slow rcp to AIX 5.2 43P-150

[MoshiachNow]

HI,

rcp to 43P-150 was fast with AIX 4.3.3 (about 8MB/SEC)over 100BT interface.
Mow with AIX 5.2+ML01 it slow - about 3.5 MB/sec.
rcp from this machine to others is still fast .
The problem is only with copying to it.
I will appreciate any advise,the "no -a" output is :
==========================
no -a
arpqsize = 12
arpt_killc = 20
arptab_bsiz = 7
arptab_nb = 73
bcastping = 0
clean_partial_conns = 0
ddp_recvspace = 9376
ddp_sendspace = 586
ddpcksum = 0
ddpforwarding = 1
ddpraw_recvspace = 19168
ddpraw_sendspace = 599
delayack = 0
delayackports = {}
dgd_packets_lost = 3
dgd_ping_time = 5
dgd_retry_time = 5
directed_broadcast = 0
extendednetstats = 0
fasttimo = 200
icmp6_errmsg_rate = 10
icmpaddressmask = 0
ie5_old_multicast_mapping = 0
ifsize = 256
inet_stack_size = 16
ip6_defttl = 64
ip6_prune = 1
ip6forwarding = 0
ip6srcrouteforward = 1
ipforwarding = 1
ipfragttl = 60
ipignoreredirects = 0
ipqmaxlen = 100
ipsendredirects = 1
ipsrcrouteforward = 1
ipsrcrouterecv = 0
ipsrcroutesend = 1
llsleep_timeout = 3
lo_perf = 1
lowthresh = 90
main_if6 = 0
main_site6 = 0
maxnip6q = 20
maxttl = 255
medthresh = 95
multi_homed = 1
nbc_limit = 445644
nbc_max_cache = 131072
nbc_min_cache = 1
nbc_ofile_hashsz = 12841
nbc_pseg = 0
nbc_pseg_limit = 15680
ndp_mmaxtries = 3
ndp_umaxtries = 3
ndpqsize = 50
ndpt_down = 3
ndpt_keep = 120
ndpt_probe = 5
ndpt_reachable = 30
ndpt_retrans = 1
net_malloc_police = 0
nonlocsrcroute = 0
nstrpush = 8
passive_dgd = 0
pmtu_default_age = 10
pmtu_rediscover_interval = 30
psebufcalls = 20
psecache = 1
pseintrstack = 12288
psetimers = 20
rfc1122addrchk = 0
rfc1323 = 1
rfc2414 = 0
route_expire = 1
routerevalidate = 0
rto_high = 64
rto_length = 13
rto_limit = 7
rto_low = 1
sack = 0
sb_max = 1048576
send_file_duration = 300
site6_index = 0
sockthresh = 85
sodebug = 0
somaxconn = 1024
strctlsz = 1024
strmsgsz = 0
strthresh = 85
strturncnt = 15
subnetsarelocal = 1
tcp_bad_port_limit = 0
tcp_ecn = 0
tcp_ephemeral_high = 65535
tcp_ephemeral_low = 32768
tcp_finwait2 = 1200
tcp_init_window = 0
tcp_inpcb_hashtab_siz = 24499
tcp_keepcnt = 8
tcp_keepidle = 14400
tcp_keepinit = 150
tcp_keepintvl = 150
tcp_limited_transmit = 1
tcp_maxburst = 0
tcp_mssdflt = 512
tcp_nagle_limit = 65535
tcp_ndebug = 100
tcp_newreno = 1
tcp_nodelayack = 0
tcp_pmtu_discover = 1
tcp_recvspace = 245760
tcp_sendspace = 245760
tcp_timewait = 1
tcp_ttl = 60
thewall = 524288
udp_bad_port_limit = 0
udp_ephemeral_high = 65535
udp_ephemeral_low = 32768
udp_inpcb_hashtab_siz = 24499
udp_pmtu_discover = 1
udp_recvspace = 42080
udp_sendspace = 9216
udp_ttl = 30
udpcksum = 1
use_isno = 1

"Long live king Moshiach !"

http://www.7for70.com/

 

[sbix]

try to set
udp_pmtu_discover=0
tcp_pmtu_discover=0
You have huge values for tcp_sendspace and tcp_recvspace, reccomended values are 16384 for both while
for udp_sendspace, udprecv_space the recommended val are 9216 and 41600

 

[MoshiachNow]

Thanks,sbix.

However:
The increased receivespace and sendspace are problematic only when there is not enough memory - I have enough for this machine (1 GB).
Anyhow,I have tried the params you have suggested - no difference.Also ,we do not use udp,only tcp here.
Any other suggestions ?
Thanks

"Long live king Moshiach !"

http://www.7for70.com/

 

[sbix]

Try to execute:
netstat -p tcp
rcp what_you_want_to_rcp
netstat -p tcp
And ... if you wish post the result pls

 

