This patch optimizes UDMA timings to increase write transfer rate on
ATA bus, these transfers are clocked by HCLK, tDVS+tDVH is modified to
decrease Tcyctyp (typical write cycle period). This is not overclocking,
we meet the ATA standar, the settings used by OF are not well optimized
for each UDMA mode, we will never know but probably this was due some
documentation issue.
ATA_UDMA_TIME register is documented on s3c6400 datasheet, information
included in s5l8700 datasheet is wrong or not valid for s5l8702.
From ATA specs, (Minimum, Maximum) values in nanoseconds:
UDMA 0 UDMA 1 UDMA 2 UDMA 3 UDMA 4
tACKENV (20, 70) (20, 70) (20, 70) (20, 55) (20, 55)
tRP (160, --) (125, --) (100, --) (100, --) (100, --)
tSS (50, --) (50, --) (50, --) (50, --) (50, --)
tDVS (70, --) (48, --) (31, --) (20, --) (6.7, --)
tDVH (6.2, --) (6.2, --) (6.2, --) (6.2, --) (6.2, --)
tDVS+tDVH (120, --) (80, --) (60, --) (45, --) (30, --)
Tcyc = tDVS+tDVH
WR[bytes/s] = 1/Tcyc[s] * 2[bytes]
On Classic (boosted):
HClk = 108 MHz. -> T = ~9.26 ns.
Old values (used by OF):
UDMA ATA_UDMA_TIME tACK tRP tSS tDVS tDVH Tcyc WR(MB/s)
0 0x5071152 27.8 166.7 55.6 74.1 55.6 129.7 15.4
1 0x3050a52 27.8 101.8 55.6 55.6 37 92.6 21.6
2 0x3030a52 27.8 101.8 55.6 37 37 74 27
3 0x2020a52 27.8 101.8 55.6 27.8 27.8 55.6 36
4 0x2010a52 27.8 101.8 55.6 18.5 27.8 46.3 43.2
New values:
UDMA ATA_UDMA_TIME tACK tRP tSS tDVS tDVH Tcyc WR(MB/s)
0 0x4071152 27.8 166.7 55.6 74.1 46.3 120.4 16.6
1 0x2050d52 27.8 129.6 55.6 55.6 27.8 83.4 24
2 0x2030a52 27.8 101.8 55.6 37 27.8 64.8 30.9
3 0x1020a52 27.8 101.8 55.6 27.8 18.5 46.3 43.2
4 0x1010a52 27.8 101.8 55.6 18.5 18.5 37 54
To verify that the settings are correct, a write-to-cache test was
performed using emCORE, the measured transfer rate (WRm) is compared
against the theoric transfer rate (WR) at 108 Mhz for the old and
the new UDMA4 settings (iPod 160, HDD Toshiba MK1634GAL):
UDMA ATA_UDMA_TIME Tcyc(ns) WR(MB/s) WRm(MB/s) RDm(MB/s)
4 0x2010a52 46.3 43.2 42.9 59.8
4 0x1010a52 37 54 53.5 59.8
Notes:
- The new UDMA4 settings increases ~25% the ATA transfer rate for
cached-writes. The real HDD write speed is limited by the internal
transfer rate (depends on cilinder, for the MK1634GAL it is 276 to
573 Mbits/s). Sequential write benchmark using diskdump on USB are
~8% faster.
- Read transfers are clocked by the device, it depends on UDMA mode
selected and are not affected by HClk or ATA_UDMA_TIME settings.
Read-from-cache tests results (RDm) using HClk=108 and HClk=54 for
UDMA4 are 59.8 MB/s on MK1634GAL.
- Minimum HClk is limited by tACKENV specs, using current settings
it is 54 MHz for UDMA4,UDMA3 and 43 MHz for UDMA2,UDMA1,UDMA0.
