Messages in this thread | | | From | "Van Maren, Kevin" <> | Subject | RE: The cause of the "VM" performance problem with 2.4.X | Date | Thu, 23 Aug 2001 12:26:40 -0500 |
| |
I did a "mkfs" on a "md" of 3 8-disk "md"s (24 disk md). So no lock contention, and only one "dev" to match, right? [Try to avoid the problem.]
getblk was holding the lru_list_lock lock 86% of the time.
Was averaging about 25,000 blocks/sec to the disks (vmstat), but it was often 200,000 over 2 seconds, then 5 seconds idle, etc. Disk lights didn't come on much (but they all blinked nicely in sync).
I'll try your patch out and run individual disks again.
Kevin - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |