1HDPARM(8) System Manager's Manual HDPARM(8)
2
6 hdparm - get/set SATA/IDE device parameters
7
9 hdparm [options] [device ...]
10
12 hdparm provides a command line interface to various kernel interfaces
13 supported by the Linux SATA/PATA/SAS "libata" subsystem and the older
14 IDE driver subsystem. Many newer (2008 and later) USB drive enclosures
15 now also support "SAT" (SCSI-ATA Command Translation) and therefore may
16 also work with hdparm. E.g. recent WD "Passport" models and recent
17 NexStar-3 enclosures. Some options may work correctly only with the
18 latest kernels.
19
21 When no options are given, -acdgkmur is assumed. For "Get/set"
22 options, a query without the optional parameter (e.g. -d) will query
23 (get) the device state, and with a parameter (e.g., -d0) will set the
24 device state.
25 -a Get/set sector count for filesystem (software) read-ahead. This
27 is used to improve performance in sequential reads of large
28 files, by prefetching additional blocks in anticipation of them
29 being needed by the running task. Many IDE drives also have a
30 separate built-in read-ahead function, which augments this
31 filesystem (software) read-ahead function.
32 -A Get/set the IDE drive´s read-lookahead feature (usually ON by
34 default). Usage: -A0 (disable) or -A1 (enable).
35 -b Get/set bus state.
37 -B Get/set Advanced Power Management feature, if the drive supports
39 it. A low value means aggressive power management and a high
40 value means better performance. Possible settings range from
41 values 1 through 127 (which permit spin-down), and values 128
42 through 254 (which do not permit spin-down). The highest degree
43 of power management is attained with a setting of 1, and the
44 highest I/O performance with a setting of 254. A value of 255
45 tells hdparm to disable Advanced Power Management altogether on
46 the drive (not all drives support disabling it, but most do).
47 -c Get/set (E)IDE 32-bit I/O support. A numeric parameter can be
49 used to enable/disable 32-bit I/O support. Currently supported
50 values include 0 to disable 32-bit I/O support, 1 to enable
51 32-bit data transfers, and 3 to enable 32-bit data transfers
52 with a special sync sequence required by many chipsets. The
53 value 3 works with nearly all 32-bit IDE chipsets, but incurs
54 slightly more overhead. Note that "32-bit" refers to data
55 transfers across a PCI or VLB bus to the interface card only;
56 all (E)IDE drives still have only a 16-bit connection over the
57 ribbon cable from the interface card.
58 -C Check the current IDE power mode status, which will always be
60 one of unknown (drive does not support this command),
61 active/idle (normal operation), standby (low power mode, drive
62 has spun down), or sleeping (lowest power mode, drive is com‐
63 pletely shut down). The -S, -y, -Y, and -Z options can be used
64 to manipulate the IDE power modes.
65 -d Get/set the "using_dma" flag for this drive. This option now
67 works with most combinations of drives and PCI interfaces which
68 support DMA and which are known to the kernel IDE driver. It is
69 also a good idea to use the appropriate -X option in combination
70 with -d1 to ensure that the drive itself is programmed for the
71 correct DMA mode, although most BIOSs should do this for you at
72 boot time. Using DMA nearly always gives the best performance,
73 with fast I/O throughput and low CPU usage. But there are at
74 least a few configurations of chipsets and drives for which DMA
75 does not make much of a difference, or may even slow things down
76 (on really messed up hardware!). Your mileage may vary.
77 --dco-freeze
79 DCO stands for Device Configuration Overlay, a way for vendors
80 to selectively disable certain features of a drive. The --dco-
81 freeze option will freeze/lock the current drive configuration,
82 thereby preventing software (or malware) from changing any DCO
83 settings until after the next power-on reset.
84 --dco-identify
86 Query and dump information regarding drive configuration set‐
87 tings which can be disabled by the vendor or OEM installer.
88 These settings show capabilities of the drive which might be
89 disabled by the vendor for "enhanced compatibility". When dis‐
90 abled, they are otherwise hidden and will not show in the -I
91 identify output. For example, system vendors sometimes disable
92 48_bit addressing on large drives, for compatibility (and loss
93 of capacity) with a specific BIOS. In such cases, --dco-iden‐
94 tify will show that the drive is 48_bit capable, but -I will not
95 show it, and nor will the drive accept 48_bit commands.
