| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
| |
SVN-Revision: 32590
|
|
|
|
| |
SVN-Revision: 32580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Despite Westwood's theoretical advantages, in nearly
every benchmark we ran last year, TCP cubic won, whether it be
on correct RTT estimates, amount of buffering, responsiveness,
etc. on current hardware and software designs.
(both need timestamps on to work well, besides)
TCP cubic is better maintained and understood than westwood,
also.
While a scenario where westwood would win possibly exists,
there is too much buffering in the wifi stack in particular
at present, to see any improvement.
If you wish to exercise various TCPs under contention,
the current svn head of netperf (2.6) has options to switch
congestion control agorithms on the fly, as does iperf.
SVN-Revision: 32514
|
|
|
|
| |
SVN-Revision: 32498
|
|
|
|
| |
SVN-Revision: 32456
|
|
|
|
|
|
|
|
| |
that applies to all mips targets
The dcache bug that it works around is a generic issue, not a brcm47xx cache quirk
SVN-Revision: 32395
|
|
|
|
| |
SVN-Revision: 32094
|
|
|
|
| |
SVN-Revision: 32085
|
|
|
|
| |
SVN-Revision: 32077
|
|
|
|
| |
SVN-Revision: 32059
|
|
|
|
| |
SVN-Revision: 32006
|
|
|
|
| |
SVN-Revision: 32000
|
|
|
|
| |
SVN-Revision: 31999
|
|
|
|
| |
SVN-Revision: 31998
|
|
|
|
| |
SVN-Revision: 31924
|
|
|
|
| |
SVN-Revision: 31917
|
|
|
|
| |
SVN-Revision: 31916
|
|
|
|
| |
SVN-Revision: 31915
|
|
|
|
| |
SVN-Revision: 31914
|
|
|
|
| |
SVN-Revision: 31906
|
|
|
|
| |
SVN-Revision: 31905
|
|
|
|
| |
SVN-Revision: 31891
|
|
|
|
|
|
| |
significantly improves ethernet<->wireless performance with mac80211 based drivers
SVN-Revision: 31886
|
|
|
|
| |
SVN-Revision: 31856
|
|
|
|
| |
SVN-Revision: 31848
|
|
|
|
|
|
| |
Should fix #11513. Tested with the x86/generic squashfs image within a VM.
SVN-Revision: 31841
|
|
|
|
|
|
| |
overriding eeprom, fixes bogus wlan mac address on arv4520
SVN-Revision: 31835
|
|
|
|
| |
SVN-Revision: 31813
|
|
|
|
| |
SVN-Revision: 31808
|
|
|
|
| |
SVN-Revision: 31774
|
|
|
|
|
|
| |
master-2012-05-16-2
SVN-Revision: 31772
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Dave Täht)
Codel is a new AQM algorithm and RED replacement designed by
Kathie Nichols and Van Jacobson, and published in ACM queue:
http://queue.acm.org/detail.cfm?id=2209336
Codel stands for "Controlled Delay", and needs no knobs in the
general case, twiddled, for optimum results. It aims for 5ms of
delay, at most, when in use.
Additionally,
fq_codel (by eric dumazet) builds on codel to provide fair queuing
superior to what could be had with SFQ, and drop behavior saner
than RED, BLUE, or choke.
These patches are backported from net-next and are known to work
on Linux 3.3.4 and later.
Includes updates to codel for better portability and speed
SVN-Revision: 31756
|
|
|
|
| |
SVN-Revision: 31748
|
|
|
|
|
|
| |
It was missing in the previous commit.
SVN-Revision: 31738
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* CONFIG_ARCH_DMA_ADDR_T_64BIT
* CONFIG_ARCH_HAS_ILOG2_U32
* CONFIG_ARCH_HAS_ILOG2_U64
* CONFIG_ARCH_PHYS_ADDR_T_64BIT
* CONFIG_ARCH_SUPPORTS_MSI
* CONFIG_GENERIC_CPU_DEVICES
* CONFIG_HWMON_DEBUG_CHIP
* CONFIG_I2C_PXA_PCI
* CONFIG_LEDS_GPIO
* CONFIG_MINIX_FS_NATIVE_ENDIAN
* CONFIG_MLX4_CORE
* CONFIG_POWER_SUPPLY
* CONFIG_POWER_SUPPLY_DEBUG
* CONFIG_QUOTACTL
* CONFIG_SDIO_UART
* CONFIG_SENSORS_K10TEMP
* CONFIG_SENSORS_SCH56XX_COMMON
* CONFIG_SENSORS_VIA_CPUTEMP
* CONFIG_SERIO_AMBAKMI
* CONFIG_SERIO_I8042
* CONFIG_SERIO_LIBPS2
* CONFIG_SERIO_PCIPS2
* CONFIG_SERIO_RAW
* CONFIG_SERIO_SERPORT
* CONFIG_SPI_BITBANG
* CONFIG_SPI_GPIO
SVN-Revision: 31737
|
|
|
|
|
|
| |
It is used by the broken omap35xx/gumstix target only.
SVN-Revision: 31717
|
|
|
|
| |
SVN-Revision: 31713
|
|
|
|
| |
SVN-Revision: 31710
|
|
|
|
| |
SVN-Revision: 31709
|
|
|
|
|
|
|
|
|
|
|
| |
The 0x4322 ID is found on the BCM4322 used on some SoCs like the
Linksys WRT610N V1 connected to a BCM4705. The 43222 (0xa8d6) ID
is found on the BCM43222 used on some other SoCs like the D-Link
DSL-2760U connected to a BCM63xx.
This fixes #10887.
SVN-Revision: 31695
|
|
|
|
|
|
| |
It is used only by the broken coldfire target.
SVN-Revision: 31688
|
|
|
|
| |
SVN-Revision: 31687
|
|
|
|
| |
SVN-Revision: 31654
|
|
|
|
| |
SVN-Revision: 31645
|
|
|
|
|
|
| |
having to keep non-upstream ethernet driver changes
SVN-Revision: 31637
|
|
|
|
|
|
| |
newer kernels
SVN-Revision: 31625
|
|
|
|
| |
SVN-Revision: 31597
|
|
|
|
| |
SVN-Revision: 31586
|
|
|
|
|
|
|
|
| |
[juhosg: export xt_layer7.h for all kernel versions]
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
SVN-Revision: 31566
|
|
|
|
| |
SVN-Revision: 31552
|