| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2006-08-04 | [PKT_SCHED] RED: Fix overflow in calculation of queue average | Ilpo Järvinen | |
| Overflow can occur very easily with 32 bits, e.g., with 1 second us_idle is approx. 2^20, which leaves only 11-Wlog bits for queue length. Since the EWMA exponent is typically around 9, queue lengths larger than 2^2 cause overflow. Whether the affected branch is taken when us_idle is as high as 1 second, depends on Scell_log, but with rather reasonable configuration Scell_log is large enough to cause p->Stab to have zero index, which always results zero shift (typically also few other small indices result in zero shift). Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net> | |||
| 2006-04-26 | Don't include linux/config.h from anywhere else in include/ | David Woodhouse | |
| Signed-off-by: David Woodhouse <dwmw2@infradead.org> | |||
| 2005-11-05 | [PKT_SCHED]: Generic RED layer | Thomas Graf | |
| Extracts the RED algorithm from sch_red.c and puts it into include/net/red.h for use by other RED based modules. The statistics are extended to be more fine grained in order to differ between probability/forced marks/drops. We now reset the average queue length when setting new parameters, leaving it might result in an unreasonable qavg for a while depending on the value of W. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> | |||
 |
index : Kernel | |
| My Linux kernel repository | Thomas White |
| aboutsummaryrefslogtreecommitdiff |