mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-20 02:07:40 +07:00
6d69b1f1eb
Using GSO with small MTUs currently results in a substantial throughput
regression - which is caused by how qeth needs to map non-linear skbs
into its IO buffer elements:
compared to a linear skb, each GSO-segmented skb effectively consumes
twice as many buffer elements (ie two instead of one) due to the
additional header-only part. This causes the Output Queue to be
congested with low-utilized IO buffers.
Fix this as follows:
If the MSS is low enough so that a non-SG GSO segmentation produces
order-0 skbs (currently ~3500 byte), opt out from NETIF_F_SG. This is
where we anticipate the biggest savings, since an SG-enabled
GSO segmentation produces skbs that always consume at least two
buffer elements.
Larger MSS values continue to get a SG-enabled GSO segmentation, since
1) the relative overhead of the additional header-only buffer element
becomes less noticeable, and
2) the linearization overhead increases.
With the throughput regression fixed, re-enable NETIF_F_SG by default to
reap the significant CPU savings of GSO.
Fixes:
|
||
|---|---|---|
| .. | ||
| ctcm_dbug.c | ||
| ctcm_dbug.h | ||
| ctcm_fsms.c | ||
| ctcm_fsms.h | ||
| ctcm_main.c | ||
| ctcm_main.h | ||
| ctcm_mpc.c | ||
| ctcm_mpc.h | ||
| ctcm_sysfs.c | ||
| fsm.c | ||
| fsm.h | ||
| Kconfig | ||
| lcs.c | ||
| lcs.h | ||
| Makefile | ||
| netiucv.c | ||
| qeth_core_main.c | ||
| qeth_core_mpc.c | ||
| qeth_core_mpc.h | ||
| qeth_core_sys.c | ||
| qeth_core.h | ||
| qeth_l2_main.c | ||
| qeth_l2_sys.c | ||
| qeth_l2.h | ||
| qeth_l3_main.c | ||
| qeth_l3_sys.c | ||
| qeth_l3.h | ||
| smsgiucv_app.c | ||
| smsgiucv.c | ||
| smsgiucv.h | ||