RE: [squid-users] slower connections using squid (squid is slowing down all connections)

> -----Original Message-----
> From: Alex [mailto:linuxro@online.ie]
> Sent: Thursday, September 22, 2005 10:26 PM
> To: squid-users@squid-cache.org
> Subject: Re: [squid-users] slower connections using squid (squid is
> slowing down all connections)
>
>
> Hi Chris,
>
> > > Also, i have:
> > > Last 5 minutes:
> > > client_http.requests = 2.723098/sec
> > > client_http.hits = 0.779933/sec
> >
> > Well, the box is not being stressed... What is the output
> of "hdparm -t
> > /dev/sda" (I think SATA shows up as SCSI in linux)?
>
> # cat /proc/partitions
> major minor #blocks name
>
> 8 0 120059840 sda
> 8 1 104391 sda1
> 8 2 1 sda2
> 8 5 2008093 sda5
> 8 6 117941166 sda6
>
> # hdparm -t /dev/sda
>
> /dev/sda:
> Timing buffered disk reads: 170 MB in 3.03 seconds = 56.15 MB/sec
> [root@ns1 ~]# hdparm -tT /dev/sda
>
> # hdparm -tT /dev/sda
>
> /dev/sda:
> Timing cached reads: 3792 MB in 2.00 seconds = 1896.29 MB/sec
> Timing buffered disk reads: 156 MB in 3.02 seconds = 51.73 MB/sec
> [root@ns1 ~]#
>
> I am using 2 sata HDD drives mounted in RAID1 hardware
> controller (3ware - 2
> ports)
>
> Timings above are ok or not?

They look okay to me...

>
> > If I set the BIOS to
> > use the SATA drives in "Enhanced" (both SATA and PATA
> drives are available)
> > or "SATA Only", I get very poor performance. Only if I set them as
> > "Combined" (the SATA drives "act" like a PATA channel) do I
> get decent
> > performance.
> >
> I can't access BIOS settings now (require to stop our
> services)... Only
> tonight, when our network will be free... I will do it only
> if speed above is
> poor ....

I no longer think this could be causing your problem.

>
> > I see nothing in here that would be causing the horrid
> performance that you
> > are reporting. What do the Median Service Times (under the
> General Runtime
> > Info) look like?
>
> I increased cache_mem from 32 MB to 256MB and nothing seems
> to change my
> life ... as you said, the box is not being stressed
> anyway.... Now, I have
> only 138 clients accessing cache and squid is working worse
> then a dial-up
> connection. Here comes General Runtime Info including Median
> Service Times
> too...
>
> Connection information for squid:
> Number of clients accessing cache: 135
> Number of HTTP requests received: 82681
> 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: 62.4
> Average ICP messages per minute since start: 0.0
> Select loop called: 22219278 times, 3.579 ms avg
> Cache information for squid:
> Request Hit Ratios: 5min: 34.3%, 60min: 38.8%
> Byte Hit Ratios: 5min: 4.4%, 60min: 24.5%
> Request Memory Hit Ratios: 5min: 1.0%, 60min: 5.9%
> Request Disk Hit Ratios: 5min: 39.3%, 60min: 32.4%
> Storage Swap size: 4053340 KB
> Storage Mem size: 43480 KB
> Mean Object Size: 17.73 KB
> Requests given to unlinkd: 0
> Median Service Times (seconds) 5 min 60 min:
> HTTP Requests (All): 0.01955 0.02317
> Cache Misses: 0.44492 0.35832
> Cache Hits: 0.00865 0.01035
> Near Hits: 0.28853 0.22004
> Not-Modified Replies: 0.01164 0.01035
> DNS Lookups: 0.08717 0.16304
> ICP Queries: 0.00000 0.00000

Okay... These look pretty good. Hits are fast, misses are okay, DNS requests are about what I would expect... I'm a bit perplexed. What are the symptoms of slow connections? Is it throughput on large downloads, pages with lots of connections (msn.com with it's thousands of images), does it just take forever for a connection to get started, or is it something else entirely?

> Resource usage for squid:
> UP Time: 79515.851 seconds
> CPU Time: 387.250 seconds
> CPU Usage: 0.49%
> CPU Usage, 5 minute avg: 0.24%
> CPU Usage, 60 minute avg: 0.17%
> Process Data Segment Size via sbrk(): 79920 KB
> Maximum Resident Size: 0 KB
> Page faults with physical i/o: 0
> Memory usage for squid via mallinfo():
> Total space in arena: 79920 KB
> Ordinary blocks: 79544 KB 3201 blks
> Small blocks: 0 KB 0 blks
> Holding blocks: 1784 KB 3 blks
> Free Small blocks: 0 KB
> Free Ordinary blocks: 375 KB
> Total in use: 81328 KB 100%
> Total free: 375 KB 0%
> Total size: 81704 KB
> Memory accounted for:
> Total accounted: 65164 KB
> memPoolAlloc calls: 11051188
> memPoolFree calls: 10437330
> File descriptor usage for squid:
> Maximum number of file descriptors: 1024
> Largest file desc currently in use: 140
> Number of file desc currently in use: 130
> Files queued for open: 0
> Available number of file descriptors: 894
> Reserved number of file descriptors: 100
> Store Disk files open: 0
> Internal Data Structures:
> 228996 StoreEntries
> 6823 StoreEntries with MemObjects
> 6819 Hot Object Cache Items
> 228639 on-disk objects
>
>
> Alex
>

Chris
Received on Fri Sep 23 2005 - 17:13:53 MDT