| created | 2020-07-28T20:16:01Z |
|---|---|
| begin | 2020-05-21T00:00:00Z |
| end | 2020-05-22T00:00:00Z |
| path | src/sys |
| commits | 16 |
| date | 2020-05-21T00:06:16Z | |||
|---|---|---|---|---|
| author | dlg | |||
| files | src/sys/net/ifq.c | log | diff | annotate |
| message |
back out 1.38. some bits of the stack aren't ready for it yet. mark patruck found significant packet drops with trunk(4), and there's some reports that pppx or pipex relies on some implicit locking that it shouldn't. i can fix those without this diff being in the tree. |
|||
| date | 2020-05-21T00:44:36Z | |||
|---|---|---|---|---|
| author | dlg | |||
| files | src/sys/net/if_trunk.c | log | diff | annotate |
| message |
don't limit the output queue (ifq) length to 1 anymore. if we use the ifq to move packet processing to another context, it's too easy to fill up the one slot and cause packet loss. the ifq len was set to 1 to avoid delays produced by the original implementation of tx mitigation. however, trunk now introduces latency because it isn't mpsafe yet, which causes the network stack to have to take the kernel lock for each packet, and the kernel lock can be quite contended. i want to use the ifq to move the packet to the systq thread (which already has the kernel lock) before trunk is asked to transmit it. tested by mark patruck and myself. |
|||
| date | 2020-05-21T01:39:07Z | |||
|---|---|---|---|---|
| author | visa | |||
| files | src/sys/arch/sparc64/sparc64/Attic/mutex.S | log | diff | annotate |
| message |
Remove sparc64 mutex.S. The architecture has been using the MI mutex for a while. OK mpi@ |
|||
| date | 2020-05-21T01:39:56Z | |||
|---|---|---|---|---|
| author | visa | |||
| files | src/sys/sys/syslog.h | log | diff | annotate |
| message |
Update comment to reflect current headers. OK millert@ |
|||
| date | 2020-05-21T01:48:43Z | |||
|---|---|---|---|---|
| author | visa | |||
| files | src/sys/arch/sgi/dev/dsrtc.c | log | diff | annotate |
| message |
Use <dev/clock_subr.h> in dsrtc(4). Tested on IP30 with DS1687. Looks good to miod@ |
|||
| date | 2020-05-21T01:49:49Z | |||
|---|---|---|---|---|
| author | visa | |||
| files | src/sys/arch/sgi/hpc/dpclock.c | log | diff | annotate |
| message |
Use <dev/clock_subr.h> in dpclock(4). Looks good to miod@ |
|||
| date | 2020-05-21T01:50:42Z | |||
|---|---|---|---|---|
| author | visa | |||
| files | src/sys/arch/sgi/hpc/dsclock.c | log | diff | annotate |
| message |
Use <dev/clock_subr.h> in dsclock(4). Looks good to miod@ |
|||
| date | 2020-05-21T02:08:31Z | |||
|---|---|---|---|---|
| author | jmatthew | |||
| files | src/sys/dev/pci/if_mcx.c | log | diff | annotate |
| message |
Make use of checksum offloads. Very little effort required from the driver here. remi@ observed a small but noticeable improvement in packet forwarding performance, and I saw a significant increase in TCP receive throughput, especially with high MTU. ok dlg@ |
|||
| date | 2020-05-21T03:33:44Z | |||
|---|---|---|---|---|
| author | dlg | |||
| files | src/sys/netinet/ip_carp.c | log | diff | annotate |
| message |
implement a carp_transmit that bypasses the ifq on output. this is modelled on vlan_transmit, and basically enqueues the packet directly on the parent interface. even though carp is generally not used to transmit packets, we run dhcp relays on it at work and hit a situation where we unecessarily dropped packets because it's ifq maxlen was 1. i've been running this for a month in production. ok jmatthew@ |
|||
| date | 2020-05-21T05:24:59Z | |||
|---|---|---|---|---|
| author | dlg | |||
| files | src/sys/netinet/ip_carp.c | log | diff | annotate |
| message |
don't count packets in the carp protocol handling against an interface. these packets have generally already been counted on the interface because that's where they were sent or received from. the protocol handling side of things already counts things like packets, which you see with netstat -sp carp. |
|||
| date | 2020-05-21T09:31:59Z | |||
|---|---|---|---|---|
| author | mpi | |||
| files | src/sys/dev/pci/cz.c | log | diff | annotate |
| message |
Kill commented out czttypoll() routine. ok visa@ |
|||
| date | 2020-05-21T09:34:06Z | |||
|---|---|---|---|---|
| author | mpi | |||
| files | src/sys/kern/tty_pty.c | log | diff | annotate |
| message |
Add missing ICANON check in filt_ptcwrite(). ok millert@, visa@ |
|||
| date | 2020-05-21T09:35:09Z | |||
|---|---|---|---|---|
| author | mpi | |||
| files | src/sys/ufs/mfs/mfs_vnops.c | log | diff | annotate |
| message |
Explicitly documents that `vop_kqfilter' isn't missing. Just like most of the vop_* methods in MFS they aren't used. ok millert@, visa@ |
|||
| date | 2020-05-21T19:54:14Z | |||
|---|---|---|---|---|
| author | kettenis | |||
| files | src/sys/arch/powerpc64/include/trap.h | log | diff | annotate |
| src/sys/arch/powerpc64/powerpc64/machdep.c | log | diff | annotate | |
| message | Claim the memory region reserved for the interrupt vectors. | |||
| date | 2020-05-21T21:46:34Z | |||
|---|---|---|---|---|
| author | patrick | |||
| files | src/sys/dev/pci/pcidevs | log | diff | annotate |
| message | ASMedia ASM1182e PCIe switch. | |||
| date | 2020-05-21T21:46:50Z | |||
|---|---|---|---|---|
| author | patrick | |||
| files | src/sys/dev/pci/pcidevs.h | log | diff | annotate |
| src/sys/dev/pci/pcidevs_data.h | log | diff | annotate | |
| message | regen | |||