[MoshiachNow]

netstat -p tcp
tcp:
6068 packets sent
538 data packets (154299 bytes)
0 data packets (0 bytes) retransmitted
613 ack-only packets (595 delayed)
0 URG only packets
0 window probe packets
4910 window update packets
7 control packets
0 large sends
0 bytes sent using largesend
0 bytes is the biggest largesend
217865 packets received
547 acks (for 154269 bytes)
0 duplicate acks
0 acks for unsent data
217432 packets (314576955 bytes) received in-sequence
0 completely duplicate packets (0 bytes)
0 old duplicate packets
0 packets with some dup. data (0 bytes duped)
0 out-of-order packets (0 bytes)
0 packets (0 bytes) of data after window
0 window probes
0 window update packets
0 packets received after close
0 packets with bad hardware assisted checksum
0 discarded for bad checksums
0 discarded for bad header offset fields
0 discarded because packet too short
0 discarded by listeners
0 discarded due to listener's queue full
3 ack packet headers correctly predicted
217303 data packet headers correctly predicted
4 connection requests
10 connection accepts
14 connections established (including accepts)
12 connections closed (including 1 drop)
0 connections with ECN capability
0 times responded to ECN
0 embryonic connections dropped
551 segments updated rtt (of 553 attempts)
0 segments with congestion window reduced bit set
0 segments with congestion experienced bit set
0 resends due to path MTU discovery
0 path MTU discovery terminations due to retransmits
0 retransmit timeouts
0 connections dropped by rexmit timeout
0 fast retransmits
0 when congestion window less than 4 segments
0 newreno retransmits
0 times avoided false fast retransmits
0 persist timeouts
0 connections dropped due to persist timeout
0 keepalive timeouts
0 keepalive probes sent
0 connections dropped by keepalive
0 times SACK blocks array is extended
0 times SACK holes array is extended
0 packets dropped due to memory allocation failure
0 connections in timewait reused
0 delayed ACKs for SYN
0 delayed ACKs for FIN
0 send_and_disconnects
0 spliced connections
0 spliced connections closed
0 spliced connections reset
0 spliced connections timeout
0 spliced connections persist timeout
0 spliced connections keepalive timeout
#

============
rcp ....
============
netstat -p tcp
tcp:
7912 packets sent
592 data packets (180607 bytes)
0 data packets (0 bytes) retransmitted
762 ack-only packets (742 delayed)
0 URG only packets
0 window probe packets
6550 window update packets
8 control packets
0 large sends
0 bytes sent using largesend
0 bytes is the biggest largesend
290340 packets received
602 acks (for 180581 bytes)
0 duplicate acks
0 acks for unsent data
289854 packets (419434629 bytes) received in-sequence
0 completely duplicate packets (0 bytes)
0 old duplicate packets
0 packets with some dup. data (0 bytes duped)
0 out-of-order packets (0 bytes)
0 packets (0 bytes) of data after window
0 window probes
0 window update packets
0 packets received after close
0 packets with bad hardware assisted checksum
0 discarded for bad checksums
0 discarded for bad header offset fields
0 discarded because packet too short
0 discarded by listeners
0 discarded due to listener's queue full
3 ack packet headers correctly predicted
289722 data packet headers correctly predicted
4 connection requests
11 connection accepts
15 connections established (including accepts)
13 connections closed (including 1 drop)
0 connections with ECN capability
0 times responded to ECN
0 embryonic connections dropped
606 segments updated rtt (of 608 attempts)
0 segments with congestion window reduced bit set
0 segments with congestion experienced bit set
0 resends due to path MTU discovery
0 path MTU discovery terminations due to retransmits
0 retransmit timeouts
0 connections dropped by rexmit timeout
0 fast retransmits
0 when congestion window less than 4 segments
0 newreno retransmits
0 times avoided false fast retransmits
0 persist timeouts
0 connections dropped due to persist timeout
0 keepalive timeouts
0 keepalive probes sent
0 connections dropped by keepalive
0 times SACK blocks array is extended
0 times SACK holes array is extended
0 packets dropped due to memory allocation failure
0 connections in timewait reused
0 delayed ACKs for SYN
0 delayed ACKs for FIN
0 send_and_disconnects
0 spliced connections
0 spliced connections closed
0 spliced connections reset
0 spliced connections timeout
0 spliced connections persist timeout
0 spliced connections keepalive timeout
#


"Long live king Moshiach !"

http://www.7for70.com/

 

[sbix]

Uhm .... doing some maths comes out your system sends data in chuncks of avg 1447 bytes which is near the Ehternet MTU.
So problem should not reside in packet size.
If you update tcp_sendspace and tcp_recvspace parameter then you have to stop and start inetd

 

[MoshiachNow]

HI,

It's solved - in the new version we load (AIX 5.2 +our sw)we have lost our disk stanzas.
Now that we fixed it - the performace is ok.

Thanks

"Long live king Moshiach !"

http://www.7for70.com/

 

[d3vzero]

Hi Levw,

I'm quite suprised to read that you have a 43P at Aix 5.2.

I had thought that the RSPC Architecture of the 43P could not support Aix 5.2.

Please correct me if I'm wrong, as I have a few of these boxs (and other RSPC boxs) currently on 4.3.3 that I would upgrade to 5.2 if their hardware could actually support it.

Best Regards, Peter.

 

[MoshiachNow]

Hi,

As you see below - 43P-150 is NOT mentioned below:


Table 12- 5 Version 5.2 PCI RS/6000 withdrawn support listing
Systems Family Systems Family
7020-0U0 40P 6015-066
7020-SPE 40P 7248-100 43P
7020-B1B 40P 7248-120 43P
7020-B1C 40P 7248-132 43P
7020-D1D 40P 7043-140
7020-D2D 40P 7043-240


"Long live king Moshiach !"

http://www.7for70.com/