Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.os.linux.hardware > #3062
| From | Mike Spencer <mds@bogus.nodomain.nowhere> |
|---|---|
| Newsgroups | comp.os.linux.hardware |
| Subject | SATA->IDE emulation on IBM P4 bogs down on HD writes |
| Date | 2016-05-19 20:23 -0300 |
| Organization | Bridgewater Institute for Advanced Study - Blacksmith Shop |
| Message-ID | <87a8jl7htw.fsf@bogus.nodomain.nowhere> (permalink) |
This probably isn't a hardware matter per se but maybe a hardware wizard here will have a solution. IBM P4 desktop came with an IDE HD. HD failed. Mobo has two plugs labeled "SATA IDE n" where n is "1" and "2". Plugging a SATA drive into one of those (suitable cable and power adapter) results in the SATA drive being seen by Linux as hda. (?!) It works just fine in every respect except one: Large writes to the HD, e.g. cp bigfile-from-foo /dir/on/HD, runs as expected for a few seconds, then the system bogs down. X cursor gets jerky, key strokes may take a minute to elicit visible response. Copy proceeds at an acceptable speed but the box is unusable until the copy is finished and sync'd. This happens for any foo from which bigfile is copied -- USB thumb drive, HD mounted over USB or another partition on the HD. Does *not* happen with no HD writes, viz. cp /dir/on/HD/bigfile /mnt/usb/other-media or cp /mnt/usb/thumb/bigfile /mnt/usb2/other-thumb. I've tried various things -- tweaking bits in /proc/... according to Documentation/sysctl/vm.txt, runnning mbuffer. Looks (to me; but what do I know?) like RAM is filling up with reads and stays filled up until writes to HD are completed. Aynone know about this? Using SLackware 11 with 2.4.33 kernel. A (much) newer kernel might very well fix it. I need to continue with the 2.4 kernel on this box. -- Mike Spencer Nova Scotia, Canada
Back to comp.os.linux.hardware | Previous | Next — Next in thread | Find similar | Unroll thread
SATA->IDE emulation on IBM P4 bogs down on HD writes Mike Spencer <mds@bogus.nodomain.nowhere> - 2016-05-19 20:23 -0300
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Bobbie Sellers <bliss-sf4ever@dslextreme.com> - 2016-05-19 16:32 -0700
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Mike Spencer <mds@bogus.nodomain.nowhere> - 2016-05-20 12:28 -0300
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Bobbie Sellers <bliss-sf4ever@dslextreme.com> - 2016-05-20 09:10 -0700
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Pascal Hambourg <boite-a-spam@plouf.fr.eu.org> - 2016-05-22 11:37 +0200
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes "Carlos E.R." <robin_listas@invalid.es> - 2016-05-24 21:52 +0200
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Mike Spencer <mds@bogus.nodomain.nowhere> - 2016-05-28 04:07 -0300
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Henrik Carlqvist <Henrik.Carlqvist@deadspam.com> - 2016-05-28 11:09 +0000
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes "Carlos E.R." <robin_listas@invalid.es> - 2016-05-28 17:12 +0200
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Mike Spencer <mds@bogus.nodomain.nowhere> - 2016-05-29 01:50 -0300
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes ANTant@zimage.com (Ant) - 2016-05-29 11:41 -0500
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Mike Spencer <mds@bogus.nodomain.nowhere> - 2016-05-29 02:41 -0300
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes "Carlos E.R." <robin_listas@invalid.es> - 2016-05-29 14:06 +0200
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes ANTant@zimage.com (Ant) - 2016-05-29 11:42 -0500
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes "Carlos E.R." <robin_listas@invalid.es> - 2016-05-29 21:09 +0200
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Aragorn <thorongil@telenet.be.invalid> - 2016-05-30 10:57 +0200
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes "Carlos E.R." <robin_listas@invalid.es> - 2016-05-30 14:21 +0200
Re: SATA->IDE emulation on IBM P4 bogs down on HD writes Aragorn <thorongil@telenet.be.invalid> - 2016-05-30 15:49 +0200
csiph-web