how to avoid lost trace records?

[Olaf Hering <olaf@aepfle.de>]

Today I inspected the xenalyze and the dump-raw output and noticed that
huge number of lost trace records, even when booted with tbuf_size=200:

grep -wn 1f001 log.sles11_6.xentrace.txt.dump-raw
274438:R p 5 o000000000063ffd4    1f001 4 t0000006d215b3c6b [ b6aed 57fff 9e668fb6 51 ]
274468:R p 3 o00000000006401e8    1f001 4 t0000006e21a1c004 [ b557d 37fff 87924040 51 ]
274554:R p 2 o0000000000640668    1f001 4 t0000006e62629592 [ c7747 40000 b8f5d7ac 4f ]
274562:R p 0 o00000000006406dc    1f001 4 t0000006e63e3415a [ be911 7fff fb77cb80 4a ]
274567:R p 1 o0000000000640728    1f001 4 t0000006e6e45e5d5 [ e624e 0 199d7db0 4b ]
321539:R p 1 o0000000000726128    1f001 4 t0000006e76da7821 [ 2554 0 756c584b 6e ]
329858:R p 1 o000000000074eba8    1f001 4 t0000006e95de2638 [ 289b7 0 781c474a 6e ]
348457:R p 1 o00000000008042a0    1f001 4 t0000006e9c0cea86 [ 15202 0 96ff6f1e 6e ]
352634:R p 7 o000000000082ca74    1f001 4 t0000006ed46cea24 [ b18f0 40000 9efcab44 51 ]
354038:R p 4 o0000000000837df0    1f001 4 t0000006fe86a765f [ c402e 1 86b51960 51 ]
356635:R p 6 o00000000008474e0    1f001 4 t0000007671b75052 [ b69dd 1 9e4272a2 51 ]
356716:R p 1 o0000000000847b80    1f001 4 t000000769dc250ca [ 21f5f 1 9c526d83 6e ]

That means more than 740K lost entries on cpu5,3,2,1,0.
Is this expected?
This is 4.0 with a simple boot into Linux and shut it down again.

My command line was first just '-e all', now its like this and it does
not really reduce the number of lost entries:
xentrace -s 1 -e $(( 0x0010f000 | 0x0001f000 + 1 | 0x0001f000 + 2 | 0x0001f000 + 3 )) $file

Is the tracebuffer handling well debugged?

Olaf