96 --dco-restore
98 Reset all drive settings, features, and accessible capacities
99 back to factory defaults and full capabilities. This command
100 will fail if DCO is frozen/locked, or if a -Np maximum size
101 restriction has also been set. This is EXTREMELY DANGEROUS and
102 will very likely cause massive loss of data. DO NOT USE THIS
103 COMMAND.
104 --direct
106 Use the kernel´s "O_DIRECT" flag when performing a -t timing
107 test. This bypasses the page cache, causing the reads to go
108 directly from the drive into hdparm's buffers, using so-called
109 "raw" I/O. In many cases, this can produce results that appear
110 much faster than the usual page cache method, giving a better
111 indication of raw device and driver performance.
112 --drq-hsm-error
114 VERY DANGEROUS, DON'T EVEN THINK ABOUT USING IT. This option
115 causes hdparm to issue an IDENTIFY command to the kernel, but
116 incorrectly marked as a "non-data" command. This results in the
117 drive being left with its DataReQust(DRQ) line "stuck" high.
118 This confuses the kernel drivers, and may crash the system imme‐
119 diately with massive data loss. The option exists to help in
120 testing and fortifying the kernel against similar real-world
121 drive malfunctions. VERY DANGEROUS, DO NOT USE!!
122 -D Enable/disable the on-drive defect management feature, whereby
124 the drive firmware tries to automatically manage defective sec‐
125 tors by relocating them to "spare" sectors reserved by the fac‐
126 tory for such. Control of this feature via the -D option is not
127 supported for most modern drives since ATA-4; thus this command
128 may fail.
129 -E Set cd/dvd drive speed. This is NOT necessary for regular oper‐
131 ation, as the drive will automatically switch speeds on its own.
132 But if you want to play with it, just supply a speed number
133 after the option, usually a number like 2 or 4. This can be
134 useful in some cases, though, to smooth out DVD video playback.
135 -f Sync and flush the buffer cache for the device on exit. This
137 operation is also performed internally as part of the -t and -T
138 timings and other options.
139 --fallocate
141 This option currently works only on ext4 and xfs filesystem
142 types. When used, this must be the only option given. It
143 requires two parameters: the desired file size in kilo-bytes
144 (byte count divided by 1024), followed by the pathname for the
145 new file. It will create a new file of the specified size, but
146 without actually having to write any data to the file. This
147 will normally complete very quickly, and without thrashing the
148 storage device.
149 E.g. Create a 10KByte file: hdparm --fallocate 10 temp_file
151 --fibmap
153 When used, this must be the only option given. It requires a
154 file path as a parameter, and will print out a list of the block
155 extents (sector ranges) occupied by that file on disk. Sector
156 numbers are given as absolute LBA numbers, referenced from sec‐
157 tor 0 of the physical device rather than from the partition or
158 filesystem. This information can then be used for a variety of
159 purposes, such as examining the degree of fragmenation of larger
160 files, or determining appropriate sectors to deliberately cor‐
161 rupt during fault-injection testing procedures.
162 This option uses the new FIEMAP (file extent map) ioctl() when
164 available, and falls back to the older FIBMAP (file block map)
165 ioctl() otherwise. Note that FIBMAP suffers from a 32-bit
166 block-number interface, and thus not work beyond 8TB or 16TB.
167 FIBMAP is also very slow, and does not deal well with preallo‐
168 cated uncommitted extents in ext4/xfs filesystems, unless a
169 sync() is done before using this option.
170 --fibmap-sector
172 When used, this must be the only flag given. It requires a file
173 path followed by a sector number as parameters. This sector
174 number is given relative to the start of the file itself, not
175 the device. hdparm will scan the device extents occupied by the
176 file, and print out the absolute LBA number of the requested
177 sector of the file. This LBA number is referenced from sector 0
178 of the physical device (not the partition or filesystem). This
179 LBA value can then be used for a variety of purposes, including
180 determining an appropriate sector to deliberately corrupt during
181 fault-injection testing procedures.
182 --fwdownload
184 When used, this should be the only option given. It requires a
185 file path immediately after the option, indicating where the new
186 drive firmware should be read from. The contents of this file
187 will be sent to the drive using the (S)ATA DOWNLOAD MICROCODE
188 command, using either transfer protocol 7 (entire file at once),
189 or, if the drive supports it, transfer protocol 3 (segmented
190 download). This command is EXTREMELY DANGEROUS and could
191 destroy both the drive and all data on it. DO NOT USE THIS COM‐
192 MAND. The --fwdownload-mode3 , --fwdownload-mode3-max , and
193 --fwdownload-mode7 variations on basic --fwdownload allow over‐
194 riding automatic protocol detection in favour of forcing hdparm
195 to use a specific transfer protocol, for testing purposes only.
