1950 with a PERC 6/i internal (RAID1 2x 136.13Gbyte SAS), PERC 6/e to an MD1000 (RAID5 7x 698.13Gbyte SATA + hot spare), CentOS 5.4, attached as a head-node to a beowulf, serving NFS over gigabit to 17 slaves.
Internal disks ST3146855SS rev S527 External disks ST3750640NS rev 3BKS3BKS All has been fine for some time, but now I'm getting some really strange i/o problems, that I was hoping somebody could advise on. The machine's been trundling on just nicely, with perfectly reasonable performance. Reads are in the 100-140Mbyte/sec for the internal, and 300-360Mbytes/sec for the external. Sequential writes are >100Mbytes/sec on the internal, and >150Mbytes/sec on the external. It's been happy for maybe 6 months. I did update the kernel mid-november to 2.6.18-164.6.1.el5. On friday, it went into a high load average state and was timing out on logins This would last for a couple of minutes. Once that'd passed, nothing was obviously wrong with the machine, no errors in any logs I can find. It's done it again over the weekend, and again today. Load average peaked at >100, so the machine was decidedly unhappy. PERC firmware is 6.2.0-0013, driver is the default CentOS driver 00.00.04.08-RH2. Watching the disk array this morning, it appeared that you'd get a period of normal blinking activity lights, then it'd all go silent for maybe 5 seconds, then solid on for a short while, then back to blinking. This looked odd to me. Pointers as to where I should start looking? jh _______________________________________________ Linux-PowerEdge mailing list [email protected] https://lists.us.dell.com/mailman/listinfo/linux-poweredge Please read the FAQ at http://lists.us.dell.com/faq
