Hi,all:
Our squid box's performance is not very good(40000 reqs/min), cpu
load is very high, and the traffic can't great bigger than
100MBits/s.(Gbits/s network).
We use aufs scheme now.We have a test for coss, and the result is
not very good also(cpu overload also).
can we optimize continue?Is the best performace that our hardware
can achived?where is the bottle-neck?
what is the best performance of your box?
there are some infomations:
++++++ hardware:
cpu: Xeon 1.8G(Hyper-Threading)
os: RHAS 4.3
file discriptor num: 32768
mem: 2G
disk: OS: 17G(scsi) for OS,
cache:73G(SCSI,10000rpm for cache data)
++++++ squid.conf
about 100 ACLs
cache_mem 1500 MB
cache_dir coss /dev/sdb1 50000 max-size=10000000 block-size=8192
(some server use aufs: cache_dir aufs /cache/cache 50000 240 256,
and sdb1 is mounted with options of async and noatime)
++++++ top:
top - 11:37:46 up 42 days, 12:00, 1 user, load average: 1.00, 0.99, 0.91
Tasks: 54 total, 3 running, 51 sleeping, 0 stopped, 0 zombie
Cpu(s): 41.8% us, 8.3% sy, 0.0% ni, 47.9% id, 1.3% wa, 0.7% hi, 0.0% si
Mem: 2074980k total, 1979160k used, 95820k free, 686568k buffers
Swap: 4192956k total, 3404k used, 4189552k free, 355632k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
3738 squid 25 0 918m 714m 2104 R 99.9 35.3 63:59.56 squid
3901 root 16 0 3664 912 740 R 0.3 0.0 0:00.04 top
1 root 16 0 3312 236 208 S 0.0 0.0 0:04.01 init
++++++ mgr:info
Squid Object Cache: Version 2.6.STABLE12
Start Time: Thu, 22 Mar 2007 02:34:09 GMT
Current Time: Thu, 22 Mar 2007 03:21:32 GMT
Connection information for squid:
Number of clients accessing cache: 9967
Number of HTTP requests received: 1705959
Number of ICP messages received: 0
Number of ICP messages sent: 0
Number of queued ICP replies: 0
Request failure ratio: 0.00
Average HTTP requests per minute since start: 36012.7
Average ICP messages per minute since start: 0.0
Select loop called: 1805771 times, 1.574 ms avg
Cache information for squid:
Request Hit Ratios: 5min: 97.9%, 60min: 97.6%
Byte Hit Ratios: 5min: 83.9%, 60min: 78.7%
Request Memory Hit Ratios: 5min: 9.6%, 60min: 18.2%
Request Disk Hit Ratios: 5min: 16.3%, 60min: 7.5%
Storage Swap size: 240512 KB
Storage Mem size: 241140 KB
Mean Object Size: 26.95 KB
Requests given to unlinkd: 0
Median Service Times (seconds) 5 min 60 min:
HTTP Requests (All): 0.00919 0.00562
Cache Misses: 0.09736 0.10281
Cache Hits: 0.00919 0.00562
Near Hits: 0.06640 0.05331
Not-Modified Replies: 0.00865 0.00463
DNS Lookups: 0.03868 0.06364
ICP Queries: 0.00000 0.00000
Resource usage for squid:
UP Time: 2842.262 seconds
CPU Time: 2911.327 seconds
CPU Usage: 102.43%
CPU Usage, 5 minute avg: 87.11%
CPU Usage, 60 minute avg: 102.57%
Process Data Segment Size via sbrk(): 378764 KB
Maximum Resident Size: 0 KB
Page faults with physical i/o: 0
Memory usage for squid via mallinfo():
Total space in arena: 378764 KB
Ordinary blocks: 297942 KB 10127 blks
Small blocks: 0 KB 0 blks
Holding blocks: 401944 KB 6 blks
Free Small blocks: 0 KB
Free Ordinary blocks: 80821 KB
Total in use: 699886 KB 90%
Total free: 80821 KB 10%
Total size: 780708 KB
Memory accounted for:
Total accounted: 552999 KB
memPoolAlloc calls: 147261049
memPoolFree calls: 147041272
File descriptor usage for squid:
Maximum number of file descriptors: 32768
Largest file desc currently in use: 6319
Number of file desc currently in use: 5784
Files queued for open: 0
Available number of file descriptors: 26984
Reserved number of file descriptors: 100
Store Disk files open: 0
IO loop method: epoll
Internal Data Structures:
8976 StoreEntries
4571 StoreEntries with MemObjects
4537 Hot Object Cache Items
8924 on-disk objects
-- Best regards Felix NewReceived on Wed Mar 21 2007 - 21:49:57 MDT
This archive was generated by hypermail pre-2.1.9 : Sat Mar 31 2007 - 13:00:02 MDT