lkml.org 
[lkml]   [1996]   [Jul]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: NCR benchmarking

Alexander,

The current timeout value for sd(s) is 15 seconds.
So it seems that something was broken before you got timeout problems.
I tried some bonnie tests with 2 sec timeout and tagged queue disabled
without any problems (I am very fortunate).

We can assume that it is a software problem directly or indirectly
related to the driver.
So it seems to me interesting to compare our kernel configurations:

If the problem occurs often with tagged queue disabled, and almost
never with tagged queue enabled, we can assume that there is a problem in
the driver code. I need some informations about the frequency of the problem.

The behaviour of bonnie you describe below is a very important information.

Now, I will check the source code, assuming that all I wrote above is true.

The "NCR benchmarking" subject is probably important. If you want all
our mails to be "cc" to the mailing list, it is ok for me. However I
think that only some results will be interesting enough for subscribers.
On the other hand, I would appreciate any help.

Here is the kernel config I used for the tests:
Can you send to me your config?

begin 644 autoconf.h.gz
M'XL("!N2WS$``V%U=&]C;VYF+F@`?5==4^,Z#'W?7^&9?;CL#@MM*86];\9Q
M6D\3)]A.M^Q+)C0&<BE)ITE9^/=7^2@LCLM3.SJR),O2D7+Z_0OZCO"N*IZ2
M*ELEZ_4KNM>YWB:53A%!JR*_R^[_16F1_U,AG685Z)]^.6V.D2+5",[MMEGU
MBM;Z6:]1L:FR(B\;K:^[/-5WB`3<9=.8+D,JF$^YPEYGP"N2-+E=@Y$BW<%/
MN=MLBFWKXBL<S7*]/^T'3N11B8:&59`OJ)`LX-)`YE1PZCF=JVESJ34J=;7;
M6*+SL9K%U(\\K,"6Z9U3U?>,E_%PXINJ(6&UZD>AO)$+%I(^<,6XZZL8!Y$Z
M"%+/[3EO+U=#O42=7TY`O;VUNRXVF]=CQ!QZC)(\147UH+?H=EVL'E&JG[.5
M+FW9OO+FL4,7L>M8HNHPL/GF)USKI(3WTQHYQ6KWI/,JJ>O@-$OU2?52H;MB
MBQ[T>G.:Y7<%*O(Z(I1NLV=M*Y6]BYE3>SD``D*<PYC"X2<GX9E\PO`!!>([
MD_'@T,658"K@O2?9P^+W<#`8&&#MDLQ8**F27<YP"MT$.8*BO&K>P_G[/:RF
MO2`(#T#^H50([!]`EOO>X+KZ4VP?L_S^D_9UF:"_L.<98NB,&'L,2S-;S-8S
M+(S=0/S"PHP6`.@]Q0B6J@]A0E07ZU%6H:Q$97*G454`Z23/\.=!0_7M\JK8
MK1YT^LT2?AT./+HB9@(;0&!ARGD0AS4G^"J*'29)`#1ST[MD"'I26!I^?A5[
M6$S?6P39@@J7A@0#.<Y-V7)TWL^ZQ_B\,RV)9)]Q9X,/+<JH>MUH=)1FY>,Q
MJI*-/D;$^2$"_]MGI"`MI$!FHL5L-+8_9\G3V[GI>X#%DVZC[`@*'>F3^Q.(
M#/VW>]2WQ<NWM_B?=NLJV\#D\")N);+:3EM9,:A8WJG&X;]4F"OY,4GKXL^/
M=J@U1+6U=45S_@+ZW<6R5[D-B&=X>#XRW_D=&H\.01=CDT5:B)&+Y=)NT%E@
M#K/&AC$^ZM-2>\H_/R,_+\8V["J27C!EQ(8YBIR-+JTF*=3Q(7GL^(>QD`4V
MS(U4)&CL!#YFW*8PI1R6"Q)S(L[/[#$U$!D/)E;O+7KQ\F*MD!:]7"Y[C/81
MCA6>3JD37T<T,J>/H<G@+F%(32(TM("%&O+AG!)K>;VK`K$2&F-YPZ&I`AY$
MUC(P]6MUH).I->UA:,U5B.5P8@.NFUJ)76QUW:%,FE3;H)+B*5;6I*GAZ-(F
MCX;C^&SL6B%/"1@E@?@XXCI*^8PL@5J!D!BQ[)I.Y/N]$=`(N_6T=X)>1S`<
M?U-AR$./A;W%,0S?^(>0$%;OI\U6EV6Q+9OUJ<:3K8;E"7;TVUVVKE!2=IMS
M>6+CIL9);UH+[-1-UKMU3-6LWBK[4[L&%Y0[@8C/2&"N$Q[FQ'RVOTY(WR2/
M&F32K*PF`KLX#,B<FM6OS)QB04"Y2R"3#H=7OBU?RTH_V48O*.R3W8R\/<FC
MH[QH]]5F",`O[&ZGP$TAZQ96VWI!G+I50;,^M%^^,WB8QK]M<EQ'08\C/;@H
M?%=P!T/E]BK-9YQ!V_;KDBX5B$UUD(YLVDN&+=HN5IVRX50Z@;296;0G#&FT
MU^]5MPB(S0QW9=^*]*\L)I@,?DXF`YN566@U`U]=EA!;U>[M'Y)MLJK@F^B3
MKR$)HP5[?3I@4V:6P0WQ,!2!&0AL=8Y8&%)1$[MO,ELH&%<]PO"!SLTFBWPP
M8%85(X-1;/GV<2TR')J]_`LK,G."J1FI(F_+&0`VK@DBOO^<F.MM#DO30[*J
4/RDLRE`++O/HE_\!R>JFZGT0``""
`
end
-------------------------------------------------------------

