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.htmlReceived 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