Доброго времени суток, (извините за длинный пост) подскажите плиз где порыться? Есть FreeNAS (ну так уж исторически сложилось что оно..)
Огромная благодарность заранее за любые мысли!FreeBSD host 6.2-RELEASE-p9 FreeBSD 6.2-RELEASE-p9 #0: Tue Dec 25 11:18:29 CET 2007 root@FreeBSD.local:/usr/obj/freenas/usr/src/sys/FREENAS-i386 i386
раздел с оного безобразия по nfs прилеплен на линукс (CentOS release 4.5 (Final); Linux host2 2.6.9-55.0.2.ELsmp #1 SMP Tue Jun 26 14:30:58 EDT 2007 i686 i686 i386 GNU/Linux
- это pcbackup & etc). Производительность этой связки стремится к 0 и на интерфейсе FreeNAS видится приличный и постоянный прирост ierrs:# netstat -in
Name Mtu Network Address Ipkts Ierrs Opkts Oerrs Coll
fxp0 1500 <Link#1> 00:60:e0:01:9e:bf 910053577 41248693 1139321656 13 0
fxp0 1500 192.168.254 192.168.254.23 908973751 - 1139314298 - -tcpdump - постоянные обновления размера окна, перепосылки и дубликаты ack
причем беда только с nfs (ver 3 с дефолтными установками) - ssh все совершенно нормальнонесколько тестов:
# time dd if=/dev/zero of=/backuppc/testfile bs=16k count=4096 (попытка менять размер блока дает только микро-улучшения)
4096+0 records in
4096+0 records out
real 60m26.792s
user 0m0.010s
sys 0m0.347s# netstat -s -p tcp
tcp:
1137231692 packets sent
419590015 data packets (171407559 bytes)
1220857 data packets (1324925622 bytes) retransmitted
9920 data packets unnecessarily retransmitted
0 resends initiated by MTU discovery
662589132 ack-only packets (0 delayed)
0 URG only packets
0 window probe packets
53819033 window update packets
12655 control packets
883241053 packets received
252008873 acks (for 3555942661 bytes)
44164764 duplicate acks
0 acks for unsent data
592609019 packets (2504593146 bytes) received in-sequence
14795377 completely duplicate packets (4120887360 bytes)
0 old duplicate packets
721 packets with some dup. data (121300 bytes duped)
58997678 out-of-order packets (2394235623 bytes)
3 packets (0 bytes) of data after window
0 window probes
58322 window update packets
10 packets received after close
0 discarded for bad checksums
0 discarded for bad header offset fields
0 discarded because packet too short
106 connection requests
12472 connection accepts
14 bad connection attempts
0 listen queue overflows
0 ignored RSTs in the windows
12578 connections established (including accepts)
12606 connections closed (including 24 drops)
4685 connections updated cached RTT on close
4685 connections updated cached RTT variance on close
1459 connections updated cached ssthresh on close
0 embryonic connections dropped
252008873 segments updated rtt (of 151193126 attempts)
727995 retransmit timeouts
0 connections dropped by rexmit timeout
0 persist timeouts
0 connections dropped by persist timeout
6 keepalive timeouts
6 keepalive probes sent
0 connections dropped by keepalive
60783262 correct ACK header predictions
528811004 correct data packet header predictions
12548 syncache entries added
16 retransmitted
6 dupsyn
0 dropped
12472 completed
0 bucket overflow
0 cache overflow
75 reset
0 stale
0 aborted
0 badack
1 unreach
0 zone failures
0 cookies sent
0 cookies received
4743826 SACK recovery episodes
11081753 segment rexmits in SACK recovery episodes
925272612 byte rexmits in SACK recovery episodes
42109085 SACK options (SACK blocks) received
65960433 SACK options (SACK blocks) sent
0 SACK scoreboard overflownas01:/mnt/ColoBackups# netstat -m
1097/1933/3030 mbufs in use (current/cache/total)
1083/981/2064/32768 mbuf clusters in use (current/cache/total/max)
522/184 mbuf+clusters out of packet secondary zone in use (current/cache)
0/0/0/0 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/0 9k jumbo clusters in use (current/cache/total/max)
0/0/0/0 16k jumbo clusters in use (current/cache/total/max)
2440K/2445K/4885K bytes allocated to network (current/cache/total)
0/45/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/0/0 requests for jumbo clusters denied (4k/9k/16k)
0/5/4112 sfbufs in use (current/peak/max)
0 requests for sfbufs denied
0 requests for sfbufs delayed
0 requests for I/O initiated by sendfile
109082 calls to protocol drain routines# sysctl -a | grep nfs
vfs.nfs.downdelayinitial: 12
vfs.nfs.downdelayinterval: 30
vfs.nfs.nfs3_jukebox_delay: 10
vfs.nfs.reconnects: 0
vfs.nfs.bufpackets: 4
vfs.nfs.realign_count: 0
vfs.nfs.realign_test: 0
vfs.nfs.defect: 0
vfs.nfs.iodmax: 20
vfs.nfs.iodmin: 0
vfs.nfs.iodmaxidle: 120
vfs.nfs.diskless_rootpath:
vfs.nfs.diskless_valid: 0
vfs.nfs.nfs_ip_paranoia: 1
vfs.nfs.nfs_directio_allow_mmap: 1
vfs.nfs.nfs_directio_enable: 0
vfs.nfs.clean_pages_on_close: 1
vfs.nfs.nfsv3_commit_on_close: 0
vfs.nfs.access_cache_timeout: 60
vfs.nfs4.nfsv3_commit_on_close: 0
vfs.nfs4.access_cache_timeout: 60
vfs.nfsrv.nfs_privport: 0
vfs.nfsrv.commit_miss: 722233
vfs.nfsrv.commit_blks: 6356806
vfs.nfsrv.async: 0
vfs.nfsrv.realign_count: 19061
vfs.nfsrv.realign_test: 113796761
vfs.nfsrv.gatherdelay_v3: 0
vfs.nfsrv.gatherdelay: 10000
solved :)
>solved :)И что было? :-)
>solved :)..а было напросто кривое автоопределение моды порта при подключении сего чуда к catalyst 2950 (аж самой смешно что туда сразу не залезла :D - смутил ssh, который при этом всем вел себя совершенно пристойно)- примитивно надо ручками выставить то что требуется