196 -F Flush the on-drive write cache buffer (older drives may not
198 implement this).
199 -g Display the drive geometry (cylinders, heads, sectors), the size
201 (in sectors) of the device, and the starting offset (in sectors)
202 of the device from the beginning of the drive.
203 -h Display terse usage information (help).
205 -H Read the temperature from some (mostly Hitachi) drives. Also
207 reports if the temperature is within operating condition range
208 (this may not be reliable). Does not cause the drive to spin up
209 if idle.
210 -i Display the identification info which the kernel drivers (IDE,
212 libata) have stored from boot/configuration time. This may dif‐
213 fer from the current information obtainable directly from the
214 drive itself with the -I option. The data returned may or may
215 not be current, depending on activity since booting the system.
216 For a more detailed interpretation of the identification info,
217 refer to AT Attachment Interface for Disk Drives, ANSI ASC
218 X3T9.2 working draft, revision 4a, April 19/93, and later edi‐
219 tions.
220 --idle-immediate
222 Issue an ATA IDLE_IMMEDIATE command, to put the drive into a
223 lower power state. Usually the device remains spun-up.
224 --idle-unload
226 Issue an ATA IDLE_IMMEDIATE_WITH_UNLOAD command, to unload or
227 park the heads and put the drive into a lower power state. Usu‐
228 ally the device remains spun-up.
229 -I Request identification info directly from the drive, which is
231 displayed in a new expanded format with considerably more detail
232 than with the older -i option.
233 --Istdin
235 This is a special variation on the -I option, which accepts a
236 drive identification block as standard input instead of using a
237 /dev/hd* parameter. The format of this block must be exactly
238 the same as that found in the /proc/ide/*/hd*/identify "files",
239 or that produced by the --Istdout option described below. This
240 variation is designed for use with collected "libraries" of
241 drive identification information, and can also be used on ATAPI
242 drives which may give media errors with the standard mechanism.
243 When --Istdin is used, it must be the *only* parameter given.
244 --Istdout
246 This option dumps the drive's identify data in hex to stdout, in
247 a format similar to that from /proc/ide/*/identify, and suitable
248 for later use with the --Istdin option.
249 -J Get/set the Western Digital (WD) Green Drive's "idle3" timeout
251 value. This timeout controls how often the drive parks its
252 heads and enters a low power consumption state. The factory
253 default is eight (8) seconds, which is a very poor choice for
254 use with Linux. Leaving it at the default will result in hun‐
255 dreds of thousands of head load/unload cycles in a very short
256 period of time. The drive mechanism is only rated for 300,000
257 to 1,000,000 cycles, so leaving it at the default could result
258 in premature failure, not to mention the performance impact of
259 the drive often having to wake-up before doing routine I/O.
260 WD supply a WDIDLE3.EXE DOS utility for tweaking this setting,
262 and you should use that program instead of hdparm if at all pos‐
263 sible. The reverse-engineered implementation in hdparm is not
264 as complete as the original official program, even though it
265 does seem to work on at a least a few drives. A full power
266 cycle is required for any change in setting to take effect,
267 regardless of which program is used to tweak things.
268 A setting of 30 seconds is recommended for Linux use. Permitted
270 values are from 8 to 12 seconds, and from 30 to 300 seconds in
271 30-second increments. Specify a value of zero (0) to disable
272 the WD idle3 timer completely (NOT RECOMMENDED!).
273 -k Get/set the "keep_settings_over_reset" flag for the drive. When
275 this flag is set, the drive will preserve the -dmu settings over
276 a soft reset, (as done during the error recovery sequence).
277 This option defaults to off, to prevent drive reset loops which
278 could be caused by combinations of -dmu settings. The -k option
279 should therefore only be set after one has achieved confidence
280 in correct system operation with a chosen set of configuration
281 settings. In practice, all that is typically necessary to test
282 a configuration (prior to using -k) is to verify that the drive
283 can be read/written, and that no error logs (kernel messages)
284 are generated in the process (look in /var/log/messages on most
285 systems).
286 -K Set the drive´s "keep_features_over_reset" flag. Setting this
288 enables the drive to retain the settings for -APSWXZ over a soft
289 reset (as done during the error recovery sequence). Not all
290 drives support this feature.