On Sun, 7 Jul 1996, Alexander Sanda wrote:

> On Sun, 7 Jul 1996, Gerard Roudier wrote:
>
> Allright, I just finished re-testing, here are the results:
>
> 53c7,8xx: 10MHz FAST SCSI-2, disconnect enabled
>
> -------Sequential Output-------- ---Sequential Input-- --Random--
> -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
> Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
> 53C7xx 210 3628 67.6 3404 19.6 1549 17.4 3362 53.9 3819 18.1 33.7 1.9
>
>
> 53C8xx: 10MHz, disconnect enabled, TQ4 (see note below)
>
> -------Sequential Output-------- ---Sequential Input-- --Random--
> -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
> Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
> 53C8xx 210 3529 69.7 3328 20.8 1481 17.7 3150 51.6 3559 16.4 36.9 2.2
>
>
> I tried to re-test the 53C8xx driver with tagged queuing set to 0, but
> unfortunately, Bonnie crashed during the test. I was able to switch VC,
> but couldn't kill the Bonnie task, which was consuming 99.9% CPU and
> totally hung.
>
> I browsed my kernel-log and found the following:
>
>
> kernel: scsi : aborting command due to timeout : pid 1876, scsi0, channel 0, id 0, lun 0 0x0a 06 62 df 46 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 1979, scsi0, channel 0, id 0, lun 0 0x0a 06 af 07 f4 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 1980, scsi0, channel 0, id 0, lun 0 0x0a 06 af fb f4 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 1876, scsi0, channel 0, id 0, lun 0 0x0a 06 62 df 46 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 1979, scsi0, channel 0, id 0, lun 0 0x0a 06 af 07 f4 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 1980, scsi0, channel 0, id 0, lun 0 0x0a 06 af fb f4 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi0 channel 0 : resetting for second half of retries.
> kernel: SCSI bus is being reset for host 0 channel 0.
> kernel: ncr53c810-0: restart (scsi bus reset).
> kernel: ncr53c810-0-<target 0, lun 0>: FAST SCSI-2 100ns (10 Mb/sec) offset 8.
> kernel: scsi : aborting command due to timeout : pid 3393, scsi0, channel 0, id 0, lun 0 0x08 09 d3 63 02 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 1876, scsi0, channel 0, id 0, lun 0 0x0a 06 62 df 46 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 1876, scsi0, channel 0, id 0, lun 0 0x0a 06 62 df 46 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 4203, scsi0, channel 0, id 0, lun 0 0x08 09 68 cb 02 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 4203, scsi0, channel 0, id 0, lun 0 0x08 09 68 cb 02 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi0 channel 0 : resetting for second half of retries.
> kernel: SCSI bus is being reset for host 0 channel 0.
> kernel: ncr53c810-0: restart (scsi bus reset).
> kernel: ncr53c810-0-<target 0, lun 0>: FAST SCSI-2 100ns (10 Mb/sec) offset 8.
> kernel: scsi : aborting command due to timeout : pid 4260, scsi0, channel 0, id 0, lun 0 0x08 04 b8 f9 02 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 4407, scsi0, channel 0, id 0, lun 0 0x08 09 d3 63 02 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 4444, scsi0, channel 0, id 0, lun 0 0x08 09 d7 d5 02 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 4515, scsi0, channel 0, id 0, lun 0 0x08 05 13 45 02 00
> kernel: ncr53c8xx_abort : abort call
> kernel: scsi : aborting command due to timeout : pid 4518, scsi0, channel 0, id 0, lun 0 0x0a 04 f2 35 02 00
> kernel: ncr53c8xx_abort : abort call
>
> [continued with some more lines like the above]
>
>
> # /AS/ powered by #
> # http://www.ping.at/members/alexa/ Linux 2.0 #
> -----------------------------------------------------------------------

Gerard.


\
 
 \ /
  Last update: 2005-03-22 13:38    [W:6.889 / U:0.020 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site