[squid-users] AUFS vs. DISKS
Yuri Voinov
yvoinov at gmail.com
Wed Jul 15 13:26:33 UTC 2015
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA256
Here is my stats:
client_http.all_median_svc_time = 0.097357 seconds
client_http.miss_median_svc_time = 0.097357 seconds
client_http.nm_median_svc_time = 0.000000 seconds
client_http.nh_median_svc_time = 0.000000 seconds
client_http.hit_median_svc_time = 0.000000 seconds
icp.query_median_svc_time = 0.000000 seconds
icp.reply_median_svc_time = 0.000000 seconds
dns.median_svc_time = 0.000000 seconds
client_http.all_median_svc_time = 0.102812 seconds
client_http.miss_median_svc_time = 0.108570 seconds
client_http.nm_median_svc_time = 0.000000 seconds
client_http.nh_median_svc_time = 0.127833 seconds
client_http.hit_median_svc_time = 0.000000 seconds
icp.query_median_svc_time = 0.000000 seconds
icp.reply_median_svc_time = 0.000000 seconds
dns.median_svc_time = 0.000000 seconds
client_http.all_median_svc_time = 0.102812 seconds
client_http.miss_median_svc_time = 0.108570 seconds
client_http.nm_median_svc_time = 0.000911 seconds
client_http.nh_median_svc_time = 0.127833 seconds
client_http.hit_median_svc_time = 0.010350 seconds
icp.query_median_svc_time = 0.000000 seconds
icp.reply_median_svc_time = 0.000000 seconds
dns.median_svc_time = 0.000000 seconds
Diskd:
sent_count: 103224
recv_count: 103224
max_away: 129
max_shmuse: 129
open_fail_queue_len: 0
block_queue_len: 15478
OPS SUCCESS FAIL
open 4180 4180 0
create 4057 4057 0
close 8237 8237 0
unlink 737 737 0
read 16741 16741 0
write 69272 69272 0
You has too long queue, so this indicates bottleneck in IO. Need to find
and resolve.
15.07.15 19:18, FredB пишет:
>
>>
>> Did you check the TCP_HIT response times with the Diskd ?
>
> Yes
>
> 192.x.x.x - fred [15/Jul/2015:14:30:27 +0200] "GET
http://ec.ccm2.net/www.commentcamarche.net/download/files/youtube_downloader_hd_setup-2.9.9.23.exe
HTTP/1.0" 200 10096376 TCP_HIT:HIER_NONE "Wget/1.13.4 (linux-gnu)"
> 192.x.x.x - fred [15/Jul/2015:14:30:31 +0200] "GET
http://ec.ccm2.net/www.commentcamarche.net/download/files/youtube_downloader_hd_setup-2.9.9.23.exe
HTTP/1.0" 200 10096376 TCP_HIT:HIER_NONE "Wget/1.13.4 (linux-gnu)"
> 192.x.x.x - fred [15/Jul/2015:14:36:56 +0200] "GET
http://ec.ccm2.net/www.commentcamarche.net/download/files/youtube_downloader_hd_setup-2.9.9.23.exe
HTTP/1.0" 200 10096376 TCP_HIT:HIER_NONE "Wget/1.13.4 (linux-gnu)"
>
>
>> During our tests, we have seen than it's sometime better to download
>> the
>> object from internet again instead using the one from the cache, we
>> got
>> better response times...
>>
>
> Now I can't tell because I have a lot of bandwidth free (hundreds),
but a request from squid cache to user is fast
> Something between 6 and 10 M/s (En Français 6 and 10 MO -> 32 and 80
mbits) and I'm not sure than my lan network is unused ...
>
> So with hundreds of concurrent users I think that there is no special
problem.