291 -L Set the drive´s doorlock flag. Setting this to 1 will lock the
293 door mechanism of some removable hard drives (e.g. Syquest, ZIP,
294 Jazz..), and setting it to 0 will unlock the door mechanism.
295 Normally, Linux maintains the door locking mechanism automati‐
296 cally, depending on drive usage (locked whenever a filesystem is
297 mounted). But on system shutdown, this can be a nuisance if the
298 root partition is on a removable disk, since the root partition
299 is left mounted (read-only) after shutdown. So, by using this
300 command to unlock the door after the root filesystem is
301 remounted read-only, one can then remove the cartridge from the
302 drive after shutdown.
303 -m Get/set sector count for multiple sector I/O on the drive. A
305 setting of 0 disables this feature. Multiple sector mode (aka
306 IDE Block Mode), is a feature of most modern IDE hard drives,
307 permitting the transfer of multiple sectors per I/O interrupt,
308 rather than the usual one sector per interrupt. When this fea‐
309 ture is enabled, it typically reduces operating system overhead
310 for disk I/O by 30-50%. On many systems, it also provides
311 increased data throughput of anywhere from 5% to 50%. Some
312 drives, however (most notably the WD Caviar series), seem to run
313 slower with multiple mode enabled. Your mileage may vary. Most
314 drives support the minimum settings of 2, 4, 8, or 16 (sectors).
315 Larger settings may also be possible, depending on the drive. A
316 setting of 16 or 32 seems optimal on many systems. Western Dig‐
317 ital recommends lower settings of 4 to 8 on many of their
318 drives, due tiny (32kB) drive buffers and non-optimized buffer‐
319 ing algorithms. The -i option can be used to find the maximum
320 setting supported by an installed drive (look for MaxMultSect in
321 the output). Some drives claim to support multiple mode, but
322 lose data at some settings. Under rare circumstances, such
323 failures can result in massive filesystem corruption.
324 --make-bad-sector
326 Deliberately create a bad sector (aka. "media error") on the
327 disk. EXCEPTIONALLY DANGEROUS. DO NOT USE THIS OPTION!! This
328 can be useful for testing of device/RAID error recovery mecha‐
329 nisms. The sector number is given as a (base10) parameter after
330 the option. Depending on the device, hdparm will choose one of
331 two possible ATA commands for corrupting the sector. The
332 WRITE_LONG works on most drives, but only up to the 28-bit sec‐
333 tor boundary. Some very recent drives (2008) may support the
334 new WRITE_UNCORRECTABLE_EXT command, which works for any LBA48
335 sector. If available, hdparm will use that in preference to
336 WRITE_LONG. The WRITE_UNCORRECTABLE_EXT command itself presents
337 a choice of how the new bad sector should behave. By default,
338 it will look like any other bad sector, and the drive may take
339 some time to retry and fail on subsequent READs of the sector.
340 However, if a single letter f is prepended immediately in front
341 of the first digit of the sector number parameter, then hdparm
342 will issue a "flagged" WRITE_UNCORRECTABLE_EXT, which causes the
343 drive to merely flag the sector as bad (rather than genuinely
344 corrupt it), and subsequent READs of the sector will fail imme‐
345 diately (rather than after several retries). Note also that the
346 --repair-sector option can be used to restore (any) bad sectors
347 when they are no longer needed, including sectors that were gen‐
348 uinely bad (the drive will likely remap those to a fresh area on
349 the media).
350 -M Get/set Automatic Acoustic Management (AAM) setting. Most modern
352 harddisk drives have the ability to speed down the head move‐
353 ments to reduce their noise output. The possible values are
354 between 0 and 254. 128 is the most quiet (and therefore slowest)
355 setting and 254 the fastest (and loudest). Some drives have only
356 two levels (quiet / fast), while others may have different lev‐
357 els between 128 and 254. At the moment, most drives only sup‐
358 port 3 options, off, quiet, and fast. These have been assigned
359 the values 0, 128, and 254 at present, respectively, but integer
360 space has been incorporated for future expansion, should this
361 change.
362 -n Get or set the "ignore_write_errors" flag in the driver. Do NOT
364 play with this without grokking the driver source code first.