Change-Id: I61d67060410752518a59e1ff08072b21747ca997
Read/write buffers who are aligned to 16 were not re-aligned to 32 as
it should be. Althrough USB storage and buffering are always passing
buffers aligned to 32, a few unaligned buffers are being received from
other tasks, so this patch could solve some rare random issues.
Also fixes DMA configuration for HDDs that support any MDMA mode but
only UDMA0 (probably will never happen).
Change-Id: I00219ae434205681c69293fc563e0526224c9adf
- Add description for attributes supported by Samsung HS081HA (80Gb)
and HS161JQ (CEATA 160Gb).
- Show error code when ata_read_smart() fails.
Change-Id: I618cc4f37d139fc90f596e2cf3a751346b27deb6
Adds ata_read_smart() function to storage ATA driver, current
SMART data can be displayed and optionally written to hard
disk using System->Debug menu.
Change-Id: Ie8817bb311d5d956df2f0fbfaf554e2d53e89a93
Use 32 bytes for cache line length (arm926ej-s), this prevents
misalignments of ATA storage buffer which in some builds could
cause weird faults.
Change-Id: I88dc595d251315620ec49b0251ddc039ff47181e
Reviewed-on: http://gerrit.rockbox.org/1031
Reviewed-by: Marcin Bukat <marcin.bukat@gmail.com>
This improves compatibility with various HDD and CF/SD card mods.
It should also reduce power consumption while the drive is powered down.
Change-Id: I4b22c59b5d9ae2daea2ec5892e348e7e1934ca3e
Reviewed-on: http://gerrit.rockbox.org/897
Tested: Franklin Wei <frankhwei536@gmail.com>
Tested: Nial Shui <nialv7@gmail.com>
Tested: Michael Sparmann <theseven@gmx.net>
Reviewed-by: Marcin Bukat <marcin.bukat@gmail.com>
This patch redoes the filesystem code from the FAT driver up to the
clipboard code in onplay.c.
Not every aspect of this is finished therefore it is still "WIP". I
don't wish to do too much at once (haha!). What is left to do is get
dircache back in the sim and find an implementation for the dircache
indicies in the tagcache and playlist code or do something else that
has the same benefit. Leaving these out for now does not make anything
unusable. All the basics are done.
Phone app code should probably get vetted (and app path handling
just plain rewritten as environment expansions); the SDL app and
Android run well.
Main things addressed:
1) Thread safety: There is none right now in the trunk code. Most of
what currently works is luck when multiple threads are involved or
multiple descriptors to the same file are open.
2) POSIX compliance: Many of the functions behave nothing like their
counterparts on a host system. This leads to inconsistent code or very
different behavior from native to hosted. One huge offender was
rename(). Going point by point would fill a book.
3) Actual running RAM usage: Many targets will use less RAM and less
stack space (some more RAM because I upped the number of cache buffers
for large memory). There's very little memory lying fallow in rarely-used
areas (see 'Key core changes' below). Also, all targets may open the same
number of directory streams whereas before those with less than 8MB RAM
were limited to 8, not 12 implying those targets will save slightly
less.
4) Performance: The test_disk plugin shows markedly improved performance,
particularly in the area of (uncached) directory scanning, due partly to
more optimal directory reading and to a better sector cache algorithm.
Uncached times tend to be better while there is a bit of a slowdown in
dircache due to it being a bit heavier of an implementation. It's not
noticeable by a human as far as I can say.
Key core changes:
1) Files and directories share core code and data structures.
2) The filesystem code knows which descriptors refer to same file.
This ensures that changes from one stream are appropriately reflected
in every open descriptor for that file (fileobj_mgr.c).
3) File and directory cache buffers are borrowed from the main sector
cache. This means that when they are not in use by a file, they are not
wasted, but used for the cache. Most of the time, only a few of them
are needed. It also means that adding more file and directory handles
is less expensive. All one must do in ensure a large enough cache to
borrow from.
4) Relative path components are supported and the namespace is unified.
