em_ 65 What: /sys/class/scsi_host/hostX/em_message_type
66 Date: Jun, 2008 66 Date: Jun, 2008
67 KernelVersion: v2.6.27 67 KernelVersion: v2.6.27
68 Contact: linux-ide@vger.kernel.org 68 Contact: linux-ide@vger.kernel.org
69 Description: 69 Description:
70 em_message: (RW) Enclosure man 70 em_message: (RW) Enclosure management support. For the LED
71 protocol, writes and reads cor 71 protocol, writes and reads correspond to the LED message format
72 as defined in the AHCI spec. 72 as defined in the AHCI spec.
73 73
74 The user must turn sw_activity 74 The user must turn sw_activity (under `/sys/block/*/device/`)
75 OFF it they wish to control th 75 OFF it they wish to control the activity LED via the em_message
76 file. 76 file.
77 77
78 em_message_type: (RO) Displays 78 em_message_type: (RO) Displays the current enclosure management
79 protocol that is being used by 79 protocol that is being used by the driver (for eg. LED, SAF-TE,
80 SES-2, SGPIO etc). 80 SES-2, SGPIO etc).
81 81
82 What: /sys/class/scsi_host/hostX/ahc 82 What: /sys/class/scsi_host/hostX/ahci_port_cmd
83 What: /sys/class/scsi_host/hostX/ahc 83 What: /sys/class/scsi_host/hostX/ahci_host_caps
84 What: /sys/class/scsi_host/hostX/ahc 84 What: /sys/class/scsi_host/hostX/ahci_host_cap2
85 Date: Mar, 2010 85 Date: Mar, 2010
86 KernelVersion: v2.6.35 86 KernelVersion: v2.6.35
87 Contact: linux-ide@vger.kernel.org 87 Contact: linux-ide@vger.kernel.org
88 Description: 88 Description:
89 [to be documented] 89 [to be documented]
90 90
91 What: /sys/class/scsi_host/hostX/ahc 91 What: /sys/class/scsi_host/hostX/ahci_host_version
92 Date: Mar, 2010 92 Date: Mar, 2010
93 KernelVersion: v2.6.35 93 KernelVersion: v2.6.35
94 Contact: linux-ide@vger.kernel.org 94 Contact: linux-ide@vger.kernel.org
95 Description: 95 Description:
96 (RO) Display the version of th 96 (RO) Display the version of the AHCI spec implemented by the
97 host. 97 host.
98 98
99 What: /sys/class/scsi_host/hostX/em_ 99 What: /sys/class/scsi_host/hostX/em_buffer
100 Date: Apr, 2010 100 Date: Apr, 2010
101 KernelVersion: v2.6.35 101 KernelVersion: v2.6.35
102 Contact: linux-ide@vger.kernel.org 102 Contact: linux-ide@vger.kernel.org
103 Description: 103 Description:
104 (RW) Allows access to AHCI EM 104 (RW) Allows access to AHCI EM (enclosure management) buffer
105 directly if the host supports 105 directly if the host supports EM.
106 106
107 For eg. the AHCI driver suppor 107 For eg. the AHCI driver supports SGPIO EM messages but the
108 SATA/AHCI specs do not define 108 SATA/AHCI specs do not define the SGPIO message format of the EM
109 buffer. Different hardware(HW) 109 buffer. Different hardware(HW) vendors may have different
110 definitions. With the em_buffe 110 definitions. With the em_buffer attribute, this issue can be
111 solved by allowing HW vendors 111 solved by allowing HW vendors to provide userland drivers and
112 tools for their SGPIO initiato 112 tools for their SGPIO initiators.
113 113
114 What: /sys/class/scsi_host/hostX/em_ 114 What: /sys/class/scsi_host/hostX/em_message_supported
115 Date: Oct, 2009 115 Date: Oct, 2009
116 KernelVersion: v2.6.39 116 KernelVersion: v2.6.39
117 Contact: linux-ide@vger.kernel.org 117 Contact: linux-ide@vger.kernel.org
118 Description: 118 Description:
119 (RO) Displays supported enclos 119 (RO) Displays supported enclosure management message types.
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.