need a solution
we have 2 node cluster and with version 5.1 we experienced outage and I think it was due to below error messages can someone shed some light on these messages qlc: [ID 630585 kern.info] NOTICE: Qlogic qlc(1): Loop OFFLINE qlc: [ID 630585 kern.info] NOTICE: Qlogic qlc(1): Loop ONLINE fctl: [ID 999315 kern.warning] WARNING: fctl(4): AL_PA=0xe8 doesn't exist in LILP map scsi: [ID 107833 kern.warning] WARNING: /pci@0,600000/pci@0/pci@9/SUNW,qlc@0/fp@0,0/ssd@w203400a0b875f9d9,0 (ssd3): Command failed to complete...Device is gone scsi: [ID 107833 kern.warning] WARNING: /pci@0,600000/pci@0/pci@9/SUNW,qlc@0/fp@0,0/ssd@w203400a0b875f9d9,0 (ssd3): Command failed to complete...Device is gone scsi: [ID 107833 kern.warning] WARNING: /pci@0,600000/pci@0/pci@9/SUNW,qlc@0/fp@0,0/ssd@w203400a0b875f9d9,0 (ssd3): Command failed to complete...Device is gone scsi: [ID 243001 kern.info] /pci@0,600000/pci@0/pci@9/SUNW,qlc@0/fp@0,0 (fcp4): offlining lun=0 (trace=0), target=e8 (trace=2800004) vxdmp: [ID 631182 kern.notice] NOTICE: VxVM vxdmp V-5-0-0 removed disk array 600A0B800075F9D9000000004D2334F5, datype = ST2540- vxdmp: [ID 443116 kern.notice] NOTICE: VxVM vxdmp V-5-0-0 i/o error occured (errno=0x6) on dmpnode 334/0x2c last message repeated 59 times vxdmp: [ID 480808 kern.notice] NOTICE: VxVM vxdmp V-5-0-112 disabled path 118/0x18 belonging to the dmpnode 334/0x28 due to open failure vxdmp: [ID 824220 kern.notice] NOTICE: VxVM vxdmp V-5-0-111 disabled dmpnode 334/0x28 what is this dmpnode 334/0x28 signify, I forget how to map this to device as i only remember is tht its in hexadecimal. Also, what could be the cause of it ... is it due to HBA as issue starts with the message like below qlc: [ID 630585 kern.info] NOTICE: Qlogic qlc(1): Loop OFFLINE qlc: [ID 630585 kern.info] NOTICE: Qlogic qlc(1): Loop ONLINE fctl: [ID 999315 kern.warning] WARNING: fctl(4): AL_PA=0xe8 doesn't exist in LILP map
VMotion vs VCS
We have a slightly complicated question, it is, however, not really that complicated. We are moving one of our money generating apps over to dedicated UCS blades, and in VCS, (Linux on UCS blades with VCS), there is, however, some talk of using VMware and vMotion, and treat this application like other VM's that we have - in the sense, vMotion them in case of failover. This app has Terabytes of data. It is currently running on powerful Solaris systems and will be migrated to Linux on UCS. I sense that VMware is good for small databases and small apps..... My thinking is that changes should occur at higher levels, thereby insulating lower levels, given this logic, for instance, a failover should occur at the VCS level, not below the os....things like, if the os gets corrupted, vMotion will move the corrupted data alongwith. What do you recommend and why?
2-node VCS CFS - du command takes 10x longer on one node!
Hi All, I have setup a 2 node VCS/CFS Cluster. Both nodes are identical HP Blades (460G6 I think), storage is on EMC Symmetrix arrays. Servers are split between data centers and communications is over Sonet Ring with Storage going over DWDM. Both nodes are running RedHat 5u4 64-bit and have identical packages and kernel parameters. Both were built from the same kickstart files. 2 QLogic HBA's are in each blade and DMP is managing the multipathing. Storage is divided into 2 plexes mirrored by VxVM over the data centers. One plex is on an array(s) in each data center. iozone profiling shows I/O rates are pretty identical from both nodes. du -hsc on shared filesystem is the only issue I'm currently seeing. The shared filesystem has 66,000 files in it currently. du on one node takes about 3 minutes, but on the other node takes anywhere from 30-48 minutes. No other activity is occuring. I've tried changing the master, but it doesn't seem to matter. I have strace output if that would help, but my analysis shows that lstat on the slow node is much slower (.001 on ave) so that times 66,000 kind of gets close to the time disparity. Also noted the an lstat immediately following getdent is much, much slower than subsequent lstat commands. Has anyone seen this behavior? Thanks, Danté