365 -N Get/set max visible number of sectors, also known as the Host
367 Protected Area setting. Without a parameter, -N displays the
368 current setting, which is reported as two values: the first
369 gives the current max sectors setting, and the second shows the
370 native (real) hardware limit for the disk. The difference
371 between these two values indicates how many sectors of the disk
372 are currently hidden from the operating system, in the form of a
373 Host Protected Area (HPA). This area is often used by computer
374 makers to hold diagnostic software, and/or a copy of the origi‐
375 nally provided operating system for recovery purposes. Another
376 possible use is to hide the true capacity of a very large disk
377 from a BIOS/system that cannot normally cope with drives of that
378 size (eg. most current {2010} BIOSs cannot deal with drives
379 larger than 2TB, so an HPA could be used to cause a 3TB drive to
380 report itself as a 2TB drive). To change the current max (VERY
381 DANGEROUS, DATA LOSS IS EXTREMELY LIKELY), a new value should be
382 provided (in base10) immediately following the -N option. This
383 value is specified as a count of sectors, rather than the "max
384 sector address" of the drive. Drives have the concept of a tem‐
385 porary (volatile) setting which is lost on the next hardware
386 reset, as well as a more permanent (non-volatile) value which
387 survives resets and power cycles. By default, -N affects only
388 the temporary (volatile) setting. To change the permanent (non-
389 volatile) value, prepend a leading p character immediately
390 before the first digit of the value. Drives are supposed to
391 allow only a single permanent change per session. A hardware
392 reset (or power cycle) is required before another permanent -N
393 operation can succeed. Note that any attempt to set this value
394 may fail if the disk is being accessed by other software at the
395 same time. This is because setting the value requires a pair of
396 back-to-back drive commands, but there is no way to prevent some
397 other command from being inserted between them by the kernel.
398 So if it fails initially, just try again. Kernel support for -N
399 is buggy for many adapter types across many kernel versions, in
400 that an incorrect (too small) max size value is sometimes
401 reported. As of the 2.6.27 kernel, this does finally seem to be
402 working on most hardware.
403 --offset
405 Offsets to given number of GiB (1024*1024*1024) when performing
406 -t timings of device reads. Speed changes (about twice) along
407 many mechanical drives. Usually the maximum is at the begin‐
408 ning, but not always. Solid-state drives (SSDs) should show
409 similar timings regardless of offset.
410 -p Attempt to reprogram the IDE interface chipset for the specified
412 PIO mode, or attempt to auto-tune for the "best" PIO mode sup‐
413 ported by the drive. This feature is supported in the kernel
414 for only a few "known" chipsets, and even then the support is
415 iffy at best. Some IDE chipsets are unable to alter the PIO
416 mode for a single drive, in which case this option may cause the
417 PIO mode for both drives to be set. Many IDE chipsets support
418 either fewer or more than the standard six (0 to 5) PIO modes,
419 so the exact speed setting that is actually implemented will
420 vary by chipset/driver sophistication. Use with extreme cau‐
421 tion! This feature includes zero protection for the unwary, and
422 an unsuccessful outcome may result in severe filesystem corrup‐
423 tion!
424 -P Set the maximum sector count for the drive´s internal prefetch
426 mechanism. Not all drives support this feature, and it was
427 dropped from the offical spec as of ATA-4.
428 --prefer-ata12
430 When using the SAT (SCSI ATA Translation) protocol, hdparm nor‐
431 mally prefers to use the 16-byte command format whenever possi‐
432 ble. But some USB drive enclosures don't work correctly with
433 16-byte commands. This option can be used to force use of the
434 smaller 12-byte command format with such drives. hdparm will
435 still revert to 16-byte commands for things that cannot be done
436 with the 12-byte format (e.g. sector accesses beyond 28-bits).
437 -q Handle the next option quietly, suppressing normal output (but
439 not error messages). This is useful for reducing screen clutter
440 when running from system startup scripts. Not applicable to the
441 -i or -v or -t or -T options.
442 -Q Get or set the device's command queue_depth, if supported by the
444 hardware. This only works with 2.6.xx (or later) kernels, and
445 only with device and driver combinations which support changing
446 the queue_depth. For SATA disks, this is the Native Command
447 Queuing (NCQ) queue depth.
448 -r Get/set read-only flag for the device. When set, Linux disal‐
450 lows write operations on the device.
451 -R Get/set Write-Read-Verify feature, if the drive supports it.
453 Usage: -R0 (disable) or -R1 (enable). This feature is intended
454 to have the drive firmware automatically read-back any data that
455 is written by software, to verify that the data was successfully
456 written. This is generally overkill, and can slow down disk
457 writes by as much as a factor of two (or more).
458 --read-sector
460 Reads from the specified sector number, and dumps the contents
461 in hex to standard output. The sector number must be given
462 (base10) after this option. hdparm will issue a low-level read
463 (completely bypassing the usual block layer read/write mecha‐
464 nisms) for the specified sector. This can be used to defini‐
465 tively check whether a given sector is bad (media error) or not
466 (doing so through the usual mechanisms can sometimes give false
467 positives).
