RFC2001: TCP Slow Start, Congestion Avoidance, Fast Retransmit,
and Fast Recovery Algorithms
...
3. Fast Retransmit
Modifications to the congestion avoidance algorithm were proposed in
1990 [3]. Before describing the change, realize that TCP may
generate an immediate acknowledgment (a duplicate ACK) when an out-
of-order segment is received (Section 4.2.2.21 of [1], with a note
that one reason for doing so was for the experimental fast-
retransmit algorithm). This duplicate ACK should not be delayed.
The purpose of this duplicate ACK is to let the other end know that a
segment was received out of order, and to tell it what sequence
number is expected.
Since TCP does not know whether a duplicate ACK is caused by a lost
segment or just a reordering of segments, it waits for a small number
of duplicate ACKs to be received. It is assumed that if there is
just a reordering of the segments, there will be only one or two
duplicate ACKs before the reordered segment is processed, which will
then generate a new ACK. If three or more duplicate ACKs are
received in a row, it is a strong indication that a segment has been
lost. TCP then performs a retransmission of what appears to be the
missing segment, without waiting for a retransmission timer to
expire.
Change-Id: Ie2cbcecab507c3d831f74390a6a85e0c5c8e0652
Signed-off-by: chao.an <anchao@xiaomi.com>
1.Consolidate absolute to relative timeout conversion into one place(_net_timedwait)
2.Drive the wait timeout logic by net_timedwait instead of devif_timer
This patch help us remove devif_timer(period tick) to save the power in the future.
Change-Id: I534748a5d767ca6da8a7843c3c2f993ed9ea77d4
Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
Author: Gregory Nutt <gnutt@nuttx.org>
Run all .h and .c files modified in last PR through nxstyle.
Author: Xiang Xiao <xiaoxiang@xiaomi.com>
Net cleanup (#17)
* Fix the semaphore usage issue found in tcp/udp
1. The count semaphore need disable priority inheritance
2. Loop again if net_lockedwait return -EINTR
3. Call nxsem_trywait to avoid the race condition
4. Call nxsem_post instead of sem_post
* Put the work notifier into free list to avoid the heap fragment in the long run. Since the allocation strategy is encapsulated internally, we can even refine the implementation later.
* Network stack shouldn't allocate memory in the poll implementation to avoid the heap fragment in the long run, other modification include:
1. Select MM_IOB automatically since ICMP[v6] socket can't work without the read ahead buffer
2. Remove the net lock since xxx_callback_free already do the same thing
3. TCP/UDP poll should work even the read ahead buffer isn't enabled at all
* Add NET_ prefix for UDP_NOTIFIER and TCP_NOTIFIER option to align with other UDP/TCP option convention
* Remove the unused _SF_[IDLE|ACCEPT|SEND|RECV|MASK] flags since there are code to set/clear these flags, but nobody check them.
Iobinstrumentation
* mm/iob: Introduces producer/consumer id to every iob call. This is so that the calls can be instrumented to monitor the IOB resources.
* iob instrumentation - Merges producer/consumer enumeration for simpler IOB user.
* fs/procfs: Starts adding support for /proc/iobinfo
* fs/procfs: Finishes first pass of simple IOB user stastics and /proc/iobinfo entry
Approved-by: Gregory Nutt <gnutt@nuttx.org>
net/utils: return from net_breaklock() was being clobbered.
net/: Replace all calls to iob_alloc() with calls to net_ioballoc() which will release the network lock, if necessary.
net/utils, tcp, include/net: Separate out the special IOB allocation logic and place it in its own function. Prototype is available in a public header file where it can also be used by network drivers.
net/utils: net_timedwait() now uses new net_breaklock() and net_restorelock().
This commit backs out most of commit b4747286b1. That change was added because sem_wait() would sometimes cause cancellation points inappropriated. But with these recent changes, nxsem_wait() is used instead and it is not a cancellation point.
In the OS, all calls to sem_wait() changed to nxsem_wait(). nxsem_wait() does not return errors via errno so each place where nxsem_wait() is now called must not examine the errno variable.
In all OS functions (not libraries), change sem_wait() to nxsem_wait(). This will prevent the OS from creating bogus cancellation points and from modifying the per-task errno variable.
sched/semaphore: Add the function nxsem_wait(). This is a new internal OS interface. It is functionally equivalent to sem_wait() except that (1) it is not a cancellation point, and (2) it does not set the per-thread errno value on return.
sched/semaphore: Add nxsem_post() which is identical to sem_post() except that it never modifies the errno variable. Changed all references to sem_post in the OS to nxsem_post().
sched/semaphore: Add nxsem_destroy() which is identical to sem_destroy() except that it never modifies the errno variable. Changed all references to sem_destroy() in the OS to nxsem_destroy().
libc/semaphore and sched/semaphore: Add nxsem_getprotocol() and nxsem_setprotocola which are identical to sem_getprotocol() and set_setprotocol() except that they never modifies the errno variable. Changed all references to sem_setprotocol in the OS to nxsem_setprotocol(). sem_getprotocol() was not used in the OS
libc/semaphore: Add nxsem_getvalue() which is identical to sem_getvalue() except that it never modifies the errno variable. Changed all references to sem_getvalue in the OS to nxsem_getvalue().
sched/semaphore: Rename all internal private functions from sem_xyz to nxsem_xyz. The sem_ prefix is (will be) reserved only for the application semaphore interfaces.
libc/semaphore: Add nxsem_init() which is identical to sem_init() except that it never modifies the errno variable. Changed all references to sem_init in the OS to nxsem_init().
sched/semaphore: Rename sem_tickwait() to nxsem_tickwait() so that it is clear this is an internal OS function.
sched/semaphoate: Rename sem_reset() to nxsem_reset() so that it is clear this is an internal OS function.
When a poll requesting POLLOUT happens, the poll should return
immediately if a write will not block. This change adds that, as
opposed to the old behaviour of blocking until a timer from the
Ethernet driver eventually triggers the poll to complete.
This is only implemented for buffered TCP. Unbuffered TCP should
behave as before.
