Hi Tachu,
this might be a similar problem to what we experienced. Would you like to give a try to our garbage collector? Ivan 2008. máj. 28, 21:27 DU dátummal Email Lists <[EMAIL PROTECTED]> ezt írta: > I continue to have cant connect issues with php and memcache > connections > > Here is my memcache extension info > > memcache > > memcache support => enabled > Active persistent connections => 0 > Version => 2.2.3 > Revision => $Revision: 1.98 $ > > Directive => Local Value => Master Value > memcache.allow_failover => 1 => 1 > memcache.chunk_size => 8192 => 8192 > memcache.default_port => 11211 => 11211 > memcache.hash_function => fnv => fnv > memcache.hash_strategy => standard => standard > memcache.max_failover_attempts => 20 => 20 > > All my servers run memcache with this info > > stats > STAT pid 10873 > STAT uptime 1025398 > STAT time 1212002320 > STAT version 1.2.4 > STAT pointer_size 32 > STAT rusage_user 4369.616717 > STAT rusage_system 8704.080778 > STAT curr_items 881362 > STAT total_items 107502215 > STAT bytes 469183947 > STAT curr_connections 1763 > STAT total_connections 4640291 > STAT connection_structures 3983 > STAT cmd_get 140951340 > STAT cmd_set 107413099 > STAT get_hits 129967586 > STAT get_misses 10983754 > STAT evictions 809436 > STAT bytes_read 137458144520 > STAT bytes_written 311553302637 > STAT limit_maxbytes 536870912 > STAT threads 4 > > I have a pool of 32 servers. > > For some reason I keep getting constant cant connect error messages > like this > > memcache_pconnect(): Can't connect to 10.200.1.53:1024, Unknown error > (0) > > Its not related to a specific server it will randomly report one as > cant connect. I've checked iptables already its not even running on > the memcache server or the apache server iptables -L > Chain INPUT (policy ACCEPT) > target prot opt source destination > > Chain FORWARD (policy ACCEPT) > target prot opt source destination > > Chain OUTPUT (policy ACCEPT) > target prot opt source destination > I even have unloaded the module from the kernel > > lsmod > Module Size Used by > autofs4 24389 2 > hidp 23105 2 > rfcomm 42457 0 > l2cap 29633 10 hidp,rfcomm > bluetooth 53925 5 hidp,rfcomm,l2cap > sunrpc 144253 1 > ipv6 251393 232 > dm_multipath 21577 0 > raid0 11841 0 > video 19269 0 > sbs 18533 0 > backlight 10049 0 > i2c_ec 9025 1 sbs > button 10705 0 > battery 13637 0 > asus_acpi 19289 0 > ac 9157 0 > lp 15849 0 > floppy 57125 0 > intel_rng 9793 0 > pcspkr 7105 0 > i82875p_edac 10181 0 > serio_raw 10693 0 > edac_mc 24977 1 i82875p_edac > parport_pc 29157 1 > e1000 119505 0 > i2c_i801 11469 0 > parport 37513 2 lp,parport_pc > e100 36809 0 > ide_cd 40033 0 > i2c_core 23745 2 i2c_ec,i2c_i801 > mii 9409 1 e100 > cdrom 36705 1 ide_cd > dm_snapshot 20709 0 > dm_zero 6209 0 > dm_mirror 28741 0 > dm_mod 58201 9 > dm_multipath,dm_snapshot,dm_zero,dm_mirror > ata_piix 18501 0 > libata 115833 1 ata_piix > sd_mod 24897 0 > scsi_mod 132685 2 libata,sd_mod > ext3 123337 2 > jbd 56553 1 ext3 > ehci_hcd 32973 0 > ohci_hcd 23261 0 > uhci_hcd 25421 0 > > If i go to the apache machine and do telnet to memcache machine i can > connect without a problem and run stats or read a key. > > If anyone has any idea as to what causes this please help. > > Some info on the servers > > Linux fl1-9 2.6.18-53.el5 #1 SMP Mon Nov 12 02:22:48 EST 2007 i686 > i686 i386 GNU/Linux > > CentOS release 5 (Final) > > 2 gigs of ram each. allocating 512 megs to memcache. > > they both run apache and memcache on them and are load balanced based > on 1 minute avg load > > typical uptime on machines > load average: 0.54, 0.73, 0.72 > > If you guys need any more information please let me know ill post it > right away > > Thanks > > Tachu > > >