468 --repair-sector
470 This is an alias for the --write-sector option. VERY DANGEROUS.
471 -s Enable/disable the power-on in standby feature, if supported by
473 the drive. VERY DANGEROUS. Do not use unless you are abso‐
474 lutely certain that both the system BIOS (or firmware) and the
475 operating system kernel (Linux >= 2.6.22) support probing for
476 drives that use this feature. When enabled, the drive is pow‐
477 ered-up in the standby mode to allow the controller to sequence
478 the spin-up of devices, reducing the instantaneous current draw
479 burden when many drives share a power supply. Primarily for use
480 in large RAID setups. This feature is usually disabled and the
481 drive is powered-up in the active mode (see -C above). Note
482 that a drive may also allow enabling this feature by a jumper.
483 Some SATA drives support the control of this feature by pin 11
484 of the SATA power connector. In these cases, this command may be
485 unsupported or may have no effect.
486 -S Put the drive into idle (low-power) mode, and also set the
488 standby (spindown) timeout for the drive. This timeout value is
489 used by the drive to determine how long to wait (with no disk
490 activity) before turning off the spindle motor to save power.
491 Under such circumstances, the drive may take as long as 30 sec‐
492 onds to respond to a subsequent disk access, though most drives
493 are much quicker. The encoding of the timeout value is somewhat
494 peculiar. A value of zero means "timeouts are disabled": the
495 device will not automatically enter standby mode. Values from 1
496 to 240 specify multiples of 5 seconds, yielding timeouts from 5
497 seconds to 20 minutes. Values from 241 to 251 specify from 1 to
498 11 units of 30 minutes, yielding timeouts from 30 minutes to 5.5
499 hours. A value of 252 signifies a timeout of 21 minutes. A
500 value of 253 sets a vendor-defined timeout period between 8 and
501 12 hours, and the value 254 is reserved. 255 is interpreted as
502 21 minutes plus 15 seconds. Note that some older drives may
503 have very different interpretations of these values.
504 -t Perform timings of device reads for benchmark and comparison
506 purposes. For meaningful results, this operation should be
507 repeated 2-3 times on an otherwise inactive system (no other
508 active processes) with at least a couple of megabytes of free
509 memory. This displays the speed of reading through the buffer
510 cache to the disk without any prior caching of data. This mea‐
511 surement is an indication of how fast the drive can sustain
512 sequential data reads under Linux, without any filesystem over‐
513 head. To ensure accurate measurements, the buffer cache is
514 flushed during the processing of -t using the BLKFLSBUF ioctl.
515 -T Perform timings of cache reads for benchmark and comparison pur‐
517 poses. For meaningful results, this operation should be
518 repeated 2-3 times on an otherwise inactive system (no other
519 active processes) with at least a couple of megabytes of free
520 memory. This displays the speed of reading directly from the
521 Linux buffer cache without disk access. This measurement is
522 essentially an indication of the throughput of the processor,
523 cache, and memory of the system under test.
524 --trim-sector-ranges
526 For Solid State Drives (SSDs). EXCEPTIONALLY DANGEROUS. DO NOT
527 USE THIS OPTION!! Tells the drive firmware to discard unneeded
528 data sectors, destroying any data that may have been present
529 within them. This makes those sectors available for immediate
530 use by the firmware's garbage collection mechanism, to improve
531 scheduling for wear-leveling of the flash media. This option
532 expects one or more sector range pairs immediately after the
533 option: an LBA starting address, a colon, and a sector count
534 (max 65535), with no intervening spaces. EXCEPTIONALLY DANGER‐
535 OUS. DO NOT USE THIS OPTION!!
536 E.g. hdparm --trim-sector-ranges 1000:4 7894:16 /dev/sdz
538 --trim-sector-ranges-stdin
540 Identical to --trim-sector-ranges above, except the list of
541 lba:count pairs is read from stdin rather than being specified
542 on the command line. This can be used to avoid problems with
543 excessively long command lines. It also permits batching of
544 many more sector ranges into single commands to the drive, up to
545 the currently configured transfer limit (max_sectors_kb).
