Date: Sun, 26 Oct 2008 14:56:25 +0100 From: Morten Winther <none@mw--mwi.dk.lh.bsd-dk.dk> To: bsd-dk@bsd-dk.dk Subject: PHP og mysql anvender ikke tilgængelige ressourer på FreeBSD?
Hej
Jeg har stadig lidt problemer med at få performance op på to FreeBSD
servere ved indlæsning af noget data fra xml-filer til mysql.
Tidligere har kørt det på samme server, men nu har jeg
indlæsningsscriptet på den ene server og mysql på den anden.
Er der nogen hits til hvordan jeg finder flaskehalsen?
1) Båndbredde
Trafikken mellem de to servere er kun på maks 4 MB i sekundet. Jeg kan
snildt overføre 10MB sek ved scp.
2) MySQL database server
Serveren foretager cirka 1000 forespørgsler i sekundet.
Er det ram der mangler i denne server? Hvorfor swap'er den hvis der er
72M ledig?
PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND
27408 mysql 13 96 0 473M 209M ucond 0 19:03 26.07% mysqld
last pid: 27574; load averages: 0.24, 0.22,
0.20
57 processes: 2 running, 55 sleeping
CPU states: 6.8% user, 0.0% nice, 2.6% system, 0.0% interrupt, 90.6%
idle
Mem: 270M Active, 72M Inact, 122M Wired, 22M Cache, 60M Buf, 3652K Free
Swap: 1024M Total, 29M Used, 995M Free, 2% Inuse
Gstat er grøn.
3) Script server
Kører et php script som indlæser nogle store xml filer på cirka 200 MB
stykket.
PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND
2212 root 1 4 0 18352K 9336K sbwait 3 0:18 30.16% php
last pid: 2213; load averages: 0.26, 0.33,
0.35
84 processes: 2 running, 82 sleeping
CPU states: 8.7% user, 0.0% nice, 0.3% system, 0.5% interrupt, 90.5%
idle
Mem: 133M Active, 3037M Inact, 210M Wired, 123M Cache, 112M Buf, 5004K Free
Swap: 4096M Total, 128K Used, 4096M Free
Gstat er grøn.
4) Netstat -m
script server:
258/1212/1470 mbufs in use (current/cache/total)
256/706/962/25600 mbuf clusters in use (current/cache/total/max)
256/620 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)
576K/1715K/2291K bytes allocated to network (current/cache/total)
0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/0/0 requests for jumbo clusters denied (4k/9k/16k)
0/7/6656 sfbufs in use (current/peak/max)
0 requests for sfbufs denied
0 requests for sfbufs delayed
0 requests for I/O initiated by sendfile
1585 calls to protocol drain routines
257/1423/1680 mbufs in use (current/cache/total)
256/1474/1730/16960 mbuf clusters in use (current/cache/total/max)
256/832 mbuf+clusters out of packet secondary zone in use (current/cache)
0/376/376/8480 4k (page size) jumbo clusters in use
(current/cache/total/max)
0/0/0/4240 9k jumbo clusters in use (current/cache/total/max)
0/0/0/2120 16k jumbo clusters in use (current/cache/total/max)
576K/4807K/5384K bytes allocated to network (current/cache/total)
0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/0/0 requests for jumbo clusters denied (4k/9k/16k)
0/7/4496 sfbufs in use (current/peak/max)
0 requests for sfbufs denied
0 requests for sfbufs delayed
0 requests for I/O initiated by sendfile
0 calls to protocol drain routines
Hvad er det mere jeg skal kigge efter?
Vh Morten
This archive was generated by hypermail 2b30 : Fri 31 Oct 2008 - 23:00:02 CET