Lines Matching refs:throughput
14 throughput high).
17 throughput. So, when needed for achieving a lower latency, BFQ builds
18 schedules that may lead to a lower throughput. If your main or only
20 throughput at all times, then do switch off all low-latency heuristics
23 latency and throughput, or on how to maximize throughput.
31 instrumentation, and using the throughput-sync.sh script of the S
50 support is enabled), then the sustainable throughput with BFQ
117 High throughput
120 On hard disks, BFQ achieves up to 30% higher throughput than CFQ, and
121 up to 150% higher throughput than DEADLINE and NOOP, with all the
124 instead, about the same throughput as the other schedulers.
129 BFQ distributes the device throughput, and not just the device time,
135 applications that would otherwise cause a throughput loss.
179 throughput.
186 throughput on rotational devices and on non-queueing flash-based
189 guaranteeing the desired throughput fraction to processes
196 guarantees the expected throughput distribution without ever
202 for throughput. So, with these devices, BFQ performs idling
205 throughput may be sub-optimal. No solution currently exists to
206 provide both strong service guarantees and optimal throughput
215 throughput. For brevity, we call just "weight-raising" the whole
224 from a high throughput. Examples are systemd during boot, or git
232 that it enables BFQ to achieve a high throughput, by queue
234 mechanism, preemption, to get a high throughput. As such EQM is a
235 unified mechanism to achieve a high throughput with interleaved
246 throughput proportional to its weight, even if the throughput
260 receive a higher fraction of the device throughput.
266 allows a high throughput to be achieved, while still providing
274 got access to the device, the higher the throughput is.
284 guarantees the expected throughput distribution without ever idling
300 fairness) and throughput. For full details on how to choose the
301 desired tradeoff between service guarantees and throughput, see the
303 on how to maximise throughput, see slice_idle, timeout_sync and
333 throughput and making sure that the desired throughput distribution is
337 As for throughput, idling can be very helpful on highly seeky media
339 number of seeks and see improved throughput.
342 should see an overall improved throughput on faster storage devices
353 throughput and acceptable latencies.
369 where it is beneficial also for throughput, idling can severely impact
370 throughput. One important case is random workload. Because of this
372 beneficial also for throughput (as detailed in Section 2). As a
376 more important than guaranteeing maximum throughput. For example, in
378 than maximum throughput. In these cases, consider setting the
406 Setting strict_guarantees may evidently affect throughput.
456 DISABLE this mode if your only goal is to achieve a high throughput.
458 entail a lower throughput. To achieve the highest-possible throughput
468 increasing this time usually increases maximum throughput. On the
479 the algorithm, larger values increase the throughput in proportion to
489 reached a higher throughput by setting max_budget explicitly, i.e., by
520 the group lowers the throughput too much. This switch occurs on a
521 per-process basis: if a process of a leaf group causes throughput loss
552 throughput sustainable with bfq, because updating the blkio.bfq.*