>
> FI more informations: username_cache tells me 4612 users
>
> Diskd stats
>
> squidclient -p 8080 mgr:diskd
>
> sent_count: 23105099
> recv_count: 23105042
> max_away: 143
> max_shmuse: 141
> open_fail_queue_len: 40114
> block_queue_len: 629596120
>
> OPS SUCCESS FAIL
> open 2192154 2192133 4
> create 1284546 1284546 0
> close 3476648 3476630 4
> unlink 981134 981131 2
> read 6541304 6541279 0
> write 8629313 8629313 0
>
>
> Last five minutes:
>
> squidclient -p 8080 mgr:5min
>
>
> sample_start_time = 1436965191.905545 (Wed, 15 Jul 2015 12:59:51 GMT)
> sample_end_time = 1436965491.907754 (Wed, 15 Jul 2015 13:04:51 GMT)
> client_http.requests = 334.370871/sec
> client_http.hits = 114.399158/sec
> client_http.errors = 22.943164/sec
> client_http.kbytes_in = 2948.928286/sec
> client_http.kbytes_out = 6090.041824/sec
> client_http.all_median_svc_time = 0.050460 seconds
> client_http.miss_median_svc_time = 0.177113 seconds
> client_http.nm_median_svc_time = 0.000911 seconds
> client_http.nh_median_svc_time = 0.038286 seconds
> client_http.hit_median_svc_time = 0.007665 seconds
> server.all.requests = 237.598250/sec
> server.all.errors = 0.000000/sec
> server.all.kbytes_in = 5110.549036/sec
> server.all.kbytes_out = 2765.982966/sec
> server.http.requests = 185.981964/sec
> server.http.errors = 0.000000/sec
> server.http.kbytes_in = 1963.482209/sec
> server.http.kbytes_out = 162.952133/sec
> server.ftp.requests = 0.000000/sec
> server.ftp.errors = 0.000000/sec
> server.ftp.kbytes_in = 0.000000/sec
> server.ftp.kbytes_out = 0.000000/sec
> server.other.requests = 51.616287/sec
> server.other.errors = 0.000000/sec
> server.other.kbytes_in = 3147.070160/sec
> server.other.kbytes_out = 2603.030833/sec
> icp.pkts_sent = 0.000000/sec
> icp.pkts_recv = 0.000000/sec
> icp.queries_sent = 0.000000/sec
> icp.replies_sent = 0.000000/sec
> icp.queries_recv = 0.000000/sec
> icp.replies_recv = 0.000000/sec
> icp.replies_queued = 0.000000/sec
> icp.query_timeouts = 0.000000/sec
> icp.kbytes_sent = 0.000000/sec
> icp.kbytes_recv = 0.000000/sec
> icp.q_kbytes_sent = 0.000000/sec
> icp.r_kbytes_sent = 0.000000/sec
> icp.q_kbytes_recv = 0.000000/sec
> icp.r_kbytes_recv = 0.000000/sec
> icp.query_median_svc_time = 0.000000 seconds
> icp.reply_median_svc_time = 0.000000 seconds
> dns.median_svc_time = 0.005733 seconds
> unlink.requests = 2.859979/sec
> page_faults = 0.010000/sec
> select_loops = 6428.069335/sec
> select_fds = 7919.858350/sec
> average_select_fd_period = 0.000000/fd
> median_select_fds = 0.000000
> swap.outs = 62.482873/sec
> swap.ins = 129.082383/sec
> swap.files_cleaned = 0.000000/sec
> aborted_requests = 14.339894/sec
> syscalls.disk.opens = 192.085252/sec
> syscalls.disk.closes = 192.045253/sec
> syscalls.disk.reads = 376.233896/sec
> syscalls.disk.writes = 499.342990/sec
> syscalls.disk.seeks = 0.000000/sec
> syscalls.disk.unlinks = 57.879574/sec
> syscalls.sock.accepts = 243.548207/sec
> syscalls.sock.sockets = 131.322366/sec
> syscalls.sock.connects = 131.322366/sec
> syscalls.sock.binds = 0.000000/sec
> syscalls.sock.closes = 377.267222/sec
> syscalls.sock.reads = 3535.117303/sec
> syscalls.sock.writes = 3999.197219/sec
> syscalls.sock.recvfroms = 21.509842/sec
> syscalls.sock.sendtos = 10.876587/sec
> cpu_time = 170.718669 seconds
> wall_time = 300.002209 seconds
> cpu_usage = 56.905804%
>
> _______________________________________________
> squid-users mailing list
> squid-users at lists.squid-cache.org
> http://lists.squid-cache.org/listinfo/squid-users
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2
iQEcBAEBCAAGBQJVpl+JAAoJENNXIZxhPexGk2IH/1zGNmtNl9xvTRjoyS2T2Js2
Xl7k4jU4n/63hSWki8FbZ8vdcDaiErZKx2SwrYhGW144Xp2ldShnEi9O0vpt5NIa
3gT/J3xO8+GQTqnUa58BwFag+ROlvuvUYSqcJIMJ7O5bcPCOgYP+dZC1sEcGATQS
avq5F1NjmCn3f+Xk+lQP1xXipCI1gPYkvNXUbCkM0JODYsdGe2AdMoJ5fGQ397np
SpmSvkXdQxqL720qgtuFgjIH/xXomMsW9MPusDDUos2IMvMtz1m8OtZu1sK4J9SW
F5oAJowK7Y1Bd2L+DWKcwcXXdmpSuPuiUS9YLSEP+IJyAoKQceCC+O23UuHwu0A=
=NtRA
-----END PGP SIGNATURE-----
More information about the squid-users
mailing list