[squid-users] Re: [SQU]

From: Henrik Nordstrom <hno@dont-contact.us>
Date: Wed, 14 Mar 2001 22:46:05 +0100

Your kernel probably ran out of free memory pages. This can happen when
there is a high I/O load on the system.

async-io pushes the disk I/O harder

reiserfs is more memory intensive than ext2.

What you can try is to raise the freelist sizes in
/proc/sys/vm/freepages (see the kernel documentation for an explanation
of the values).

--
Henrik Nordstrom
Squid Hacker
Hamid Hashemi Golpayegani wrote:
> 
> Hi ,
> 
> I have upgrade my Squid to squid-2.4.pre1 and change the mode to async ufs
> mode and change the file system from ext2 to reiserfs on redhat 6.2 with
> 2.2.18 kernel . So I have got this errors in cache.log and my squid died .
> Is there any missconfiguration exist ?
> what everyone think that I must to change to fix this problem for future if
> happen ?
> 
> 2001/03/08 14:37:55| comm_accept: FD 9: (105) No buffer space available
> 2001/03/08 14:37:55| httpAccept: FD 9: accept failure: (105) No buffer space
> available
> 2001/03/08 14:37:55| comm_accept: FD 9: (105) No buffer space available
> 2001/03/08 14:37:55| httpAccept: FD 9: accept failure: (105) No buffer space
> available
> 2001/03/08 14:37:55| comm_accept: FD 9: (105) No buffer space available
> 2001/03/08 14:37:55| httpAccept: FD 9: accept failure: (105) No buffer space
> available
> .
> .
> .
> 2001/03/08 14:39:56| comm_poll: poll failure: (12) Cannot allocate memory
> 2001/03/08 14:39:56| Select loop Error. Retry 1
> 2001/03/08 14:39:56| comm_poll: poll failure: (12) Cannot allocate memory
> 2001/03/08 14:39:56| Select loop Error. Retry 2
> 2001/03/08 14:39:56| comm_poll: poll failure: (12) Cannot allocate memory
> 2001/03/08 14:39:56| Select loop Error. Retry 3
> 2001/03/08 14:39:56| comm_poll: poll failure: (12) Cannot allocate memory
> 2001/03/08 14:39:56| Select loop Error. Retry 4
> FATAL: Select Loop failed!
> Squid Cache (Version 2.4.PRE-STABLE): Terminated abnormally.
> CPU Usage: 17316.350 seconds = 6569.830 user + 10746.520 sys
> Maximum Resident Size: 0 KB
> Page faults with physical i/o: 9636
> Memory usage for squid via mallinfo():
>         total space in arena:  166177 KB
>         Ordinary blocks:       165927 KB   2623 blks
>         Small blocks:               0 KB      0 blks
>         Holding blocks:          3416 KB      3 blks
>         Free Small blocks:          0 KB
>         Free Ordinary blocks:     249 KB
>         Total in use:          169343 KB 102%
>         Total free:               249 KB 0%
> 2001/03/08 14:39:56| storeDirWriteCleanLogs: Starting...
> 2001/03/08 14:39:56| WARNING: Closing open FD    9
> 2001/03/08 14:39:56|     65536 entries written so far.
> 2001/03/08 14:39:56|    131072 entries written so far.
> 2001/03/08 14:39:56|    196608 entries written so far.
> 2001/03/08 14:39:56|    262144 entries written so far.
> 2001/03/08 14:39:57|    327680 entries written so far.
> 2001/03/08 14:39:59|    393216 entries written so far.
> 2001/03/08 14:40:00|    458752 entries written so far.
> 2001/03/08 14:40:02|    524288 entries written so far.
> 2001/03/08 14:40:05|    589824 entries written so far.
> 2001/03/08 14:40:07|    655360 entries written so far.
> 2001/03/08 14:40:07|    720896 entries written so far.
> 2001/03/08 14:40:10|   Finished.  Wrote 776530 entries.
> 2001/03/08 14:40:10|   Took 14.5 seconds (53375.5 entries/sec).
> 
> --
> Regards
> 
>     ============================================================
>    /  Seyyed Hamid Reza    /        WINDOWS FOR NOW  !!            /
>   /  Hashemi Golpayegani  /  Linux for future , FreeBSD for ever  /
>  /    Morva System Co.   / ------------------------------------- /
> /  Network Administrator/ hamid@morva.net   ,   ICQ# : 42209876 /
> ===========================================================
> 
> --
> To unsubscribe, see http://www.squid-cache.org/mailing-lists.html
Received on Wed Mar 14 2001 - 14:44:33 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:58:38 MST