1IPMCTL-INJECT-ERROR(1) ipmctl IPMCTL-INJECT-ERROR(1)
2
6 ipmctl-inject-error - Injects an error or clears a previously injected
7 error
8
10 ipmctl set [OPTIONS] -dimm [TARGETS] [PROPERTIES]
11
13 Injects an error or clears a previously injected error on one or more
14 PMem module for testing purposes.
15
17 -h, -help
18 Displays help for the command.
19 -ddrt
21 Used to specify DDRT as the desired transport protocol for the
22 current invocation of ipmctl.
23 -smbus
25 Used to specify SMBUS as the desired transport protocol for the
26 current invocation of ipmctl.
27 Note
29 The -ddrt and -smbus options are mutually exclusive and may not be
30 used together.
31 -o (text|nvmxml), -output (text|nvmxml)
33 Changes the output format. One of: "text" (default) or "nvmxml".
34
36 -dimm [DimmIDs]
37 Injects or clears an error on specific PMem modules by supplying
38 one or more comma separated PMem module identifiers. The default is
39 to inject the error on all manageable PMem modules.
40
42 This command only supports setting or clearing one type of error at a
43 time.
44 Clear
46 • "1": Clears a previously injected error. This property must be
48 combined with one of the other properties indicating the
49 previously injected error to clear.
50 Temperature
52 Injects an artificial media temperature in degrees Celsius into the
53 PMem module. The firmware that is monitoring the temperature of the
54 PMem module will then be alerted and take necessary precautions to
55 preserve the PMem module. The value is injected immediately and
56 will override the firmware from reading the actual media
57 temperature of the device and use this value instead which may
58 cause adverse reactions by the firmware and result in an alert or
59 log.
60 Note
62 The injected temperature value will remain until the next reboot or
63 until it is cleared. The media temperature is an artificial
64 temperature and will not cause harm to the part. Although firmware
65 actions due to improper temperature injections may cause adverse
66 effects on the PMem module.
67 If the Critical Shutdown Temperature, or higher, is passed in, this
68 may cause the PMem module firmware to perform a shutdown in order
69 to preserve the part and data.
70 The temperature value will be ignored on clear.
71 Poison
73 The physical address to poison.
74 Poison is not possible for any address in the PM region if the PM
75 region is locked. Injected poison errors are only triggered on a
76 subsequent read of the poisoned address in which case an error log
77 will be generated by the firmware, but no alerts will be sent.
78 This command can be used to clear non-injected poison errors. The
79 data will be zeroed after clearing. There is no requirement to
80 enable error injection prior to request to clear poison errors.
81 The caller is responsible for keeping a list of injected poison
82 errors, in order to properly clear the injected errors afterwards.
83 Simply disabling injection does not clear injected poison errors.
84 Injected poison errors are persistent across power cycles and
85 system resets.
86 Note
88 System firmware (BIOS) will not read from any Intel® Optane™ PMem
89 device addresses that are known to be poisoned. For any poisoned
90 address, the first read may result in a hang/fault, but system
91 firmware (BIOS) will mark this address as poisoned so subsequent
92 attempts to read poisoned addresses will be rejected with an error.
93 The result of such an error may prevent booting from a namespace
94 that has poisoned data.
95 Note
97 The address must be 256 byte aligned (e.g., 0x10000000, 0x10000100,
98 0x10000200...).
99 PoisonType
101 The type of memory to poison. One of:
102 • "PatrolScrub": Injects a poison error at the specified address
104 simulating an error found during a patrol scrub operation
105 indifferent to how the memory is currently allocated. This is
106 the default.
107 • "MemoryMode": Injects a poison error at the specified address
109 currently allocated in Memory Mode.
110 • "AppDirect": Injects a poison error at the specified address
112 currently allocated as App Direct.
113 Note
115 If the address to poison is not currently allocated as the
116 specified memory type, an error is returned.
117 PackageSparing
119 • "1": Triggers an artificial package sparing. If package sparing
121 is enabled and the PMem module still has spares remaining, this
122 will cause the firmware to report that there are no spares
123 remaining.
124 PercentageRemaining
126 Injects an artificial percentage remaining value into the PMem
127 module. This will cause the firmware to take appropriate action
128 based on the value and if necessary generate an error log, an
129 alert, and update the health status.
130 FatalMediaError
132 • "1": Injects a fake media fatal error which will cause the
134 firmware to generate an error log and an alert.
135 Note
137 When media fatal error is injected, BSR Media Disabled status bit
138 will be set indicating media error, until the fatal error is
139 cleared using disable trigger input parameter to clear this
140 injected fatal error.
141 Note
143 Injecting a Fatal Media error is unsupported on Windows. Contact
144 Microsoft for assistance in performing this action.
145 DirtyShutdown
147 • "1": Injects an ADR failure resulting in dirty shutdown upon
149 reboot.
150
152 Sets the media temperature on all manageable PMem modules to 50 degrees
153 Celsius.
154 ipmctl set -dimm Temperature=50
156 Clears the injected media temperature on all manageable PMem modules.
158 ipmctl set -dimm Clear=1 Temperature=1
160 Poison address 0x10000200 on PMem module 1234.
162 ipmctl set -dimm 1234 Poison=0x10000200
164 Clears the injected poison of address 0x10000200 on PMem module 1234.
166 ipmctl set -dimm 1234 Poison=0x10000200 Clear=1
168 Triggers an artificial package sparing on all manageable PMem modules.
170 ipmctl set -dimm PackageSparing=1
172 Sets the life remaining percentage on all manageable PMem modules to
174 10%.
175 ipmctl set -dimm PercentageRemaining=10
177 Clears the injected remaining life percentage on all manageable PMem
179 modules. The value of PercentageRemaining is irrelevant.
180 ipmctl set -dimm PercentageRemaining=10 Clear=1
182 Triggers an artificial ADR failure on all manageable PMem modules
184 resulting in a dirty shutdown on each PMem module on the next reboot.
185 ipmctl set -dimm DirtyShutdown=1
187
189 This command is available only when error injection is enabled on the
190 PMem modules in the BIOS. To successfully execute this command, the
191 specified PMem modules must be manageable by the host software.
192
194 For each PMem module, the CLI will indicate the status of the
195 operation. If a failure occurs when injecting an error on multiple PMem
196 modules, the process will continue with the remaining PMem modules.
197
199 Set temperature on PMem module (DimmID): Success|Error (Code) -
200 (Description)
201 Clear injected temperature on PMem module (DimmID): Success|Error
202 (Code) - (Description)
203 Poison address (Address) on PMem module (DimmID): Success|Error
205 (Code) - (Description)
206 Clear injected poison of address (Address) on PMem module
207 (DimmID): Success|Error (Code) - (Description)
208 Trigger package sparing on PMem module (DimmID): Success|Error
210 (Code) - (Description)
211 Clear injected package sparing on PMem module (DimmID):
212 Success|Error (Code) - (Description)
213 Trigger a spare capacity alarm on PMem module (DimmID):
215 Success|Error (Code) - (Description)
216 Clear injected spare capacity alarm on PMem module (DimmID):
217 Success|Error (Code) - (Description)
218 Create a media fatal error on PMem module (DimmID): Success|Error
220 (Code) - (Description)
221 Clear injected media fatal error on PMem module (DimmID):
222 Success|Error (Code) - (Description)
223ipmctl 2022-02-01 IPMCTL-INJECT-ERROR(1)