- 18 Jun, 2010 40 commits
-
-
Nitin Gupta authored
Currently, ramzwap devices (/dev/ramzswapX) can only be used as swap disks since it was hard-coded to consider only the first request in bio vector. Now, we iterate over all the segments in an incoming bio which allows us to handle all kinds of I/O requests. ramzswap devices can still handle PAGE_SIZE aligned and multiple of PAGE_SIZE sized I/O requests only. To ensure that we get always get such requests only, we set following request_queue attributes to PAGE_SIZE: - physical_block_size - logical_block_size - io_min - io_opt Note: physical and logical block sizes were already set equal to PAGE_SIZE and that seems to be sufficient to get PAGE_SIZE aligned I/O. Since we are no longer limited to handling swap requests only, the next few patches rename ramzswap to zram. So, the devices will then be called /dev/zram{0, 1, 2, ...} Usage/Examples: 1) Use as /tmp storage - mkfs.ext4 /dev/zram0 - mount /dev/zram0 /tmp 2) Use as swap: - mkswap /dev/zram0 - swapon /dev/zram0 -p 10 # give highest priority to zram0 Performance: - I/O benchamark done with 'dd' command. Details can be found here: http://code.google.com/p/compcache/wiki/zramperf Summary: - Maximum read speed (approx): - ram disk: 1200 MB/sec - zram disk: 600 MB/sec - Maximum write speed (approx): - ram disk: 500 MB/sec - zram disk: 160 MB/sec Issues: - Double caching: We can potentially waste memory by having two copies of a page -- one in page cache (uncompress) and second in the device memory (compressed). However, during reclaim, clean page cache pages are quickly freed, so this does not seem to be a big problem. - Stale data: Not all filesystems support issuing 'discard' requests to underlying block devices. So, if such filesystems are used over zram devices, we can accumulate lot of stale data in memory. Even for filesystems to do support discard (example, ext4), we need to see how effective it is. - Scalability: There is only one (per-device) de/compression buffer stats. This can lead to significant contention, especially when used for generic (non-swap) purposes. Signed-off-by:Nitin Gupta <ngupta@vflare.org> Acked-by:
Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by:
Greg Kroah-Hartman <gregkh@suse.de>
-
Naveen Jain authored
Older mechanism of counting the number of protocols registered with ST was slow, in-efficient. It used to check the protocol data for NULL for each registration/unregistration. With this change, counting protocols in maintained by a single counter protos_registered. Counting protocols is not just for debug purposes Signed-off-by:
Naveen Jain <naveen_jain@ti.com> Signed-off-by:
-
Naveen Jain authored
Add version information to be available under the sysfs group for kim. Signed-off-by:
-
Naveen Jain authored
Remove the older way of communicating with user-space daemon UIM. The older way involved creating of a new kobj and pid sysfs file under it, and sending signal using that pid. Now we communicate via rfkill to user-space UIM. Background: UIM is the user-space daemon which upon notification from ldisc driver, opens the tty, sets default baud and then installs (tiocsetd) the ldisc. Signed-off-by:
-
Pavan Savoy authored
Update the TODO of TI-ST to make sure it reflects current list of activities that need to be done. Also point it out to the user-space app code relevant to it. Signed-off-by:
Pavan Savoy <pavan_savoy@ti.com> Signed-off-by:
-
R.M. Thomas authored
This adds the easycap USB video adapter driver to the staging directory. Signed-off-by: -
-
Charles Clément authored
Rename driver struct and callbacks to vt6655_* instead of device_* and add __devinit/__devexit directives. Signed-off-by:
Charles Clément <caratorn@gmail.com> Signed-off-by:
-
Uwe Kleine-König authored
Signed-off-by:
Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Signed-off-by:
-
Timofey Trofimov authored
This is a patch to the 80211mgr.c file that fixes up warnings found by the checkpatch.pl tool Signed-off-by:
Timofey Trofimov <tumoxep@gmail.com> Signed-off-by:
-
Otavio Salvador authored
Fix this build error: drivers/staging/vt6656/built-in.o: In function `rotr1': (.text+0x1a878): multiple definition of `rotr1' drivers/staging/rt2870/built-in.o:(.text+0x106c2): first defined here drivers/staging/vt6656/built-in.o: In function `tkip_sbox': (.text+0x1a848): multiple definition of `tkip_sbox' drivers/staging/rt2870/built-in.o:(.text+0x10697): first defined here drivers/staging/vt6656/built-in.o: In function `xor_32': (.text+0x1ec24): multiple definition of `xor_32' drivers/staging/rt2870/built-in.o:(.text+0x111c4): first defined here drivers/staging/vt6656/built-in.o: In function `xor_128': (.text+0x1ec00): multiple definition of `xor_128' drivers/staging/rt2870/built-in.o:(.text+0x111dd): first defined here Signed-off-by:
Otavio Salvador <otavio@ossystems.com.br> Signed-off-by:
-
Andres More authored
Resolved whitespace-related checkpatch findings in .h files Signed-off-by:
Andres More <more.andres@gmail.com> Signed-off-by:
-
Andres More authored
Resolved checkpatch findings, but some long lines warnings. ERROR: space required before the open parenthesis '(' ERROR: spaces required around that Signed-off-by: -
Greg Kroah-Hartman authored
Commit 902d2411 converted U32 to u32 which you would think would be just fine. Unfortunatly, it seems that VIA only builds their code on a 32bit processor (which makes sense if you think about it), but this doesn't work on x86-64. So fix up the few places where this really wanted to be an unsigned long width. Cc: Charles Clément <caratorn@gmail.com> Cc: Forest Bond <forest@alittletooquiet.net>, Cc: Andres More <more.andres@gmail.com> Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Use unsigned long * instead. Signed-off-by:
-
Charles Clément authored
Use unsigned short * instead. Signed-off-by:
-
Charles Clément authored
Use unsigned char * instead. Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Remove custom macro for unsigned 32-bit integers, replace by u32. Signed-off-by:
-
Charles Clément authored
Remove custom macro for unsigned 16-bit integers. Signed-off-by:
-
Charles Clément authored
Remove custom macro for unsigned 8-bit integers. Signed-off-by:
-
Charles Clément authored
Remove custom macro for signed 8-bit integers. Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Calcu_LinkQual is already defined a couple lines earlier. Signed-off-by:
-
Charles Clément authored
Signed-off-by:
-
Charles Clément authored
Replace custom macro IS_ETH_ADDRESS_EQUAL by compare_ether_addr from <linux/etherdevice.h>. Signed-off-by:
-
Charles Clément authored
Replace custom macro IS_NULL_ADDRESS by is_zero_ether_addr from <linux/etherdevice.h>. Signed-off-by:
-
Charles Clément authored
Replace custom macro IS_BROADCAST_ADDRESS by is_broadcast_ether_addr from <linux/etherdevice.h>. Signed-off-by:
-
Charles Clément authored
Replace custom macro IS_MULTICAST_ADDRESS by is_multicast_ether_addr from <linux/etherdevice.h>. Remove linux/if_ether.h include as it is included in linux/etherdevice.h already. Signed-off-by:
-
Charles Clément authored
Replace custom minimum packet lenght definition MIN_PACKET_LEN by ETH_ZLEN from <linux/if_ether.h>. Signed-off-by:
-
Timofey Trofimov authored
This is a patch to the phy_calibration.c that fixes up almost all warnings and errors (except 80 characters limit and lack of tabs errors) found by the checkpatch.pl tool Signed-off-by:
-