546 --trim-sectors
548 For Solid State Drives (SSDs). EXCEPTIONALLY DANGEROUS. DO NOT
549 USE THIS FLAG!! Tells the drive firmware to discard unneeded
550 data sectors, destroying any data that may have been present
551 within them. This makes those sectors available for immediate
552 use by the firmware's garbage collection mechanism, to improve
553 scheduling for wear-leveling of the flash media. This option
554 expects two parameters immediately after the flag: an LBA start‐
555 ing address, and a sector count. EXCEPTIONALLY DANGEROUS. DO
556 NOT USE THIS FLAG!!
557 -u Get/set the interrupt-unmask flag for the drive. A setting of 1
559 permits the driver to unmask other interrupts during processing
560 of a disk interrupt, which greatly improves Linux´s responsive‐
561 ness and eliminates "serial port overrun" errors. Use this fea‐
562 ture with caution: some drive/controller combinations do not
563 tolerate the increased I/O latencies possible when this feature
564 is enabled, resulting in massive filesystem corruption. In par‐
565 ticular, CMD-640B and RZ1000 (E)IDE interfaces can be unreliable
566 (due to a hardware flaw) when this option is used with kernel
567 versions earlier than 2.0.13. Disabling the IDE prefetch fea‐
568 ture of these interfaces (usually a BIOS/CMOS setting) provides
569 a safe fix for the problem for use with earlier kernels.
570 -v Display some basic settings, similar to -acdgkmur for IDE. This
572 is also the default behaviour when no options are specified.
573 -V Display program version and exit immediately.
575 --verbose
577 Display extra diagnostics from some commands.
578 -w Perform a device reset (DANGEROUS). Do NOT use this option. It
580 exists for unlikely situations where a reboot might otherwise be
581 required to get a confused drive back into a useable state.
582 --write-sector
584 Writes zeros to the specified sector number. VERY DANGEROUS.
585 The sector number must be given (base10) after this option.
586 hdparm will issue a low-level write (completely bypassing the
587 usual block layer read/write mechanisms) to the specified sec‐
588 tor. This can be used to force a drive to repair a bad sector
589 (media error).
590 -W Get/set the IDE/SATA drive´s write-caching feature.
592 -X Set the IDE transfer mode for (E)IDE/ATA drives. This is typi‐
594 cally used in combination with -d1 when enabling DMA to/from a
595 drive on a supported interface chipset, where -X mdma2 is used
596 to select multiword DMA mode2 transfers and -X sdma1 is used to
597 select simple mode 1 DMA transfers. With systems which support
598 UltraDMA burst timings, -X udma2 is used to select UltraDMA
599 mode2 transfers (you´ll need to prepare the chipset for UltraDMA
600 beforehand). Apart from that, use of this option is seldom nec‐
601 essary since most/all modern IDE drives default to their fastest
602 PIO transfer mode at power-on. Fiddling with this can be both
603 needless and risky. On drives which support alternate transfer
604 modes, -X can be used to switch the mode of the drive only.
605 Prior to changing the transfer mode, the IDE interface should be
606 jumpered or programmed (see -p option) for the new mode setting
607 to prevent loss and/or corruption of data. Use this with
608 extreme caution! For the PIO (Programmed Input/Output) transfer
609 modes used by Linux, this value is simply the desired PIO mode
610 number plus 8. Thus, a value of 09 sets PIO mode1, 10 enables
611 PIO mode2, and 11 selects PIO mode3. Setting 00 restores the
612 drive´s "default" PIO mode, and 01 disables IORDY. For multi‐
613 word DMA, the value used is the desired DMA mode number plus 32.
614 for UltraDMA, the value is the desired UltraDMA mode number plus
615 64.
616 -y Force an IDE drive to immediately enter the low power consump‐
618 tion standby mode, usually causing it to spin down. The current
619 power mode status can be checked using the -C option.
620 -Y Force an IDE drive to immediately enter the lowest power con‐
622 sumption sleep mode, causing it to shut down completely. A hard
623 or soft reset is required before the drive can be accessed again
624 (the Linux IDE driver will automatically handle issuing a reset
625 if/when needed). The current power mode status can be checked
626 using the -C option.
627 -z Force a kernel re-read of the partition table of the specified
629 device(s).
630 -Z Disable the automatic power-saving function of certain Seagate
632 drives (ST3xxx models?), to prevent them from idling/spinning-
633 down at inconvenient times.
634 ATA Security Feature Set
637 These switches are DANGEROUS to experiment with, and might not work
639 with some kernels. USE AT YOUR OWN RISK.
640 --security-help
642 Display terse usage info for all of the --security-* options.
643 --security-freeze
645 Freeze the drive´s security settings. The drive does not accept
646 any security commands until next power-on reset. Use this func‐
647 tion in combination with --security-unlock to protect drive from
648 any attempt to set a new password. Can be used standalone, too.
