Re: i/o benchmarks on 2.5.70* kernels

rwhron@earthlink.net
Tue, 17 Jun 2003 07:14:00 -0400


> tiobench on SMP results are not very good, lots of
> fragmentation, the random IO throughput drops is
> probably due to AS strangling TCQ though. You are
> using SMP and TCQ, right?

SMP yes. The non-benchmarked disks (which don't matter
say this at boot time:

scsi0:A:1:0: Tagged Queuing enabled. Depth 4
(aic7xxx)

These config options on the non-benchmarked disks:
CONFIG_AIC7XXX_CMDS_PER_DEVICE=4
CONFIG_AIC7XXX_RESET_DELAY_MS=15000
CONFIG_AIC7XXX_DEBUG_ENABLE=y
CONFIG_AIC7XXX_DEBUG_MASK=0
CONFIG_AIC7XXX_REG_PRETTY_PRINT=y

----

The benchmarked disks are on scsi3 and scsi4.
The benchmarked disks do not tell what TCQ they have.

CONFIG_SCSI_QLOGIC_ISP=y
CONFIG_SCSI_QLOGIC_FC=y
CONFIG_SCSI_QLOGIC_FC_FIRMWARE=y

TCQ on the benchmarked disks may be 1024...
+#define MAXISPREQUEST(isp) ((IS_FC(isp) || IS_ULTRA2(isp))? 1024 : 256)

but that's just a guess.

-- 
Randy Hron
http://home.earthlink.net/~rwhron/kernel/bigbox.html

- 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/