It does not support full relative paths to an implied current directory;
what is does support is use of "." and "..". Adding the former would
not be very difficult. The namespace is unified in the sense that
volumes may be specified several times along with relative parts, e.g.:
"/<0>/foo/../../<1>/bar" :<=> "/<1>/bar".
5) Stack usage is down due to sharing of data, static allocation and
less duplication of strings on the stack. This requires more
serialization than I would like but since the number of threads is
limited to a low number, the tradoff in favor of the stack seems
reasonable.
6) Separates and heirarchicalizes (sic) the SIM and APP filesystem
code. SIM path and volume handling is just like the target. Some
aspects of the APP file code get more straightforward (e.g. no path
hashing is needed).
Dircache:
Deserves its own section. Dircache is new but pays homage to the old.
The old one was not compatible and so it, since it got redone, does
all the stuff it always should have done such as:
1) It may be update and used at any time during the build process.
No longer has one to wait for it to finish building to do basic file
management (create, remove, rename, etc.).
2) It does not need to be either fully scanned or completely disabled;
it can be incomplete (i.e. overfilled, missing paths), still be
of benefit and be correct.
3) Handles mounting and dismounting of individual volumes which means
a full rebuild is not needed just because you pop a new SD card in the
slot. Now, because it reuses its freed entry data, may rebuild only
that volume.
4) Much more fundamental to the file code. When it is built, it is
the keeper of the master file list whether enabled or not ("disabled"
is just a state of the cache). Its must always to ready to be started
and bind all streams opened prior to being enabled.
5) Maintains any short filenames in OEM format which means that it does
not need to be rebuilt when changing the default codepage.
Miscellaneous Compatibility:
1) Update any other code that would otherwise not work such as the
hotswap mounting code in various card drivers.
2) File management: Clipboard needed updating because of the behavioral
changes. Still needs a little more work on some finer points.
3) Remove now-obsolete functionality such as the mutex's "no preempt"
flag (which was only for the prior FAT driver).
4) struct dirinfo uses time_t rather than raw FAT directory entry
time fields. I plan to follow up on genericizing everything there
(i.e. no FAT attributes).
5) unicode.c needed some redoing so that the file code does not try
try to load codepages during a scan, which is actually a problem with
the current code. The default codepage, if any is required, is now
kept in RAM separarately (bufalloced) from codepages specified to
iso_decode() (which must not be bufalloced because the conversion
may be done by playback threads).
Brings with it some additional reusable core code:
1) Revised file functions: Reusable code that does things such as
safe path concatenation and parsing without buffer limitations or
data duplication. Variants that copy or alter the input path may be
based off these.
To do:
1) Put dircache functionality back in the sim. Treating it internally
as a different kind of file system seems the best approach at this
time.
2) Restore use of dircache indexes in the playlist and database or
something effectively the same. Since the cache doesn't have to be
complete in order to be used, not getting a hit on the cache doesn't
unambiguously say if the path exists or not.
Change-Id: Ia30f3082a136253e3a0eae0784e3091d138915c8
Reviewed-on: http://gerrit.rockbox.org/566
Reviewed-by: Michael Sevakis <jethead71@rockbox.org>
Tested: Michael Sevakis <jethead71@rockbox.org>
When using variadic macros there's no need for IF_MD2/IF_MV2 to deal
with function parameters. IF_MD/IF_MV are enough.
Throw in IF_MD_DRV/ID_MV_VOL that return the parameter if MD/MV, or 0
if not.
Change-Id: I7605e6039f3be19cb47110c84dcb3c5516f2c3eb
This commit changes the default HDD endianness to the correct one,
but stays compatible with the old endianness.
If an MBR with the wrong endianness is detected, it will
automatically enable word swapping and issue a warning splash.
To permanently fix this you'll need to upgrade emCORE to at least r836.
This will wipe all data! A post-r836 build of emCORE will be
officially released during the next couple of days.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@31455 a1c6a512-1295-4272-9138-f99709370657