649 No other options are permitted on the command line with this
650 one.
651 --security-unlock PWD
653 Unlock the drive, using password PWD. Password is given as an
654 ASCII string and is padded with NULs to reach 32 bytes. The
655 applicable drive password is selected with the --user-master
656 switch (default is "user" password). No other options are per‐
657 mitted on the command line with this one.
658 --security-set-pass PWD
660 Lock the drive, using password PWD (Set Password) (DANGEROUS).
661 Password is given as an ASCII string and is padded with NULs to
662 reach 32 bytes. Use the special password NULL to set an empty
663 password. The applicable drive password is selected with the
664 --user-master switch (default is "user" password) and the appli‐
665 cable security mode with the --security-mode switch. No other
666 options are permitted on the command line with this one.
667 --security-disable PWD
669 Disable drive locking, using password PWD. Password is given as
670 an ASCII string and is padded with NULs to reach 32 bytes. The
671 applicable drive password is selected with the --user-master
672 switch (default is "user" password). No other options are per‐
673 mitted on the command line with this one.
674 --security-erase PWD
676 Erase (locked) drive, using password PWD (DANGEROUS). Password
677 is given as an ASCII string and is padded with NULs to reach 32
678 bytes. Use the special password NULL to represent an empty
679 password. The applicable drive password is selected with the
680 --user-master switch (default is "user" password). No other
681 options are permitted on the command line with this one.
682 --security-erase-enhanced PWD
684 Enhanced erase (locked) drive, using password PWD (DANGEROUS).
685 Password is given as an ASCII string and is padded with NULs to
686 reach 32 bytes. The applicable drive password is selected with
687 the --user-master switch (default is "user" password). No other
688 options are permitted on the command line with this one.
689 --user-master USER
691 Specifies which password (user/master) to select. Defaults to
692 user password. Only useful in combination with --security-
693 unlock, --security-set-pass, --security-disable, --security-
694 erase or --security-erase-enhanced.
695 u user password
696 m master password
697 --security-mode MODE
700 Specifies which security mode (high/maximum) to set. Defaults
701 to high. Only useful in combination with --security-set-pass.
702 h high security
703 m maximum security
704 THIS FEATURE IS EXPERIMENTAL AND NOT WELL TESTED. USE AT YOUR
706 OWN RISK.
707
709 /etc/hdparm.conf
710
712 As noted above, the -m sectcount and -u 1 options should be used with
713 caution at first, preferably on a read-only filesystem. Most drives
714 work well with these features, but a few drive/controller combinations
715 are not 100% compatible. Filesystem corruption may result. Backup
716 everything before experimenting!
717 Some options (e.g. -r for SCSI) may not work with old kernels as neces‐
719 sary ioctl()´s were not supported.
720 Although this utility is intended primarily for use with SATA/IDE hard
722 disk devices, several of the options are also valid (and permitted) for
723 use with SCSI hard disk devices and MFM/RLL hard disks with XT inter‐
724 faces.
725 The Linux kernel up until 2.6.12 (and probably later) doesn´t handle
727 the security unlock and disable commands gracefully and will segfault
728 and in some cases even panic. The security commands however might
729 indeed have been executed by the drive. This poor kernel behaviour
730 makes the PIO data security commands rather useless at the moment.
731 Note that the "security erase" and "security disable" commands have
733 been implemented as two consecutive PIO data commands and will not suc‐
734 ceed on a locked drive because the second command will not be issued
735 after the segfault. See the code for hints how patch it to work around
736 this problem. Despite the segfault it is often still possible to run
737 two instances of hdparm consecutively and issue the two necessary com‐
738 mands that way.
739
741 hdparm has been written by Mark Lord <mlord@pobox.com>, the original
742 primary developer and maintainer of the (E)IDE driver for Linux, and
743 current contributer to the libata subsystem, along with suggestions and
744 patches from many netfolk.
745 The disable Seagate auto-powersaving code is courtesy of Tomi Leppikan‐
747 gas(tomilepp@paju.oulu.fi).
748 Security freeze command by Benjamin Benz, 2005.
750 PIO data out security commands by Leonard den Ottolander, 2005. Some
752 other parts by Benjamin Benz and others.
753
755 http://www.t13.org/ Technical Committee T13 AT Attachment (ATA/ATAPI)
756 Interface.
757 http://www.serialata.org/ Serial ATA International Organization.
759 http://www.compactflash.org/ CompactFlash Association.
761Version 9.43 November 2012 HDPARM(8)