David Young
2011-04-08 17:16:20 UTC
I am preparing to commit some improvements to TCP networking and a bug
fix both contributed by CoyotePoint Systems, Inc. The patch is large,
so I posted it at
<ftp://elmendorf.ojctech.com/users/netbsd-bdffaa79/devel-vtw-diff1>.
Please review the patches and send any questions/comments you may have.
Here's the proposed commit message:
Sometimes the reclamation of protocol buffers by tcp_drain(),
arp_drain(), frag6_drain(), or ip_drain() will sleep. When a
protocol-drain routines called in an interrupt context sleeps, the
system deadlocks. Avoid a deadlock when memory is low by deferring to a
thread context the reclamation of protocol buffers. The protocol's fast
time-out timer, protosw.pr_fasttimo, runs in thread context, so defer
reclamation to the next fast time-out.
Even after a TCP session enters the TIME_WAIT state, its corresponding
socket and protocol control blocks (PCBs) stick around until the TCP
Maximum Segment Lifetime (MSL) expires. On a host whose workload
necessarily creates and closes down many TCP sockets, the sockets & PCBs
for TCP sessions in TIME_WAIT state amount to many megabytes of dead
weight in RAM.
This patch reduces the resources demanded by TIME_WAIT-state sessions
using methods called Vestigial Time-Wait and Maximum Segment Lifetime
Truncation.
Maximum Segment Lifetimes Truncation (MSLT) assigns each TCP session to
a class based on the nearness of the peer. Corresponding to each class
is an MSL, and a session uses the MSL of its class. The classes are
loopback (local host equals remote host), local (local host and remote
host are on the same link/subnet), and remote (local host and remote
host communicate via one or more gateways). Classes corresponding to
nearer peers have lower MSLs by default: 2 seconds for loopback, 10
seconds for local, 60 seconds for remote. Loopback and local sessions
expire more quickly when MSLT is used.
Vestigial Time-Wait (VTW) replaces a TIME_WAIT session's PCB/socket
dead weight with a compact representation of the session, called a
"vestigial PCB". VTW data structures are designed to be very fast and
memory-efficient: for fast insertion and lookup of vestigial PCBs,
the PCBs are stored in a hash table that is designed to minimize the
number of cacheline visits per lookup/insertion. The memory both
for vestigial PCBs and for elements of the PCB hashtable come from
fixed-size pools, and linked data structures exploit this to conserve
memory by representing references with a narrow index/offset from the
start of a pool instead of a pointer. When space for new vestigial PCBs
runs out, VTW makes room by discarding old vestigial PCBs, oldest first.
VTW cooperates with MSLT.
It may help to think of VTW as a "FIN cache" by analogy to the SYN
cache.
A 2.8-GHz Pentium 4 running a test workload that creates TIME_WAIT
sessions as fast as it can is approximately 17% idle when VTW is active
versus 0% idle when VTW is inactive. It has 103 megabytes more free RAM
when VTW is active (approximately 64k vestigial PCBs are created) than
when it is inactive.
Dave
fix both contributed by CoyotePoint Systems, Inc. The patch is large,
so I posted it at
<ftp://elmendorf.ojctech.com/users/netbsd-bdffaa79/devel-vtw-diff1>.
Please review the patches and send any questions/comments you may have.
Here's the proposed commit message:
Sometimes the reclamation of protocol buffers by tcp_drain(),
arp_drain(), frag6_drain(), or ip_drain() will sleep. When a
protocol-drain routines called in an interrupt context sleeps, the
system deadlocks. Avoid a deadlock when memory is low by deferring to a
thread context the reclamation of protocol buffers. The protocol's fast
time-out timer, protosw.pr_fasttimo, runs in thread context, so defer
reclamation to the next fast time-out.
Even after a TCP session enters the TIME_WAIT state, its corresponding
socket and protocol control blocks (PCBs) stick around until the TCP
Maximum Segment Lifetime (MSL) expires. On a host whose workload
necessarily creates and closes down many TCP sockets, the sockets & PCBs
for TCP sessions in TIME_WAIT state amount to many megabytes of dead
weight in RAM.
This patch reduces the resources demanded by TIME_WAIT-state sessions
using methods called Vestigial Time-Wait and Maximum Segment Lifetime
Truncation.
Maximum Segment Lifetimes Truncation (MSLT) assigns each TCP session to
a class based on the nearness of the peer. Corresponding to each class
is an MSL, and a session uses the MSL of its class. The classes are
loopback (local host equals remote host), local (local host and remote
host are on the same link/subnet), and remote (local host and remote
host communicate via one or more gateways). Classes corresponding to
nearer peers have lower MSLs by default: 2 seconds for loopback, 10
seconds for local, 60 seconds for remote. Loopback and local sessions
expire more quickly when MSLT is used.
Vestigial Time-Wait (VTW) replaces a TIME_WAIT session's PCB/socket
dead weight with a compact representation of the session, called a
"vestigial PCB". VTW data structures are designed to be very fast and
memory-efficient: for fast insertion and lookup of vestigial PCBs,
the PCBs are stored in a hash table that is designed to minimize the
number of cacheline visits per lookup/insertion. The memory both
for vestigial PCBs and for elements of the PCB hashtable come from
fixed-size pools, and linked data structures exploit this to conserve
memory by representing references with a narrow index/offset from the
start of a pool instead of a pointer. When space for new vestigial PCBs
runs out, VTW makes room by discarding old vestigial PCBs, oldest first.
VTW cooperates with MSLT.
It may help to think of VTW as a "FIN cache" by analogy to the SYN
cache.
A 2.8-GHz Pentium 4 running a test workload that creates TIME_WAIT
sessions as fast as it can is approximately 17% idle when VTW is active
versus 0% idle when VTW is inactive. It has 103 megabytes more free RAM
when VTW is active (approximately 64k vestigial PCBs are created) than
when it is inactive.
Dave
--
David Young OJC Technologies
***@ojctech.com Urbana, IL * (217) 344-0444 x24
--
Posted automagically by a mail2news gateway at muc.de e.V.
Please direct questions, flames, donations, etc. to news-***@muc.de
David Young OJC Technologies
***@ojctech.com Urbana, IL * (217) 344-0444 x24
--
Posted automagically by a mail2news gateway at muc.de e.V.
Please direct questions, flames, donations, etc. to news-***@muc.de